# Research Papers — 2026-10 · bundle page 137 of 156 > Full-text markdown of papers #6801–6850 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/137 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/136.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/138.md) ### ResOPD: Tail Residualization for Sparse On-Policy Distillation Authors: Penghui Yang, Long Xing, Xuanlang Dai, Ziyu Liu, Kai Chen, Yuhang Zang Published: 2026-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.04882v1 On-policy distillation (OPD) trains a student model on self-generated trajectories, but transmitting dense teacher distributions across long reasoning traces creates prohibitive communication and memory bottlenecks. Practical systems therefore rely on sparse teacher interfaces, typically transmitting either the sampled-token score or a small Top-$k$ distribution. However, this sparse setting faces a fundamental dilemma: sampled-token estimators are unbiased but suffer from severe gradient variance, whereas directly optimizing Top-$k$ objectives introduces systematic bias. To improve this trade-off, we propose ResOPD (On-Policy Distillation with Tail Residualization), which provides unbiased full-vocabulary reverse KL gradient estimation under on-policy sampling, with substantial variance reduction under the same sparse payload in the evaluated settings. ResOPD aggregates the unobserved vocabulary into an observable coarse tail event, computes its exact aggregate gradient, and samples only the fine-grained within-tail residual, which requires no additional teacher queries or forward passes. Extensive experiments demonstrate that ResOPD substantially reduces gradient variance, stabilizes online training dynamics, and improves downstream performance across the evaluated settings. These results establish ResOPD as an efficient, plug-and-play variance reduction primitive for sparse on-policy distillation. --- ### Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense Authors: Zahra Aref, Sheng Wei, Narayan B. Mandayam Published: 2026-10-04 Categories: cs.CR, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2610.04878v1 Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets against a Deep Q-Network (DQN) attacker. We compare four defender settings: a human reward-only game operationalizing the DQN information structure, a human reward-plus-transition game operationalizing the Cognitive Hierarchy Theory-driven DQN (CHT-DQN) information structure, an automated DQN defender, and an automated CHT-DQN defender. In the reward-only game, participants receive payoff and reward feedback. In the reward-plus-transition game, they also see attacker-aware transition probabilities from the CHT-DQN model. Across 80 Mechanical Turk participants and matched automated simulations, human defenders adapted to outcomes in a way the automated defenders did not: they were more likely to reselect a node after a successful defense than after a failure, in both games, an asymmetry we interpret as consistent with Prospect Theory and Cumulative Prospect Theory. The 40-round average also mixes early rounds, where the DQN attacker acts mostly at random, with late rounds, where it mostly exploits; in the final stage, mean protection ranks the reward-plus-transition human game above the reward-only human game, then the automated CHT-DQN defender, then the automated DQN defender, an ordering the overall mean hides. By contrast, the reward-plus-transition game does not produce a statistically reliable overall gain in weighted data protection over the reward-only game. These results suggest that evaluating human-agent cyber-defense systems only by an averaged task score can miss behaviorally meaningful differences in adaptation, action allocation, and bounded human reasoning. --- ### SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models Authors: Chung-En Ho, Weiyu Sun, Cheng-Jhih Shih, He Li, Yong Liu, Yingyan Celine Lin Published: 2026-10-04 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.04875v2 Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch together with multiple draft branches in a single forward pass. While prior DLLM acceleration methods primarily exploit temporal redundancy across denoising steps, we identify a complementary redundancy axis within each speculative verification step: multi-branch computational redundancy. During speculative verification, draft branches inherit most tokens from their parents while unmasking a small set of additional positions, causing large portions of hidden states to remain highly similar across branches. We propose SpecFold, an algorithm-system co-design that exploits this multi-branch redundancy to reduce the cost of multi-branch speculative verification. Algorithmically, SpecFold performs token-level residual gating and selectively reuses parent computation through folded attention and FFN while preserving residual hidden states. Systemically, a Triton kernel implementation translates this fine-grained reuse into end-to-end throughput gains through efficient sparse multi-branch execution. SpecFold is orthogonal to temporal caching and compatible with existing DLLM speculation strategies. Across two DLLM families, five models, and five standard benchmarks, SpecFold achieves up to 1.64x throughput over Spiffy and up to 1.99x over vanilla decoding, while maintaining comparable task performance. --- ### When the noncommutative AM-GM inequality holds Authors: Yimin Zhong Published: 2026-10-04 Categories: math.PR, cs.LG, math.OC arXiv: https://arxiv.org/abs/2610.04874v1 In this note, we prove that the noncommutative AM-GM inequality holds if $n\ge 2\lceil m/2 \rceil^2$. The motivation comes from counterexamples constructed in (De Sa, Random reshuffling is not always better, NeurIPS2020). The proof constructs a vertex measure based on the Chebyshev nodes on the Boolean cube to extract the distinct indices. The main difficulty is that the measure is not positive on non-integer nodes. The key technique comes from (Grigoriev, Complexity of Positivstellensatz proofs for the knapsack, Computational Complexity (2001)) and eventually transforms the problem into a quadrature estimate. --- ### Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models Authors: Ji Zhang, Zixin Liu, Yiran Ding, Jiayi Wang, Yilu Du, Weijia Xuan Published: 2026-10-04 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2610.04869v1 An interaction has two parts: someone decides to act, and then chooses whom to act on. Temporal link prediction has concentrated on the second, and we show that it is blind to the first by construction: a standard negative keeps the real source and swaps the destination, and we prove that this cancels the source's activity exactly from the optimal score, so no model trained and evaluated this way is ever rewarded for learning it. Under the harder historical and inductive negatives, whose sources differ, the same factor becomes the dominant signal. We model it with Source Node Activity Modeling (SNAM), a self-exciting event intensity fitted by an exact point-process likelihood to decayed interaction counts the history states already contain; it has fewer than 20 parameters. On their own, never looking at the destination, these parameters beat DyGFormer and TPNet on four of five datasets under historical negatives. Added to the frozen scores of TPNet, TGN, DyGFormer and DSRD, four models of different design, without retraining anything, they raise AP on almost every backbone-dataset pair in both settings, by up to 25 points. Our full model ranks first overall against eleven baselines on 13 datasets and three protocols, and on million-event streams trains an epoch 9-100x faster than TPNet and DyGFormer. We conclude that source activity is a blind spot of temporal link prediction, and a cheap, transferable one to close. Code is available at https://github.com/Erutaner/Your-Temporal-Link-Predictor-Is-Blind-to-Who-Is-Active. --- ### From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory Authors: Zhixuan Tan, Pengjie Gu, Zhao Li, Yihan Hu, Xu He, Dong Li, Jianye Hao Published: 2026-10-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04868v1 Memory-augmented agents typically integrate procedural knowledge by injecting retrieved skills directly into text prompts. This approach dangerously equates readable text with reliable execution. To bridge this gap, we introduce From Memory to Guide, a novel paradigm that transitions procedural memory from passive text delivery to active, inference-time policy adaptation. We instantiate this paradigm through the Spatio-Temporal Composer, an active policy compiler that explicitly manages exactly how and when retrieved knowledge should be applied. Rather than treating skills as plug-and-play modules, Composer dynamically aligns historical knowledge with current environmental constraints (spatial adaptation) and precisely dictates its applicable lifecycle (temporal orchestration). It actively transforms static memories into strictly bounded Runtime Guides---equipping the agent with localized objectives and behavioral guardrails without requiring a single parameter update. Extensive evaluations on 13 demanding, long-horizon software engineering tasks in EngramBench demonstrate the clear advantages of this architecture. Composer not only robustly prevents context mismatch but drives an absolute pass-rate increase of 7.2 percentage points on the most complex tasks, while simultaneously slashing the main agent's token usage by 32.2%. --- ### Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design Authors: Jihwan Moon, Sheir A. Zaheer, Jinmyoung Lee, Gunhee Kim, Chan Y. Park Published: 2026-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.04867v1 Greedy block-wise local learning splits a network into gradient-isolated blocks trained by local auxiliary losses, deleting the backward pass between blocks: inter-stage communication becomes forward-only and every block can step its optimizer independently, properties directly relevant to decentralized model-parallel training. Local learning is competitive with end-to-end backpropagation on image classification, and on small Transformers it is known to trade a worse best loss for parallel speedup. How this loss gap behaves in autoregressive language model (LM) pretraining at larger scale, and which auxiliary designs reduce it, has not been measured. We present a token-budget-matched empirical study at 125M and 400M parameters with $K \in \{1,2,4\}$ blocks at