# Research Papers — 2026-10 · bundle page 5 of 156

> Full-text markdown of papers #201–250 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/5
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/4.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/6.md)

### Multi-sourced AI Tutor for Non-Native English Speaker Students

Authors: Yiyin Shen, Xinyi Ai, Weibing Wang, Rogers Jeffrey Leo John, Meenakshi Syamkumar
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22163v1

Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of answering student questions. With the rise in enrollment of international students in computing programs, researchers have begun to explore the difficulties that non-native English speaker (NNES) students face in computing courses due to language barriers. To aid such students, we developed a general-purpose AI tutor system that can process student questions in foreign languages (currently focused on Mandarin) and provide bilingual responses. Our system also incorporates the functionality of generating a glossary of technical terms and their explanations to enhance comprehension. Our approach utilizes a specialized Retrieval-Augmented Generation (RAG) pipeline with a novel question extraction mechanism, enabling us to effectively utilize a diverse array of course materials for answering student queries. We evaluated our AI tutor using 91 Piazza posts, demonstrating that it could answer 83.52% of the posts correctly and in a helpful manner. The tutor also provided high-quality translations for 76.92% of the questions and generated technical term glossaries for 64.47% of them. Our findings underscore the potential of multi-source RAG pipeline in enhancing AI tutor systems, offering support for non-native speakers that are challenging to provide with traditional supporting staff of a computing course.

---

### EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits Steering

Authors: Wei Xia, Yehui Tang, Zhi-Hong Deng
Published: 2026-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.22160v1

Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate control over how strongly to reinforce the distributional changes induced by a context update. We introduce EMO, a training-free framework inspired by expectation--maximization that alternates question-specific context estimation (E-step) and distribution refinement (M-step). The E-step revises a system context using textual gradients from an external judge without access to gold answers. The M-step contrasts next-token distributions under the revised and preceding contexts at a shared prefix to construct a confidence-constrained logit correction. Feedback on the steered response drives the next context update, coupling adaptation across rounds with intervention within each generation. Theoretically, we connect parameter and context optimization through a shared target-KL objective and additive logit representations, and derive the steering vector from context-induced logit displacements. Under context-improvement and faithful-steering assumptions, we prove a one-round decrease in target KL divergence for sufficiently small steering strength. Under greedy decoding across eight models and six benchmarks, EMO improves the zero-shot baseline in 39 of 40 aggregated settings, averaging $+9.10$ percentage points. With the same judge, it adds $+1.53$ points on average over context-only optimization (TextGrad), with consistent MMLU-Pro gains across models. At matched target-model generation budgets, accuracy advantages over best-of-$N$ are strongest on Llama, while oracle coverage is higher in most comparisons despite fewer candidates. The coverage--selection gap motivates allocating test-time computation jointly to candidate generation and verification.

---

### PremiseSQL: Evaluating Premise Critique and Abstention in Text-to-SQL Systems

Authors: Shuo Lin, Jinzhe Li, Chenlu Guo, Yanhan Li, Yuan Wu, Yi Chang
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.22158v1

Recent advances in large language models (LLMs) have substantially improved Text-to-SQL performance, yet existing NL2SQL systems largely assume that user queries are valid and answerable. As a result, models often generate executable SQL even for queries with flawed premises. We introduce premise critique ability in NL2SQL, namely the ability to recognize flawed queries and abstain from generating misleading SQL. To evaluate this capability, we propose PremiseSQL, a benchmark containing 1,800 flawed NL2SQL queries across four categories of premise failures, along with their 1,800 original queries. We further design an evaluation framework to measure intrinsic and prompt-induced premise-aware behavior across three prompting settings. Experiments on frontier LLMs show that current models are strongly premise-trusting by default and rarely critique flawed premises. Stronger critique-oriented prompting improves detection and abstention on flawed queries, but also increases false invalid judgments and suppresses SQL generation on originals. The code is available at https://github.com/vegeet/PremiseSQL.

---

### The importance of tensor handling and implementation of physics-informed DeepONets

Authors: Nahum Banks, Gustavo A. M. de Almeida, Sergio Maldonado
Published: 2026-10-15
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2610.22157v1