Chinchilla-optimal budgets, factorizing the auxiliary design into network architecture and training objective. We observe: (i) the gap to end-to-end training more than doubles from $K=2$ to $K=4$, but at $K=4$ shrinks from 125M to 400M; (ii) replacing an MLP auxiliary with a Transformer-based one is a strong network-side intervention, recovering 22-41% of the gap; (iii) a multi-token-prediction (MTP) auxiliary objective helps at the first block boundary, whereas adding it at deeper boundaries hurts, and restricting it to the first block yields the best $K=4$ configuration ($+0.062$ vs. $+0.075$ nats at 400M); and (iv) deployment-style per-block execution reduces activation memory by up to $2.2\times$. We frame these results as an empirically grounded method direction rather than a finalized method: local objectives should apply future-predictive pressure selectively across boundaries while resisting shortcuts that bypass predictive content. --- ### Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning Authors: Haozhe Chi, Song Jin, Yang Jin, Yadong Mu Published: 2026-10-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.04864v1 Long-video embedding requires capturing sparse query-relevant evidence under a limited visual-token budget. Uniform sampling can miss brief events in videos spanning minutes or hours, whereas encoding more frames in a single context increases memory and computation. We introduce \textbf{Query-Aware Streaming Latent Reasoning} (QASLR), a post-training framework that accumulates evidence across clips while keeping the embedding size fixed. QASLR selects a bounded set of frames, restores their temporal order, and processes them clip by clip with a vision-language backbone. A compact set of persistent think tokens cross-attends to each clip's features, while an embed token reads out a normalized representation after every update. This design integrates evidence across multiple backbone calls without requiring all selected frames to share a single context. Training combines final contrastive learning, step-wise contrastive supervision, and final-embedding self-distillation. Intermediate supervision trains partial-video readouts for retrieval, while self-distillation regularizes them toward the final representation. Query-aware selection produces query-conditioned representations for candidate-set scoring and reranking, whereas query-independent selection enables reusable corpus indexing. Under the full training recipe, HourVideo retrieval Hit@1 increases from 54.2 to 70.7 and from 57.4 to 72.8 for 2B and 8B Qwen3-VL-Embedding backbones, respectively. Gains extend to the evaluated moment-retrieval and video-QA tasks, and the streaming head transfers to a second Qwen-family embedding backbone. These results support streaming latent aggregation as an effective approach to integrating long-video evidence into fixed-dimensional representations. --- ### GitSwarm: Decentralized Compounding Inference Authors: Vedant Shah, Ankur Samanta, Paras Dahal, Mikhail Plekhanov, Carole-Jean Wu, Scott Yih, Remi Munos, Rob Fergus, Jakob Foerster, Ruslan Salakhutdinov, Sanjeev Arora, Jason Weston et al. Published: 2026-10-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.04862v1 Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental findings, and unsuccessful approaches can inform later work, yet most inference-time computation is organized around individual trajectories or candidates rather than a persistent body of reusable work. We call this paradigm compounding inference: organizing inference-time computation so that intermediate work persists and can be inspected, extended, combined, or challenged by subsequent computation. We instantiate compounding inference in GitSwarm, an asynchronous system where homogeneous agents independently decide how to advance a task while collaborating through structured persistent memory. Agents explore, experiment, verify, refine, and synthesize previous work in a shared, branch-able Git repository. Atomic commits preserve intermediate artifacts, while explicit semantic dependencies record how later contributions build on work across branches. We evaluate GitSwarm on long-horizon problem solving and sustained GPU-backed experimental research. On IMOProofBench-Advanced, GitSwarm solves all 30 problems in one run using GPT-5.5. On ProgramBench, it achieves a $79.4\%$ mean score, versus $65.1\%$ for the strongest reported baseline under the stated budget. On three neural architecture research tasks (Residual Matrix Transformer, Looped Transformer, NanoChat), GitSwarm improves upon the starting architectures through successive experimentation. Beyond final performance, we measure whether computation accumulates: on ProgramBench, $94.7\%$ of contributions are subsequently built upon, while the selected solution's ancestry covers $82-93\%$ of the contribution graph. These results show that inference-time computation can accumulate across otherwise independent episodes, forming an evolving body of work that subsequent inference can reuse. --- ### Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate Authors: Haocheng Ye, Aoting Hu, Xinwei Zhang, Xunzhu Tang, Shuchao Pang, Jason Xue Published: 2026-10-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.04860v1 Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual errors induced or amplified by watermarking even when the required evidence is present in the context and the unwatermarked model can answer correctly. Using a controlled retrieval-augmented generation setting, we compare unwatermarked and watermarked generations under the same context, query, and decoding configuration, and quantify their factual accuracy decrease. Across six representative watermarking methods, including KGW, SWEET, DiPmark, GumbelSoft, Gumbel-Max, and SynthID watermarking, we consistently observe watermark-induced hallucination. Watermarked outputs can remain fluent while introducing factual errors. We attribute this failure mode to two mechanisms: (1) token perturbations in the current-step arising from method-specific reweighting or keyed sampling, and (2) prefix-induced attention drift, which accumulates through autoregressive decoding and weakens later attention to the factual context. Motivated by this analysis, we propose two plug-in interventions at the token and attention levels that can be integrated into existing watermarking methods to improve factuality. At a matched TPR of 0.90 at 1% FPR, combining the two interventions reduces factual errors by approximately 90% relative to watermark-only decoding while preserving fluency and comparable decoding efficiency. Overall, this work highlights factuality as a first-class criterion in watermark evaluation, alongside detectability and robustness, and calls for careful factuality validation before deploying watermarks in fact-critical applications. --- ### One Tile, Multiple Instances: Rethinking MIL for Sparse Diagnostic Evidence Authors: Runsheng Liu, Cheng Jin, Hao Jiang, Hao Chen Published: 2026-10-04 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.04853v1 In weakly supervised Whole Slide Image (WSI) classification, feature extractors typically compress each image tile into a single global embedding. Consequently, slide-level aggregators are restricted to this coarse tile scale, concealing fine-grained sub-tile evidence from the attention mechanism. We introduce DI-MIL, a framework that decouples encoding context from instance granularity through decomposed instances. By clustering dense spatial tokens from a frozen foundation model within each tile, DI-MIL converts a single tile into multiple independently weighted instance embeddings. As a training-free post-encoding module, DI-MIL integrates seamlessly into existing pipelines without requiring re-encoding or downstream architectural modifications. We evaluate DI-MIL on cytopathology, a challenging testbed where sparse diagnostic signals are easily diluted within standard tiles. Across four datasets, three frozen foundation models, and two attention-based aggregators, DI-MIL demonstrates consistent efficacy, improving 67 of 72 metric-level comparisons, with the largest mean gains reaching 3.64 points under cytopathology-specific backbones. In a broader comparison against seven representative MIL baselines, DI-MIL paired with ACMIL achieves highest mean performance in 33 of 36 backbone-dataset-metric comparisons. Ablations show that direct smaller tiling inflates the extracted tile count by up to 43.3$\times$ with non-monotonic performance, whereas DI-MIL incurs zero additional image-extraction overhead while achieving the strongest overall results. These results establish instance construction as an orthogonal design dimension in MIL, supporting DI-MIL as a cost-efficient solution under sparse diagnostic evidence. --- ### CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery Authors: Tao Feng, Fangxu Yu, Zijie Lei, Jiaru Zou, Changjiang Jiang, Yi Yan, Jiaxuan You, Pan Lu Published: 2026-10-04 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.04851v1 Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large language model (LLM) can reuse previous solutions in context, but cannot update the model from its successes and failures on the test problem. Reinforcement learning (RL) enables such adaptation; however, strongly favoring high-reward trajectories may suppress low-reward yet potentially promising directions too early. We introduce CURIO, a curiosity-driven test-time learning framework that complements task feedback with an Intrinsic Curiosity World Model (ICWM). The ICWM learns transitions in the policy's hidden-state representation and supplies prediction-error bonuses at sampled tokens outside the policy's top-k choices. Epoch normalization and an annealed weight regulate their contribution to the policy update. On six mathematical discovery tasks and single-cell denoising with Qwen3 backbones from 8B to 235B, three-run means improve over a matched task-only RL control on five mathematical objectives, match the best reported performance on Circle Packing, and improve denoising Score and mean squared error (MSE) on both held-out corpora at every tested scale. Relative gains reach 18.3% on Hadamard and 10.8% on denoising Score. Code-diversity measurements show greater structural variation among generated programs, supporting curiosity as a complementary exploration signal for learning in open-ended discovery. --- ### PIT-GCL: Protein Interaction using Topological Graph Contrastive Learning Authors: Jae Won Choi, Ryoonki Hong, Alan Liang, Manjula Adiveppa Wader, Bingsong Zeng, Peiyang Tang, Longwei Liu, Ruishan Liu Published: 2026-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.04850v2 Protein binding prediction is central to target identification, therapeutic binder design, and large scale screening, yet remains challenging because binding depends on sequence, three dimensional geometry, and global structural organization. Recent folding models such as AlphaFold3 and Boltz-2 have substantially improved structure prediction, but their confidence outputs (pLDDT, pTM, ipTM) are not specifically designed for binary binding prediction, and dedicated structure aware predictors often require bound complex structures that are unavailable at screening scale. We introduce PIT-GCL, a dual tower structure aware framework that encodes each protein independently from its amino acid sequence, Cα point cloud, and a global persistent homology descriptor. Each tower combines residue ESM-2 embeddings with a topological summary computed from the H0 and H1 persistence landscapes of a Vietoris-Rips filtration, and processes the resulting tokens with a structure aware Transformer in which pairwise Cα distances enter as a learned attention bias. A bidirectional cross attention module then performs latent space soft docking between the two per-protein representations, and the model is trained with a combined binary cross entropy and NT-Xent contrastive objective. On three binary interaction prediction benchmarks, general PPI on PPIRef, TCRpMHC binding on STAG, and whole chain pairs on PPB-Affinity, PIT-GCL outperforms representative sequence based, structure aware, and task specific baselines on general PPI under our evaluation, and is the only method above chance on PPB-Affinity; on TCR-pMHC it leads at a fixed decision threshold but is outranked by a task specific sequence model. Because each protein is encoded independently in the first phase, its representation can be precomputed and reused across candidate pairs, which is convenient for large scale screening. --- ### Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution Authors: Minjae Lee, Kyunghyun Cho, Sangdon Park Published: 2026-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.04845v1 Aligning large language models (LLMs) with human values is important for safe, efficient, and beneficial AI deployment. However, human values are multifaceted: helpfulness, harmlessness and humor trade off against one another, and different users want different trade-offs. Multi-objective alignment (MOA) addresses this by training a policy that can provide any point of the Pareto front, but existing methods either train one model per preference, interpolate a few separately aligned experts post hoc, or train a single conditioned model without considering which preferences it should be trained on. Since the hard regions of the preference simplex depend on the objectives at hand, existing methods leave them under-trained and do not get the most out of a single model. Therefore, we propose MAESTRO (Multi-objective Alignment via End-to-end STeering and Robust Optimization), which formulates MOA as a minimax problem over preference distributions and trains a single prompt-conditioned policy end-to-end with RL against an adversarial preference distribution: a Dirichlet distribution updated by online mirror descent toward the preferences the current policy serves worst, rather than on a fixed one. On HH-RLHF, BeaverTails and a summarization task, with up to three objectives, MAESTRO attains the best Pareto front on most tasks in a single training run, at the lowest training cost among the compared methods. The largest margins appear in the hard regions that a fixed preference distribution leaves under-trained, confirming that a single prompt-conditioned model is capable of covering the objective trade-offs on its own. --- ### MemTrace: State-Consistent Memory for Long-Horizon Coding Agents Authors: Hongming Xu, Le Zhou, ZhongHe Jin, Xiang Zhang, Bo Tang, Zhiyu Li, Xuanhe Zhou, Juncheng Zhang Published: 2026-10-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04838v3 As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can invalidate earlier execution evidence. Existing approaches address these challenges through techniques like larger context windows, compression, retrieval, or repository representations, but often fail to reconstruct a consistent task state after a context refresh or verify whether recalled evidence remains valid. Thus, we introduce MemTrace, a provenance-aware memory system that preserves execution history and aligns its reuse with the evolving task (e.g., iterative cross-file repair) and repository state. MemTrace stores history as immutable Memory Traces anchored to key information (e.g., files, symbols, tests), and organizes their execution order and dependencies in a Memory Trace Graph. When context is constrained, working memory retains only compact Memory Anchors, from which the agent can reconstruct the latest execution state and locate evidence relevant to its next action. Before restoring historical evidence, MemTrace checks its validity against the current repository state and retrieves only what the next action requires. Across three complementary long-horizon coding benchmarks, MemTrace consistently outperforms all fully evaluated baselines under the same backbone and harness, improving DeepSWE pass@1 by 21.2 points, SWE-EVO Resolved Rate by 4.4 points, and SWE-Milestone Score by 17.8 points under Codex CLI. --- ### RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents Authors: Fuyuan Liu, Nayu Liu, Wenhao Yu, Peijin Wang, Yingchao Feng, Fanglong Yao, Liang Wan, Wei Feng Published: 2026-10-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04836v1 Remote sensing agents rely on perception, measurement, and raster analysis tools to solve Earth observation tasks. We refer to their judgments and quantitative results about ground objects as tool observations. However, these observations are subject to substantial uncertainty and may be incorrect even when the tools execute successfully. When agents accept incorrect observations, the errors can propagate through subsequent reasoning and cause task failure. We analyze 1,229 execution trajectories across three remote sensing agent benchmarks. On each benchmark, at least 88.1% of tasks depend on tool observations. Among these tasks, at least 22.7% contain incorrect observations despite successful tool execution. These errors propagate to the final answer in at least 82.0% of affected tasks on each benchmark. To address this problem, we propose RSure-Agent, a framework for verifying tool observations and limiting error propagation. We introduce a verifiable observation protocol that requires tools to return process evidence for the agent to verify their observations. We also construct a task-tool reliability prior from offline task feedback. The prior summarizes each tool configuration's past performance across task types and provides a task-specific reference for verification. Using process evidence and this prior, RSure-Agent decides whether to accept an observation, request additional evidence, or reject it. We evaluate RSure-Agent on EarthBench, ThinkGeo, TerraLogic, and CHOICE-420. Across the three agent benchmarks, RSure-Agent reduces the error propagation rate by 21.3 to 25.9 percentage points relative to the base configuration with verification and the prior disabled. On CHOICE-420, it improves overall accuracy over direct answering by 5.71 percentage points on average across 11 backbone models. On EarthBench, it reduces the tool-call ratio by 25.9% relative to Earth-Agent. --- ### Cluster Validation Indices as Self-Supervised Objectives for Text Representation Learning Authors: Kishor Kumar Bhaumik, Nicolas Roque dos Santos, Neil Shah, Jia Chen, Evangelos E. Papalexakis Published: 2026-10-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.04830v1 Self-supervised fine-tuning refines the embedding space of a pretrained language encoder without labels. However, the commonly used approaches are computationally expensive. Specifically, contrastive learning-based methods need multiview data and in-batch negative examples, while negative-free approaches require auxiliary graphs/networks. An interesting question arises: can self-supervised fine-tuning be done without relying on either additional negatives or graph data? To answer this question, we introduce SilK (Silhouette-guided K-means), which trains on a Cluster Validation Index, an internal measure of cluster quality without using labels. SilK clusters the corpus and then regresses a simplified silhouette toward a target value. Each document is compared only against the k cluster centroids, never against other documents, so the method needs no augmentation, no negative pairs and one view per document. On BERT-base, SilK trains 1.46x faster per epoch than the fastest baseline we evaluate and uses 45.4% less peak GPU memory than the leanest one. Under frozen-encoder linear probing, SilK stays competitive with the best baselines on three downstream tasks. --- ### Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search Authors: Benji Xu, Ken Zheng, Noah Han Published: 2026-10-04 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.04829v1 When an agentic prover works on an open problem, there is no proof assistant to fall back on: its verifier and lemma library are ultimately language models judging model outputs. We instrumented such a system end to end and analyzed $51{,}754$ traced observations across three full runs ($186$ hours, \$$5{,}694$). We find three connected failure modes. First, the three-model verifier requires unanimity and treats parse or API failure as non-approval; in $10$ of $12$ verification events, one member returned no parseable output or an API error, making acceptance arithmetically impossible without surfacing an error. Second, when the ensemble did function, one verifier approved $3$ attempts that GPT rejected, each claiming to resolve the open problem; a single-verifier design would therefore have announced a solution three times. Third, because nothing could be approved, every review was a refutation, yet the lemma extractor mines reviews as well as proofs: $24$ of $93$ lemmas ($26\%$) were extracted from rejected arguments with their refutational context removed. Taken together, these findings show that