Physics-informed neural networks (PINNs) reduce or eliminate the need for large labelled datasets by enforcing governing equations during training. Physics-informed Deep Operator Networks (PI-DeepONets) extend this approach to learning solution operators, enabling rapid prediction across families of problems. Despite these advantages, we show that their application to higher-dimensional problems remains limited by the computational cost of training. To address this issue, we propose a modified PI-DeepONet architecture that reduces this cost by removing redundancy in how the Branch network processes input functions across collocation points. The proposed formulation is mathematically equivalent to the original architecture but reduces input tensor sizes and the number of Branch network evaluations. We analyse the computational complexity of both architectures and derive theoretical scaling laws for training time with respect to the number of collocation points and input functions. The proposed architecture is evaluated on 1D, 2D, and 3D linear advection problems. In all cases, it achieves comparable predictive accuracy to the original PI-DeepONet while consistently reducing training time. In 2D experiments, a maximum speed-up of $3.75\times$ is observed, with empirical training-time scaling agreeing with the predicted linear dependence on collocation points and input functions. Furthermore, training a 3D model on an NVIDIA A100 GPU is only feasible using the proposed architecture, as the original formulation exceeds memory limits. These results demonstrate that careful consideration of how PI-DeepONets are implemented can yield substantial gains, enhancing the practical performance of PI-DeepONets and enabling their application to otherwise intractable physics-informed learning problems.

---

### Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?

Authors: Jingyu Tang, Xu Yang, Zhehao Zhang, Zheng Wang, Qi Cheng, Haozhe Zhao, Manling Li, Wenxuan Li, Xide Xia, Jiaxin Pei
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22155v1

Real-time interaction requires agents to perceive evolving environments and act under temporal constraints, yet existing evaluations of real-time streaming models focus on conversational quality and streaming perception, leaving effective action under strict temporal constraints untested. We introduce Realtime-Bench, a suite of carefully curated dynamic tasks where delayed actions directly affect success. Under Wall Clock, where environments advance according to actual inference latency, the best success rate reaches only 44% and the best Pass^3 is only 36%, demonstrating that real-time interaction remains challenging. To separate serving latency from models' real-time streaming capability, we compare Wall Clock with Paused Clock, which removes inference delays as an idealized reference, and introduce Token Clock, which advances simulated time according to generated token counts, testing temporal awareness independently of physical serving speed. We find that temporal costs limit success in evolving environments and that higher reasoning effort has mixed effects under time pressure, reflecting a trade-off between decision quality and timely execution. These findings suggest directions for improving real-time multimodal agents, including adaptive reasoning with temporal awareness and continuous perception and action.

---

### Specification Gaming and a Constrained Reinforcement Learning Mitigation in a Cleaning Gridworld

Authors: Hilda Adwubi Osei
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.22152v1

Reinforcement learning agents optimize exactly the reward signal they are given, which can diverge sharply from an intended true objective when that signal is only a proxy for it; this failure mode is known as specification gaming. Existing evidence for this failure mode is largely observational, with comparatively few demonstrations pairing a controlled, deliberately constructed proxy/true gap with a mitigation that carries a verifiable guarantee rather than only an empirical improvement. We construct a minimal gridworld in which a cleaning-robot agent can either genuinely remove dirt or conceal it from a cheap sensor, and show that a standard deep Q-network trained only on the sensor's proxy reward converges to a policy that games it completely, reaching near-maximal proxy reward while never achieving the true objective. We then introduce a constrained reinforcement learning fix, penalizing the specific behaviors through which the agent exploits the gap, and show that it eliminates the gaming behavior from the final policy while substantially recovering true-objective performance. We further derive and empirically verify an exact accounting identity relating the proxy reward, true reward, and our cost signal for this environment, showing that the cost signal measures the proxy/true gap exactly rather than merely tracking it, and yields a deterministic guarantee under a hard-constrained variant of the method.

---

### RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST Parsing

Authors: Mohammadreza Sediqin, Shlomo Engelson Argamon
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22150v1

In Rhetorical Structure Theory (RST), each edge of a discourse tree carries a nuclearity label, marking which span holds the central content, and a relation drawn from a closed inventory of functional categories. Neither label is a surface property: the same two clauses can be Elaboration or Background depending on rhetorical intent, and the boundary between them is fixed by annotation convention rather than by lexical cues. Predicting these labels therefore requires a formal discourse schema, and exposure to discourse-rich pretraining text does not supply it: given only a target EDU pair, a strong LLM recovers nuclearity at 0.794 F1 and relation at 0.738 F1. We propose RAG-RST, a retrieval-augmented framework that supplies this schema as in-context demonstration rather than through parameter updates, raising nuclearity to 0.846 F1 and relation to 0.788 F1 with no training. Two configurations are compared: a precomputed strategy that labels all EDU pairs before parsing, and a dynamic strategy that retrieves at each reduce step, so that the exemplars reaching the generator depend on the reductions the parser has already committed to. Both outperform existing RST parsers across span, nuclearity, relation, and full tree metrics, with the dynamic variant consistently strongest. Two properties of the retrieved schema emerge: its utility is bounded in number, saturating and then declining beyond fifty exemplars, and it depends on structural position. Both indicate that a formal linguistic schema can be supplied to a foundation model as a demonstration rather than trained into its parameters.