without external verification, supervision is itself a critical trust boundary: systems must distinguish abstention from rejection, preserve useful disagreement, and preserve the provenance and polarity of information before it becomes future context. --- ### GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory Authors: Xiaoyun Yu, Xiangfei Qiu, Yonggui Huang, Shixiang Tang, Nanqing Dong, Wanli Ouyang, Geguang Pu, Honggang Qi, Jilin Hu, Xi Chen Published: 2026-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.04827v1 Time-series foundation models (TSFMs) enable zero-shot forecasting through large-scale cross-domain pretraining, while retrieval augmentation further improves their performance by leveraging historical information. However, existing methods typically correct TSFM forecasts using the ground-truth futures of similar historical windows, which contain both predictive components already captured by the foundation model and sample-specific random fluctuation that is difficult to transfer. In contrast, recurring systematic model bias within prediction errors more directly characterizes the failure modes of a frozen TSFM and therefore provides more valuable correction signals. Effectively exploiting such model bias, however, poses two challenges: prediction errors at different numerical levels are difficult to compare due to scale differences, and the recurring bias must be extracted from prediction errors contaminated by random fluctuation. To address these challenges, we propose GRAM, a general retrieval-augmented framework for frozen TSFMs. GRAM first introduces an Amplitude Memory Module (AMM) that scales prediction errors by amplitude and aggregates them into retrievable prototypes. It then employs a Prototype Graph Module (PGM) to model relations among prototypes to aggregate consistent bias information while suppressing random fluctuation. During online forecasting, GRAM retrieves and expands prototypes relevant to the current query and generates per-horizon corrections to refine the original TSFM forecast. Experiments across multiple datasets and foundation models demonstrate consistent forecasting improvements. --- ### DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring Authors: Sayantan Pal, Kaiyi Ji, Rohini K. Srihari Published: 2026-10-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.04825v1 Fluent guidance is not the same as useful intervention. LLM tutors are typically trained to generate the next teacher utterance, implicitly assuming that every student turn warrants a response. However, our experiments indicate that this conflates tutoring capability (what to say) with intervention necessity (whether to say it). We introduce DICE, a framework that decouples intervention decisions from response generation by first selecting an explicit pedagogical action. To calibrate this action selection policy, we define Intervention Value (IV), a rollout-grounded counterfactual metric that compares each action against non-intervention. IV shows that many prescribed interventions provide little or no marginal benefit. We further introduce DICE-Bench, a multi-variant math tutoring benchmark with skill-preserving problem variants for session-level evaluation. Using IV-weighted and KL-regularized policy optimization, DICE learns to intervene selectively while preserving tutoring effectiveness. In simulated tutoring sessions, DICE reduces the over-intervention rate to near zero while guiding students to correct solutions in approximately 3-4 fewer turns on average than existing Socratic tutoring baselines. --- ### Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications Authors: Peng Qi, Chunliang Lyu, Gang Li, Fabian Chan, Cheng Chang, Ignacio Cases, Will Lu Published: 2026-10-04 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2610.04824v1 AI agents based on foundation models (FMs) have demonstrated strong capabilities to perform complex open-ended tasks. However, they face some common challenges in practice: (a) agent behavior can deviate drastically even for semantically similar tasks, leading to catastrophically propagated errors; (b) high cost and latency due to FM calls, repeated in full whenever a task recurs with different inputs; (c) FMs' limited context and instruction following capability confine how well agents manage the ever-growing execution context and follow complex plans. We introduce $\textbf{A}$gent $\textbf{B}$ehavior as $\textbf{C}$ode $\textbf{Agent}$ (ABCAgent), which uses a symbolic program (e.g., Python code with potential neural functions) to fully specify the agent's behavior at runtime, with a powerful FM agent editing that program for flexibility. Behavior is thus specified without premature variable binding, and its execution is deterministic. We evaluate ABCAgent on six agent benchmarks, two of which we construct to test how well a derived program generalizes to variants of the task it was written for. ABCAgent matches a model-matched neural agent on GAIA and augmented GAIA, and surpasses it where robustness and long control flows matter: 98.3% against 97.3% on GSM-Symbolic ($p = 0.001$), 71.9% against 47.4% $\mathrm{Pass}^4$ on the telecom domain of $τ^2$-bench ($p = 0.0001$), and more records written correctly at every loop length on our control-flow-augmented WorkArena benchmark. For more parametric task families, ABCAgent is also significantly superior in efficiency. Without authoring a new program, ABCAgent solves 92.6% of GSM-Symbolic instances and 20.1% of augmented GAIA variants, which yields $5.2\times$ lower latency and $7.0\times$ lower cost on GSM-Symbolic, 19% lower cost on augmented GAIA, and $9.5\times$ lower agent latency on $τ^2$-telecom. --- ### Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics Authors: Rajneesh Anand, Mayuresh V. Kothare Published: 2026-10-03 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.08852v1 Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms. A critical instance is autonomous droplet transport on an open surface, where contact-angle hysteresis, capillary pinning, and surface heterogeneity produce partially observable dynamics that pose significant challenges for classical model-based controllers. We introduce the first robotic platform for closed-loop autonomous liquid droplet navigation on an open, unconfined surface using model-based reinforcement learning. A two-axis tilting board coated with a thin silicone oil film drives the droplet, while an overhead camera provides real-time feedback. A learned policy was trained on just 50 to 150 physical episodes depending on geometric complexity, without simulation or analytical models. Beyond performance alone, the platform demonstrates three capabilities of interest to the SDL community: it robustly transfers zero-shot to unseen geometries; it autonomously discovers an oscillatory depinning strategy to free the droplet when it sticks; and it completes its full training pipeline in under 90 minutes. These results extend reinforcement-learning manipulation from rigid microrobots to deformable soft-matter systems for next-generation SDLs. --- ### QuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance Authors: Yiping Bai Published: 2026-10-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.08851v1 Quantifying language distance among closely related languages remains a core challenge in quantitative linguistics. Our previous work (1) introduced QuanLing (Quantitative Linguistics via Pretrained Language Models), a quantitative framework combining language distance metrics (sentence embedding distance, tokenization fragmentation rate) with language property analysis (MLM prediction probability), validated on North Germanic (Danish, Norwegian Bokmål, Swedish). This paper extends QuanLing to Western Romance--French, Portuguese, Spanish, Italian--testing cross-branch applicability with the same metric family and aggregation protocol as our North Germanic study, adapted for four languages (English anchor, quadruplet construction). Using 150 four-language parallel sentences, we compute LaBSE sentence embedding distances, tokenization fragmentation rates from four monolingual BERT tokenizers, and mBERT masked language model mutual intelligibility. Results show that Portuguese--Spanish are closest (LaBSE distance 0.0229), French--Italian most distant (0.0338); LaBSE and mBERT rankings agree on 4 of 6 pairs, confirming cross-model robustness. Western Romance shows a wider absolute distance span than North Germanic (0.011 vs. 0.008) but comparable relative ratios (1.48 vs. 1.67), consistent with longer divergence time. French exhibits notably higher MLM predictability (36.12% top-1 accuracy vs. 29.28% for Italian), reflecting its orthography--phonology decoupling. This cross-branch validation provides further evidence for QuanLing's generalizability beyond a single language branch. --- ### Uncertainty in Representation Learning on Knowledge Graphs Authors: Yuqicheng Zhu Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06974v1 Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchmark performance, their predictions often lack principled reliability guarantees, limiting their use in high-stakes applications. Moreover, uncertainty arises throughout the KGE pipeline, from incomplete or probabilistic input knowledge to stochastic training and prediction. This thesis systematically investigates three sources of uncertainty in KGE: knowledge uncertainty, arising from incomplete, noisy, or probabilistic input knowledge; algorithmic uncertainty, induced by randomness in model training; and predictive uncertainty, concerning the reliability of model outputs. To address algorithmic uncertainty, the thesis demonstrates that models trained under identical settings can produce substantially different predictions and introduces a voting-based aggregation framework to mitigate this instability. To quantify predictive uncertainty, it adapts conformal prediction to KGE, constructing answer sets with distribution-free coverage guarantees and extending them to provide predicate-conditional reliability guarantees. To support reasoning under knowledge uncertainty, it develops statistically valid prediction intervals for confidence-scored triples and an embedding-based approach to approximate probabilistic reasoning over statistical ontologies with formal soundness guarantees. Together, these complementary, model-agnostic methods provide a practical and theoretically grounded approach to uncertainty in KGE, advancing