---

### FALCON: FPGA-Accelerated Latency-Certifiable Occupancy Networks for Camera-Based Autonomous Driving

Authors: Haohua Que, Mingkai Liu, Handong Yao
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.22143v1

A perception system that must brake for a pedestrian does not need a low average latency. It must deliver an answer before the deadline on every frame, the worst case included. Commodity edge accelerators optimize the mean through dynamic scheduling, OS jitter, thermal throttling, and contention, so their per-frame latency can be measured but not bounded. We build FALCON, a camera-based 3D occupancy front-end on the AMD Kria KR260, an embedded FPGA drawing 4.3 W idle and up to 6.6 W under inference, and make the latency guarantee layered and explicit: programmable-logic (PL) compute is cycle-bounded analytically; inference is a measured envelope over 100k-frame traces; and a watchdog enforces output delivery, publishing the previous output flagged stale when a frame is late. The deadline runs use a fixed-work proxy of six ResNet-50 DPU inferences per frame, not the full occupancy network: across three 100k-frame enforced runs, all 300k proxy frames delivered an output within the 100 ms deadline plus at most 10.2 ms, the worst of the three runs. The full six-camera FlashOcc pipeline composes to about 1.3 s per frame on the board and is not yet a 10 Hz system. The two operations the DPU cannot run, a view-transform gather and a bilinear resize, become fixed-trip-count PL IPs numerically matched to their software references. On the full Occ3D-nuScenes validation set the board reaches mIoU 29.88, 92.8% of an FP32 baseline the DPU cannot run. On a ResNet-50 probe over 100k frames the KR260 tail stays within 1.5 times its median (2.0 times for the six-inference proxy), where Jetson Orin reaches 4.4 times and the worst datacenter GPU run (NVIDIA L4) 23.6 times. The deployment recipe, HLS sources, and raw timing traces are released.

---

### Are You Sure Your LLM Is Sure? Repairing and Auditing Confidence

Authors: Arijit Dey, Bhartendu Kumar, Ramya Hebbalaguppe, Khuushi Maheshwari
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22139v1

Confidence scores determine whether an LLM answer is accepted, reviewed, or regenerated, yet scalar recalibration can only correct errors visible through the score itself. We introduce RADAR (Repair, Adopt, and Diagnose After Recalibration), a reliability framework that separates confidence repair from deciding whether to deploy the repair and auditing the errors that remain. Under squared loss, we decompose prediction risk into outcome noise, information hidden by the score, and mapping error; restricting repair to order-preserving maps additionally introduces a pooling gap. For repair, we propose Probe-Anchored Isotonic Calibration (PAIC), which learns a monotone map from correctness-probe predictions on unlabeled target prompts. PAIC's excess risk depends on the probe's score-conditional bias and fitting error rather than its overall accuracy. For adoption, we derive a paired procedure with finite-sample control of false improvements. For auditing, we develop a prompt-clustered kernel test that detects feature-aligned residual errors while accounting for dependent answers from the same prompt. Across multiple LLM checkpoints, benchmarks, and distribution shifts, richer predictors can improve confidence estimation, but projecting their information back to a scalar score can lose these gains, and lower prediction risk need not yield better review decisions. Across 47,400 replayed raw-score allocations, paired betting adopts candidates with lower held-out test risk in 42.95% of allocations, versus 15.09% for one-sided empirical Bernstein. RADAR thus provides a principled workflow to repair what a scalar score can express, adopt a repair only when supported by evidence, and diagnose systematic errors that recalibration leaves behind. Code and data will be released upon acceptance.

---

### Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions

Authors: Liangjie Huang, Henry Peng Zou, Wei-Chieh Huang, Wooseong Yang, Yuwei Han, Philip S. Yu
Published: 2026-10-15
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2610.22138v1

LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors. We test this assumption against a minimal adversary. In a ten-agent factual discussion, one or three adversarial agents repeatedly assert a plausible false answer. After each round we probe each benign agent's private answer through a separate call whose response is hidden from its peers, and we separately label its public stance toward the claim. Across six models and three factual-QA datasets, groups remain stable without an attacker: only 0.6% of benign agents finish with the false answer. A single adversarial agent increases this rate to 44.8% and three to 60.5%. Studies of conformity typically report public agreement without private change; we find the reverse. With three adversarial agents present, benign agents hold the false answer in 51.6% of exposed turns but publicly endorse it in only 19.7%. Much of the influence therefore remains invisible in the discussion, and the false answers persist when agents are asked for their own views. Agents that retain the true answer often fail to defend it; once adopted, the false answer spreads among benign agents, and baseline knowledge does not predict robustness.