beyond predictive accuracy toward reliable and uncertainty-aware knowledge graph reasoning. --- ### Event Cameras for Melt-Pool Monitoring in Additive Manufacturing: A Benchmark and a Cross-Machine Transfer Analysis Authors: Mohamad Yazan Sadoun, Sarah Sharif, Yingtao Liu, Zahed Siddique, Yaser Mike Banad Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06973v1 Melt-pool monitoring is central to qualifying metal additive manufacturing (AM), yet no public event-camera benchmark exists for this domain. Event cameras report per-pixel brightness changes with microsecond timing instead of reading full frames, giving the temporal resolution AM transients demand at a fraction of the data rate. We present SynAM-E (Synthetic AM Events), the first public multi-source simulated event-camera benchmark for metal-AM melt-pool monitoring: 85 physics-calibrated event shards from 15 sources across 8 institutions, with public baselines and fixed cross-machine evaluation splits. On a single-machine case study, event-spatial monitoring matches dense-frame accuracy (0.874 versus 0.863 macro-F1), and the absolute intensity that events discard adds only +0.006 under fusion. On the NIST Additive Manufacturing Metrology Testbed (AMMT) build, a near-sensor event-rate counter recovers a raw-frame-confirmed 528.7 Hz intensity oscillation at ~380 times less sensor readout than the frame stream requires. A compact 93 k-parameter spiking model runs at 15 times lower modeled inference energy for a 0.073 macro-F1 cost. Every cross-source task includes a built-in trust test against camera identity shortcuts: process-type classification passes while material classification remains confounded by camera band, a corpus-structural limitation the release documents and the trust test exposes. --- ### BoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action Feedback Authors: Xu Dong, Wanqing Li, Anthony Adeyemi-Ejeye, Andrew Gilbert Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06972v1 Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual understanding and multimodal reasoning, yet they remain fundamentally limited in Human Action Feedback Generation. Existing methods infer coaching feedback directly from visual observations, producing generic advice, limited interpretability, and physically implausible hallucinations. In contrast, expert human coaches diagnose performance through explicit biomechanical reasoning over joint kinematics, posture, and body dynamics. We introduce BoT-Feedback, a framework that grounds MLLM reasoning in structured biomechanical evidence. Our key contribution is Biomechanics of Thought (BoT), a four-stage reasoning framework that progressively identifies the action, localises the critical body regions, analyses quantitative biomechanical differences between expert and student performances, and synthesises interpretable coaching feedback. To support this reasoning process, we develop a plug-and-play Biomechanical Data Parser (BDP) that converts videos into structured biomechanical descriptors and an alignment strategy that temporally matches expert and student motions. We further introduce BiomAF, a benchmark containing paired teacher-student videos, 3D skeletons, biomechanical attributes, and expert-coaching annotations. Experiments across twelve open- and closed-source MLLMs demonstrate that grounding reasoning in biomechanical evidence consistently improves feedback quality, interpretability, and robustness while substantially reducing biomechanical hallucinations. BoT-Feedback improves the average expert evaluation score from 2.07 to 2.95 (+40%), enabling compact open-source MLLMs to approach the performance of substantially larger proprietary systems for explainable action feedback generation. --- ### AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems Authors: Muhammad Bilal Awan, Zubair Hussain, Abdul Shahid Published: 2026-10-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.06971v1 Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Present observability tools only raise alerts but for human engineers, resulting in a high Mean Time to Repair (MTTR) and operational fatigue. In this paper we propose AegisFlow (Agentic Engine for Intelligent Self-healing and Graph-driven Operations for Workload remediation), a novel agentic framework that closes the loop between detection and resolution. AegisFlow uses a Watchdog agent to collect runtime telemetry and has a Repair agent to automatically create, test and deploy code patches based on Large Language Models (LLMs). The framework presents the non-intrusive execution model called Parallel Shadow Patching, a non-intrusive execution model based on the Monitor, Analyze, Plan, Execute, Knowledge (MAPE-K) loop to generate and verify patches in digital twin environments. Through experimental testing, we have evaluated AegisFlow across five common failure scenarios, and see 98.1 percent improvement in MTTR (from an average of 170 minutes per patch to 3.2 minutes) and a patch success rate of 92 percent . In particular, the system is successful in dealing with changes in the JSON schema (96 percent ) and punctuation drift (98 percent ), and is least successful in Shadow DOM cases (85 percent ). AegisFlow frees up about 98 percent of data engineering on-call time from firefighting and reallocates it towards innovation. The framework is deployment agnostic consisting of a system that can be deployed in a plugin fashion into an existing pipeline orchestration system with minimal uplift to the existing system. --- ### EVFormer: An Egocentric Vision-EMG Bidirectional Attention Model for Bimanual Hand Pose Estimation Authors: JiaCheng Ge, SiYu Zhang, ShengJie Li, XinTong Yang Published: 2026-10-03 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2610.06970v1 Egocentric bimanual hand pose estimation is important for virtual interaction, wearable control, and rehabilitation, but visual observations are often degraded by self-occlusion, hand-hand contact, and object manipulation. We propose EVFormer, a multimodal framework that combines the current RGB frame with the preceding 200 ms of bilateral wrist surface electromyography (sEMG) to estimate 44 finger and wrist joint angles. EVFormer separately encodes visual spatial features and sEMG temporal features, enables cross-modal information exchange through sequential bidirectional cross-attention, and integrates the two modalities using feature-wise gated fusion. We evaluate EVFormer in a single-participant feasibility study using one synchronized public EgoEMG recording with chronologically separated training, validation, and test splits. On 296 test samples, EVFormer achieves a mean absolute error of 11.482 degrees, compared with 13.228-13.610 degrees for vision-only, sEMG-only, late-fusion, and training-mean baselines. This corresponds to relative error reductions of 13.20% compared with the vision-only model and 14.23% compared with late fusion. EVFormer also achieves the lowest error in four of the five evaluated gesture classes. These results provide preliminary evidence that feature-level interaction between egocentric vision and sEMG can improve bimanual hand pose estimation. Further evaluation across participants, recording sessions, sensor placements, and real-world interaction conditions is required to establish the generalizability of the approach. --- ### APEX: Active Protection at Execution Boundaries for LLM Agents Authors: Xinran Zheng, Xin Fan Guo, Zhiqiang Hao, Fan Yang, Xingzhi Qian, Jiawei Du, Jinfeng Xu, Zheng Xing, Shuo Yang, Xingjun Wang Published: 2026-10-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.06966v2 Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind them. We instead shift defense from covering attack patterns to one stable point: whatever the carrier and however the injection propagates, harm materializes only at the \emph{execution boundary}, where the agent turns internal state into an external action or released output. Safety there turns on two conditions, both settled by the trusted task rather than by the run: whether the proposed effect is authorized, and whether the runtime information reaching it is endorsed by that task. We present APEX, an active defense that enforces both at this boundary from a single authorization contract compiled before untrusted execution: \emph{evidence-gated prevention} admits an effect only when the contract justifies it, while \emph{deception-based exposure} makes unendorsed use reveal itself before the effect commits. Protection therefore follows from what the task permits rather than from how an attack is built, and applies uniformly across capability units without attack-specific policies or taint tracking. Against 13 baselines, APEX attains 0\% attack success on five of six benchmarks and 0.56\% on the sixth, holds 0\% under adaptive attacks on all three capability-unit types, and remains effective across defender backbones. Code is available at https://github.com/ZhengXR930/APEX_official/tree/official. --- ### Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction Authors: Bowen Ye, Yongchao Xu, Junkai Ma, Xiang Yin, Wenzhao Li Published: 2026-10-03 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.06964v1 Large language model (LLM) agents have demonstrated strong capabilities in interactive environments, yet their ability to continually evolve from experience remains limited. Although fine-tuning enables adaptation, its dependence on parameter access and high computational costs restrict its flexibility, especially for large-scale and closed-source LLMs. External memory offers an alternative by allowing agents to accumulate experience without modifying model parameters. However, existing methods mainly focus on experience representation and organization, while the acquired knowledge remains tightly coupled with specific tasks and contexts, limiting generalization. A key challenge is how to transform concrete interactions into abstract and reusable knowledge that guides future decisions beyond individual experiences. To address this challenge, we propose SAGA (\underline{\textbf{S}}elf-evolving \underline{\textbf{A}}gents through Experience-\underline{\textbf{G}}rounded \underline{\textbf{A}}bstraction), a framework for experience-grounded knowledge abstraction and utilization in LLM agents. SAGA progressively transforms interaction trajectories into episodic descriptions, reusable procedures, and principles with explicit applicability conditions, while maintaining links to execution evidence. Retrieved principles are instantiated into task-specific guidance and used to refine candidate actions through corrective feedback and resampling. This creates an execution--abstraction feedback loop, where accumulated knowledge guides future interactions and new experiences continuously update hierarchical memory. Experiments on ScienceWorld and ALFWorld demonstrate improved task performance, with ablation studies highlighting the importance of contextual instantiation and action regulation for leveraging principle-level knowledge. --- ### WavePrune: One period is often enough for RoPE Authors: Guancheng Du, Luotian Huang, Shaowen Wang, Si Li, Kaifeng Lyu Published: 2026-10-03 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2610.06963v1 Rotary Position Embedding (RoPE) encodes token positions by rotating each two-dimensional channel of the query and key vectors at a channel-specific frequency, making the attention logits invariant to a common shift of positions. However, this rotation is periodic, and it leads to position aliasing where relative positions separated by a full rotation period become hard to tell apart. To address this, we propose WavePrune, which restricts each channel to its first rotation period. We show that it removes the distractions in attention maps created by position aliasing and improves overall long-context performance. Specifically, WavePrune raises the HELMET score on four of five models we test without any extra tuning (e.g., 35.7 -> 40.0 on Qwen3-8B). When pretraining models from scratch, WavePrune also achieves lower validation loss at extrapolated lengths than pretraining without it. Because WavePrune restricts each channel to a sliding window, it induces a fine-grained sparsity that our hardware-aligned CUDA kernels exploit for 1.15x prefill and 1.24x decoding speedups over FlashAttention-2 at 32K context. Together, these results show that RoPE's periodic structure, widely regarded as essential, is largely redundant beyond the first rotation period. --- ### Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery? Authors: Nishanth Nayakanti, Prasang Gupta, Ashutosh Bilthare, Kevin Paul Published: 2026-10-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.06962v1 In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than recording the decision. We measure how much of that evidence a small language model can recover when it is post-trained on the verdicts alone, with no human evidence labels at any stage. On ContractNLI the human evidence spans are held out until evaluation. Matching the recorded verdict and agreeing with those spans are not the same thing: across six systems the two scores are only weakly related and rank the systems differently, so accuracy is a poor guide when the citations have to be reviewable. Label-only training on the bare verdict reaches accuracy 0.896 and span F1 0.564. Rejection sampling, which keeps a generated trace only when its verdict matches the record and then picks one by an automatic source-grounding score, reaches 0.797 and 0.556, against 0.747 and 0.493 before training. Verbatim citation rises from 0.597 to 0.729 under label-only training and to 0.701 under rejection sampling. One seed on one corpus cannot say which method is better, but both improve the evidence without anyone annotating it. --- ### DistScene: Object-to-Scene Distillation for 3D Scene Generation Authors: Kunming Luo, Hongyu Yan, Ken Deng, Chengcheng Zhou, Tianyu Liu, Haipeng Li, Haibin Huang, Xuelong Li, Ping Tan Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06960v1 We present DistScene, a framework for single-image compositional 3D scene generation by jointly modeling the environment and individual objects. Unlike existing methods that represent scenes primarily as collections of objects, we model the environment as an explicit scene component to provide geometric context for object placement. Specifically, we introduce Scene-Frame Generation, which jointly generates separate environment and object components in a shared coordinate frame, allowing their geometry and relative placement to be learned together. Then we introduce Object-Centric Refinement to refine each object in a local frame with scene context. Finally, we develop Object-to-Scene Distillation to transfer pretrained object-generation priors to scene generation through automatically composed and rendered synthetic scenes. Evaluations on indoor and outdoor benchmarks demonstrate improved scene-level spatial coherence over the evaluated baselines. Project page: https://coolbeam.github.io/DistScene/ --- ### EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling Authors: Jianan Pan, Yiwen Gu, Xinze Li, Rui Wang, Kejie Huang Published: 2026-10-03 Categories: cs.CL, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2610.06956v1 Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especially emotion, remain difficult to preserve. Existing systems typically rely on entangled acoustic representations, which allow the underlying language model to depend excessively on recovered lexical content instead of grounding its behavior in acoustic-prosodic evidence. We address this limitation with EMODE, an emotion-aware speech language model built around \textbf{Dynamic Para-Semantic Experts (DPSE)}. DPSE decomposes continuous speech features into semantic and paralinguistic pathways, routes them dynamically, and fuses them before integration into the language model. To turn this structural decomposition into functional specialization, EMODE is trained with a three-stage curriculum consisting of semantic warm-up, paralinguistic activation, and joint refinement, guided by Orthogonal Expert Guidance (OEG), Semantic-to-Acoustic Alignment (SAA), and Gating Diversity Regularization (GDR). Experiments on SER test, empathetic response evaluation, and the newly constructed bilingual MEPA benchmark show that EMODE improves the balance between lexical fidelity and emotional sensitivity, strengthens affect-grounded response generation, and exposes the value of explicit para-semantic factorization for robust cross-corpus emotion understanding. --- ### ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perception Authors: Ruoxuan Feng, Yutong Chen, Ruihua Song, Huan Yang, Zhongyuan Wang, Guocai Yao, Di Hu Published: 2026-10-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.06955v2 Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we naturally interact with the environment by deciding what information is missing, how to acquire it, and when sufficient evidence has been obtained. In stark contrast, existing multi-sensory robot systems mainly integrate sensory inputs rather than actively acquiring missing evidence through interactions. In this work, we introduce ROMA, an LLM-based system for Real-World Object-Centric Multi-Sensory Active Perception. ROMA integrates vision, audio, tactile, and force sensing into a reasoning-interaction-feedback loop. The model identifies missing evidence and determines the target objects, interactions, and modalities, while a physical interface executes the selected interactions and collects the multi-sensory feedback. To support this capability, we construct ROMI-2K, a large-scale real-world multi-sensory object interaction dataset covering nearly 2,000 objects and 6 atomic interactions with synchronized sensory feedback. Building on these data, we develop a two-stage training framework that aligns sensory modalities and equips the LLM to assess evidence sufficiency, select informative interactions, and reason over the multi-sensory feedback. We further characterize active perception as perception chains, where acquired evidence guides subsequent interactions and reasoning, and establish ROMA Bench to evaluate single-attribute, long-horizon multi-attribute, and intent-driven active perception. Experiments show that ROMA can actively acquire missing evidence and solve complex, long-chain multi-sensory perception tasks that existing methods struggle to handle, laying a strong perceptual foundation for active multi-sensory embodied agents. --- ### Do Neural PDE Solvers Learn the Right Dynamics? Authors: Haonan Li, Yue Song, Bin Yang, Kaihong Luo Published: 2026-10-03 Categories: cs.LG, nlin.CD arXiv: https://arxiv.org/abs/2610.06952v1 Neural PDE solvers can achieve low prediction errors, but do they reproduce the dynamics of the systems they model? Prediction scores alone offer an incomplete answer: they measure agreement with reference solutions but provide limited insight into how errors accumulate, nearby states diverge, or extreme events arise. We propose an evaluation framework that directly examines these behaviors in deterministic and stochastic neural solvers. By evolving ensembles of nearby initial states and comparing them with direct numerical simulation, we assess three complementary aspects of learned dynamics: error formation, ensemble geometry, and extreme events. Experiments on two-dimensional Kolmogorov flow reveal limitations that conventional scores can obscure. Smaller trajectory errors can reflect weaker error amplification despite less accurate local updates. Models can match an ensemble's overall spread and effective dimension while failing to capture the spatial directions where nearby states diverge. Similarly, matching overall event frequencies can conceal failures to predict persistent extreme events. These findings show that improved prediction accuracy does not necessarily imply greater dynamical fidelity. Our framework makes this distinction measurable, providing concrete criteria for evaluating whether advances in neural PDE solvers better capture the underlying dynamics. --- ### Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering Authors: Ran Li, Lei Chen Published: 2026-10-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06950v2 Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline. We introduce DecSteer, a System-1 decision operator trained by behavior cloning that lowers this cost by roughly two orders of magnitude. The default operator uses 330K parameters to match a 1.33M-parameter operator trained with reinforcement learning, exceeds or achieve comparable performance, while collapsing 3,685-token deliberation into a 6-token decision with no loss in accuracy. A rank-4 variant with 23K parameters, 1/58 of the strongest published skill operator, suffices for SearchQA and near-suffices for LiveMath, where higher rank still helps; the same recipe transfers across five tasks and three backbones, with out-of-distribution gains persisting on LiveMath problems released months after training. The gap to prior work is trainability, and it is set jointly by initialization and architecture. The initialization of prior operators zeroes the gradient of both large factor matrices at the first optimization step, whereas our zero-initialized output projection inside a shared low-rank backbone receives a gradient immediately, which a gradient-flow probe confirms directly. The gain isn't chain-of-thought compression. 