---

### CART: Compatible Routing for Multimodal Continual Instruction Tuning

Authors: Ling-Xiang Zhang, Tao Hu, Da-Wei Zhou
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22137v1

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world applications often require them to continually acquire new capabilities from sequential tasks, i.e., Multimodal Continual Instruction Tuning (MCIT). In typical MLLMs, a projector is employed to align visual representations with the language model. However, existing methods primarily protect the language model from forgetting while continuously updating the projector across tasks. Such asymmetric adaptation can cause substantial representation drift in the projector, increasing the mismatch between the projector and language model and consequently exacerbating catastrophic forgetting. To address this issue, we propose Compatible Routing (CART), which explicitly coordinates the adaptation of the projector and language model. Specifically, CART maintains task-specific experts for both modules and combines them through weighted mixtures. CART jointly infers their weights by considering both expert relevance and cross-module compatibility, thereby promoting coordinated adaptation between the two modules. To further control model growth, we introduce relevance-guided expert consolidation, which merges experts exhibiting similar relevance profiles across samples within each module. Extensive experiments demonstrate that CART achieves state-of-the-art performance.

---

### Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling

Authors: Tong Zhu, Zhe Xu, Zefeng He, Yunkai Chai, Xuyang Hu, Dehong Zheng, Yun Luo, Yafu Li, Qi Zhang, Yu Cheng
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.22131v1

Interactive agents repeatedly choose among a finite set of actions, labels, or ordinal outcomes. Generating a free-form response for each choice adds latency and complicates the interface between a model and its environment. We present Intern-Decision, a family of 0.8B, 2B, and 4B multimodal decision models that return structured choices and candidate probabilities from text and optional images. Our autoregressive masked language modeling objective places one decision placeholder per field in a complete assistant JSON skeleton. Ground-truth symbols appear only in supervision, while all fields are evaluated in a single causal forward pass using the backbone's native language-model head. The 4B model achieves a 90.02% unweighted average accuracy across seven evaluation suites, compared with 88.74% for Jev v1.13.0. For a fixed 289-token request with three fields on one RTX 4090, mean latency is 44.16 ms for the 4B model and approximately 33--34 ms for the smaller models. On a separate 96-case known-distribution pilot, temperature scaling reduces expected multiclass Brier from 0.628 to 0.550 and expected calibration error from 0.213 to 0.089. A confidence-based handoff study on 111 public Jevbench-Hard items improves accuracy from 82/111 (73.87%) to 97/111 (87.39%) by routing 42 items to Atria-Dawn-Preview. We also describe qualitative game, visual interface, and browser demonstrations. These results support compact decision models as a practical component of larger agent systems.

---

### DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction

Authors: Aozhong Zhang, Selcuk Gurses, Yanxia Deng, Naigang Wang, Chi-Chun Liu, Davis Wertheimer, Derrick Liu, Xin Li, Zi Yang, Felix X. -F. Ye, Penghang Yin
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22130v1

Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory growth. While recent eviction methods have moved beyond simple attention-score heuristics to incorporate value representations, they typically face a fundamental trade-off: the underlying optimization for minimizing output perturbation is an NP-hard combinatorial problem, leading to mathematically suboptimal heuristics or implementations that are difficult to kernelize. In this work, we propose DropKV, a simple principled eviction framework based on Decoupled Residual-Output Perturbation. By decoupling the joint eviction decision into independent per-token scoring, DropKV circumvents combinatorial intractability and admits a provable constant-factor approximation guarantee under a cone condition that we empirically verify on three long-context LLMs. To ensure practical viability, we provide a high-performance implementation using fused Triton kernels that avoid materializing the full attention matrix, delivering a 19.8x scoring-kernel speedup that translates to up to a 9.9% matched-batch end-to-end prefill speedup. Extensive evaluations on the RULER and LongBench benchmarks demonstrate that DropKV consistently outperforms state-of-the-art baselines at equivalent cache budgets, achieving the lowest inference latency among eviction methods while also remaining faster than the dynamic cache baseline.