23 of 57 LiveMath points beat the base model's best-of-8 sampling, and a logit-lens probe shows the operator amplifies the answer along the model's existing late-layer pathway, not writing it earlier. Gains track the base model's headroom across 13 base-task pairs, and skills compose as approximately linear operators that can be added, interpolated, and hot-swapped at inference time. --- ### AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models Authors: Lee Seung-woo, Bowen Qi Published: 2026-10-03 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2610.06949v1 Large audio language models answer questions about speech, sound, and music, yet their accuracy drops sharply on tasks that need fine-grained acoustic analysis. Judging which of two speakers has the higher pitch demands iterative signal-level reasoning that a content question does not. Current models spend the same computational depth on both. We introduce AdaLoop, a lightweight recurrent module that learns how many latent refinement steps a given audio--question pair requires. A shared transformer block iterates over the audio representation, guided by the question, while a learned halting mechanism exits the loop once the representation is ready. AdaLoop adds fewer than 3\% of the base model's parameters and plugs into any audio encoder--language model pair without modifying either component. Evaluated on three architecturally distinct models across MMSU, MMAU-Pro, and MMAR, AdaLoop raises the average accuracy by 2.9 to 3.8 points, with the largest gains on perception-heavy subtasks where the model learns to apply deeper reasoning. --- ### FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining Authors: Zhuohan Wang, Carmine Ventre Published: 2026-10-03 Categories: q-fin.PM, cs.LG arXiv: https://arxiv.org/abs/2610.06947v1 Factor mining seeks to discover signals from financial data that predict future asset returns and guide portfolio construction. Automated factor mining now spans genetic programming, reinforcement learning, generative models, and large language model agents. Yet it remains unclear whether advances across these paradigms yield more generalizable, distinct, and economically useful financial signals. We introduce FactorBench, a portfolio-aware benchmark comparing roughly five thousand mined factors from nine automated mining methods across five equity markets. A shared data and evaluation contract supports both symbolic expressions and executable Python factors, connecting heterogeneous discovery algorithms to common signal combination and portfolio construction procedures. FactorBench traces the outputs of mining systems across three levels: factor validity, temporal generalization, and predictiveness beyond measured risk and style exposures; within- and across-method pool distinctness, including similarity to the benchmark Alpha101; and composite-signal quality and after-cost long-only and long--short portfolio performance. After systematically assessing whether advances in factor mining translate into signal quality and portfolio performance, FactorBench finds that no paradigm consistently dominates. --- ### Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models Authors: Muhammad Atif Butt, Paweł Skierś, Joost Van De Weijer, Kamil Deja Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06945v1 Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear directions in activation space. Yet a natural visual concept does not necessarily require a linear visual transition: between sunny and stormy lies an intermediate weather state such as a sky with a few white clouds, not simply a weaker storm; between a caterpillar and a butterfly, the progression is not a caterpillar with continuously growing wings. This raises the question of whether such true intermediate states are also represented nonlinearly by the model. Indeed, when we prompt text-to-image models directly for intermediate attributes, their activations rarely fall along the straight direction connecting the endpoints. Therefore, we propose KANSteer, which models concept traversal as a curve passing through its intermediate states. Seeking a representation that is both simple and interpretable, we propose to use Kolmogorov-Arnold Networks (KANs), which provide a one-dimensional coordinate whose learned functions define the trajectory. This allows the steering direction to vary along the concept while preserving an interpretable representation. Across several concepts and text-to-image diffusion transformers, we find that their activation trajectories substantially deviate from straight lines, and that KANSteer provide a closer fit and smoother traversal of intermediate attributes than linear steering. --- ### Learning to Remember: Distilling Memory Retention for Compact Recurrent Neural Networks Authors: Nilushika Udayangania, Kishor Nandakishora, Marimuthu Palaniswami Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06942v1 Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series analysis. These models capture complex, sequential patterns in time series, enabling real-time assessments. However, their high computational complexity and large model sizes pose challenges for deployment in resource-constrained environments, such as wearable devices and edge computing platforms. Knowledge Distillation (KD) offers a solution by transferring knowledge from a large, complex model (teacher) to a smaller, more efficient model (student), thereby retaining high performance while reducing computational demands. Current KD methods, originally designed for computer vision tasks, neglect the unique temporal dependencies and memory retention characteristics of time series models. To bridge this gap, we propose a novel KD framework termed Memory-Discrepancy Knowledge Distillation (MemKD). MemKD leverages a specialized loss function to capture memory retention discrepancies between the teacher and student models across subsequences within time series data, ensuring that the student model effectively mimics the teacher's behaviour. This approach facilitates the development of compact, high-performing recurrent neural networks suitable for real-time, time series analysis tasks. We provide additional experiments, in-depth theoretical analysis, and insights into the proposed framework across extended time series benchmarks. Our experiments demonstrate that MemKD significantly outperforms state-of-the-art KD methods. Additionally, we demonstrate that it can match the teacher model's performance across a wide range of compression levels, achieving notable reductions in parameter count and memory usage without a significant loss in accuracy. --- ### Stabilizing language models under continual learning via condition-anchored distillation Authors: Huan Li, Zhe Cao, Qinlei Xie, Fushun Cui, Xuechen Liang Published: 2026-10-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.06940v1 Continual adaptation of language models can change their output distribution on prompts learned earlier, while retaining every old prompt-answer pair may be undesirable or impossible. We study condition-anchored generative distillation (CAGD): retain a small set of old prompts, use a frozen previous model to reconstruct completions and generation states, and match its predictive distributions while learning the next task. The formulation separates three roles that ordinary replay conflates: conditions select the behavior to protect, teacher generations locate relevant states, and soft targets specify how predictions may change. For autoregressive language generation, teacher-rollout distillation admits an exact chain-rule decomposition of sequence divergence. For masked-diffusion language modeling, our implementation directly controls local denoising drift on teacher-generated completions. In continual adaptation of a 219M masked diffusion language model, CAGD reduces four-task final held-out loss from 2.927 to 1.114 in one task order and from 2.168 to 0.891 in exact reverse. The same soft targets lower final average loss by 0.055 over hard replay when teacher-generated support is held identical. The direction persists on fresh facts and natural instructions across SMDM and Qwen3. On GSM8K, Qwen adaptation preserves answer-format compliance, but exact-match retention is seed-mixed at 0.6B and worsens at 1.7B. These results support condition-anchored functional preservation as a common design principle across the tested language-generation objectives. --- ### UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation Authors: Bangwei Guo, Yunhe Gao, Meng Ye, Yang Zhou, Difei Gu, Guoning Zhang, Leon Axel, Dimitris Metaxas Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06938v1 Medical image segmentation remains fragmented along two axes: segmentation paradigms and data dimensionality. Existing methods are typically developed separately for semantic, in-context, and interactive segmentation, and are further specialized to either native 2D images or 3D volumetric data. In clinical practice, however, segmentation workflows take many forms: a case may be initialized by semantic prediction, reference-guided segmentation, or user interaction. Regardless of how it begins, fine-grained refinement is naturally performed on 2D views; for volumetric scans, such 2D edits must propagate coherently to the rest of the volume. We present UniPro, a unified model that bridges segmentation paradigms and data dimensionality, using propagation to extend 2D segmentation to 3D volumes. Our key insight is that volumetric propagation and in-context segmentation share the same reference-conditioned prediction mechanism, differing only in whether the reference image-mask pairs come from other cases or from previously segmented neighboring slices. Building on this view, UniPro supports semantic, in-context, interactive, and propagation-based segmentation within a single slice-based framework, using class priors, reference exemplars, user clicks, and neighboring-slice predictions as mode-specific conditioning inputs. To improve propagation reliability, UniPro further incorporates bidirectional and 3D supervision to regularize slice-wise propagation beyond per-slice losses. Extensive experiments across diverse modalities and anatomies show that UniPro achieves strong performance across all segmentation settings, enabling annotation-efficient 3D segmentation from sparse 2D initialization and reducing slice-by-slice correction effort. --- ### QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting Authors: Linfeng Wang, Ruitong Zhang, Kai Zhao, Yang Shu, Zhongwen Rao, Meng Wang, Yijie Li, Bin Yang, Chenjuan Guo Published: 2026-10-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06936v2 Irregular multivariate time series forecasting is a challenging yet important problem in real-world applications, where observations are often irregularly sampled and asynchronously recorded across variables. Existing time series foundation models are mostly built on regularly sampled sequences, making them difficult to generalize to irregular time intervals and asynchronous cross-variable dependencies. To address these challenges, we propose QiYao-I, a manifold based foundation model for irregular multivariate time series forecasting. Specifically, we introduce a novel sampling-conditioned temporal manifold attention mechanism that maps real timestamps into a learnable temporal manifold feature space and injects temporal manifold biases into attention layers, enabling the model to capture both irregular time intervals and local sampling structures. Further, we propose a dynamic variable interaction mechanism with frequency awareness. It selectively performs cross-variable message passing under asynchronous observations. Extensive experiments on real-world irregular multivariate forecasting benchmarks demonstrate that QiYao-I achieves superior performance compared with both time series foundation models and end-to-end irregular forecasting models, showing strong generalization ability in zero-shot and few-shot settings. --- ### RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation Authors: Siyu Huang, Yueyong Chen, Xuejiao Li, Jun Zhou Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06932v1 Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-based cache admission under representation variations. To address these limitations, we propose RADC, which enhances prototype learning through reliable dual caching. RADC introduces a Semantic Foreground Cache that aggregates category-consistent spatial evidence from CLIP representations, yielding foreground prototypes that complement the global cache while mitigating background interference. To reliably manage both caches, Gaussian Risk Admission models multi-view representations as diagonal Gaussian distributions and jointly considers class separation and feature uncertainty to prioritize reliable cache candidates. RADC integrates zero-shot logits with complementary global- and foreground-cache predictions for robust inference. Extensive experiments on cross-domain and out-of-distribution benchmarks demonstrate consistent state-of-the-art performance. --- ### Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model Authors: Amirparsa Bahrami, Oliver Mortensen, Mohammad Sadegh Talebi Published: 2026-10-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.06931v1 In this paper, we study the sample complexities of value and policy learning in finite discounted Markov decision processes (MDPs) under recursive entropic risk preferences with risk parameter \(β\neq 0\), assuming access to a generative model of the MDP. We provide a refined analysis of model-based risk-sensitive Q-value iteration (MB-RS-QVI), a plug-in model-based method introduced in prior work, and derive \((\varepsilon,δ)\)-PAC guarantees for both learning the optimal \(Q\)-value function and an \(\varepsilon\)-optimal policy. Our bounds improve the exponential dependence on the effective horizon \(1/(1-γ)\) compared with the best existing guarantees for this setting. In particular, they match the existing lower bounds in their exponential dependence on \(|β|/(1-γ)\), as well as in \(S\), \(A\), \(\varepsilon\), and \(|β|\), up to logarithmic factors. Consequently, our analysis removes the exponential gap between the previously known upper and lower bounds, leaving only a polynomial gap in the effective horizon. --- ### Low-Rank and Structured Sparse Tensor Decomposition for Anomaly Detection in Multivariate Functional Data Authors: Mohammad N. Bisheh, Che-Yi Liao, Kamran Paynabar Published: 2026-10-03 Categories: stat.ML, cs.LG, stat.AP, stat.CO arXiv: https://arxiv.org/abs/2610.06930v1 Multivariate functional data arise in many modern manufacturing systems, where multiple sensors record densely sampled process trajectories. Monitoring such data is challenging because nominal variation is strongly correlated across samples, sensors, and time, while faults may appear either as isolated deviations or as structured departures concentrated within a limited number of sensor-specific temporal trajectories. We propose two unsupervised sparse tensor decomposition methods that preserve this multimode structure. Entrywise Sparse CP Decomposition (ES-CP) uses an entrywise \(\ell_1\) penalty to identify localized anomalies, whereas Fiberwise Sparse-Group Lasso CP Decomposition (FG-Lasso) combines entrywise and fiberwise penalties to detect both localized deviations and anomalies concentrated within temporal fibers. Both methods represent nominal process behavior through a low-rank CP decomposition and are estimated using alternating optimization with closed-form sparse-component updates. Two simulation studies evaluate performance under different fault structures, signal severities, noise levels, and missing observations. FG-Lasso attains or ties the highest macro F$_1$ score in almost all settings in the first study and achieves the highest macro F$_1$ score. In a multichannel forging-process case study, FG-Lasso and ES-CP obtain macro F$_1$ scores of 0.85 and 0.82, respectively, compared with 0.69 or lower for TRPCA and PCA-based anomaly detectors. The results demonstrate that explicitly matching the sparse penalty to the anticipated fault structure improves both anomaly detection and fault localization in high-dimensional functional processes. --- ### Metonymic Circuits for Abstract Concept Grounding in Vision Transformers Authors: Jing Ding, Ziqiao Ma, Jiayuan Mao, Joyce Chai, Freda Shi Published: 2026-10-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06928v1 We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence. We hypothesize a metonymic grounding mechanism in which abstract predictions are driven by concrete, interpretable anchor concepts (e.g., fire) that bridge visual signals to abstract semantics. By applying Transcoders on CLIP and DINO vision encoders, we recover intermediate features that can be associated with semantic labels for more concrete concepts, and trace their contributions in circuits underlying abstract concept recognition. Experiments on a carefully curated icon dataset reveal structured metonymic circuits, in which perceptual primitives dominate early layers and object-like anchors precede abstract targets. Images containing rendered text instead recruit a distinct perceptual-to-textual route. Causal interventions further validate that metonymic intermediates are functionally involved in grounding abstract concepts. --- ### AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD Authors: Sara Abdali, Jongwoo Ko, Pashmina Cameron Published: 2026-10-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06927v1 The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free remedies evict low-importance tokens, an irreversible choice along the sequence axis. We instead keep every token and store it more cheaply along the "feature" axis. We therefore propose AttSVD, a new "interpretable" low-rank compression whose basis is derived from each prompt's own attention geometry: an online, per-prompt truncated SVD that keeps only the directions attention actually reads, cutting persistent per-head KV memory in proportion to the retained rank. We propose two decode-time caching strategies, accumulating and streaming, for short and long generation regimes. Furthermore, we propose two refinements that make compression adaptive. A per-matrix energy rule sizes the logit space and the attention mass independently. An attention-aware basis truncates only in the spaces attention actually reads, preserving both the attention logits and the attention output. The same factors also provide free, per-head interpretability insights into the effective rank and the geometry attention consumes. Across multiple models, on both an agentic benchmark and the full LongBench suite AttSVD stays on par with the dense cache while using up to 50% of the KV-cache memory. --- ### DriftSR: One-Step Real-World Image Super-Resolution via Distribution Drifting Authors: Wei Zhu, Kai Zhang, Yu Zheng, Zhaopeng Yang, Lei Luo, Yong Guo, Jian Yang Published: 2026-10-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.04819v1 One-step real-world image super-resolution (Real-ISR) offers efficient inference, but recovering realistic and perceptually rich details often relies on score distillation or adversarial learning, introducing additional trainable components and making optimization more cumbersome. To this end, we propose DriftSR, a one-step Real-ISR framework that leverages pretrained diffusion priors through distribution drifting. Specifically, we perform drifting in the frozen intermediate representation space of a pretrained diffusion model, without introducing an additional task-specific feature encoder. Building on this space, we introduce Spatial Feature Drifting, which treats spatial features rather than entire images as distributional samples, enabling denser supervision for distribution alignment. To mitigate structural deviations, we further introduce Structure-Modulated Guidance, which adaptively refines drifting guidance according to local structural consistency with the LQ input. Consequently, DriftSR optimizes only the one-step generator, without auxiliary distillation branches or adversarial discriminators. Extensive experiments on three real-world benchmarks demonstrate that DriftSR delivers high-quality super-resolution reconstruction with efficient one-step inference. ---