---

### Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization

Authors: Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein
Published: 2026-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.22127v1

Personalization of Large Language Models (LLMs) is increasingly important for user-centric applications, yet prior methods mainly adapt dense LLMs, whose polysemantic neurons, each encoding multiple unrelated concepts, hinder localizing the components behind personalization, and thus understanding and controlling it. We propose to personalize Mixture-of-Experts (MoE) LLMs, which sparsely route each token to a few specialized experts, reducing polysemanticity and enabling such localization. We adapt three open-weight MoE LLMs on a large-scale personalization dataset and train crosscoders on paired activations of the personalized and non-personalized models to learn interpretable personalized latents, from which we identify the experts encoding distinct personalization features. The personalized MoE LLMs perform competitively with dense LLMs while activating only a fraction of their parameters, exhibit lower polysemanticity than dense LLMs with similar active parameters, and, within the same model family, yield personalized latents that are less shared with the non-personalized model. Causal interventions show that these latents suffice to recover the personalized model's behavior and that boosting their associated experts moves the non-personalized model toward it, revealing distinct routing paths for different personalization features.

---

### Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths

Authors: Joran Michiels, Anis Ismail, Maarten De Vos, Alejandro Sifrim
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.22126v1

Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which extend integrated gradients to incorporate prior causal structure among input features while retaining its computational efficiency and, under conditions on the causal graph, its axiomatic guarantees. In many settings, some causal structure between features is already known, for example, that a transcription factor causally regulates a target gene's expression. Yet existing gradient-based methods cannot exploit this structure, instead crediting a feature's downstream effects over its true upstream cause, such as ranking the target gene above the transcription factor that regulates it. Our key idea is to embed this causal structure by routing the integration path along the causal graph. The method thereby decomposes each feature's attribution into a direct effect and effects mediated through its causal descendants. We evaluate CIG in three settings of increasing realism. First, on a synthetic benchmark with a known causal model, CIG's attributions best match the ground-truth causal effect from Pearl's do-calculus, matching the accuracy of causal Shapley values at a fraction of the computational cost. Second, on simulated single-cell gene expression data with a known gene regulatory network (Dyngen), CIG most accurately recovers the transcription factors driving the simulation. Third, on real interferon-$β$ stimulation data, where only an approximate causal graph is available, CIG better prioritizes the transcription factors driving the measured response than DeepSHAP and integrated gradients. Together, these results show that incorporating causal structure into gradient-based attributions recovers upstream drivers that existing methods miss, without sacrificing scalability.

---

### PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

Authors: Kshitij Mishra, Abhijith Sharma, Nils Lukas, Salem Lahlou
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22124v1

Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these agents are deployed in consequential settings, they are often constrained by policies governing pricing, privacy, confirmation, safety, and other requirements. However, existing evaluation methods leave a critical gap: capability benchmarks measure what agents can accomplish, while content-safety red-teaming measures harmful generations, but neither tests whether agents comply with predefined policies during otherwise valid tool use. Such policy violations are difficult to audit because their effects may emerge only after several turns, span multiple tool calls, or surface in downstream systems. We propose PROBE (Policy Rule Observation via Behavioral Exploration), an algorithm for training LLM-based auditors that interact with deployed agents as realistic users and probe them for policy violations through multi-turn, tool-mediated dialogue. We formalize agent auditing as a two-player Markov game and propose a composite reward that balances violation discovery, behavioral plausibility, conversation progress, and policy diversity. To study training objectives and reward design, we compare GRPO, DPO, and GFlowNet-based optimization in a controlled setting. Across extensive experiments, auditors trained with PROBE uncover substantially broader and higher-yield policy violations than same-architecture zero-shot adversaries, even when the auditor is significantly smaller than the target agent. Our results show that multi-turn behavioral auditing is a distinct and necessary axis of agent evaluation, complementing capability and safety benchmarks. PROBE offers a scalable path toward automated policy auditing for real-world agentic systems and suggests a co-evolutionary loop in which auditors expose failures and agents improve from auditor feedback.

---

### Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery

Authors: Xudong Zhang, Jianzhe Li, Yitong Tang, Peijie Zhou
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.22122v1

Genetic and drug perturbation screens are important tools for elucidating disease mechanisms and validating therapeutic targets, but experimental costs limit the number of candidates that can be tested. Existing perturbation screening methods typically update the surrogate model with feedback while keeping the acquisition function fixed, limiting their ability to adapt selection to different response landscapes. Experimental feedback reveals current hits and informs subsequent selection by updating candidate predictions, providing a training signal for learning how to select experiments. We formulate budgeted perturbation discovery as a sequential decision problem and propose Temporal Difference Active Learning (TDAL), which learns an acquisition function online through temporal difference learning from a single screening trajectory, accounting for current hits and future discoveries. TDAL uses the Hellinger distance between hit probabilities for unmeasured candidates before and after an experiment to weight successor value, and reuses measured outcomes through leave-batch-out (LBO) to construct virtual transitions and alleviate training data scarcity. Across eight public screens spanning single, double, and triple perturbations under varied experimental configurations, TDAL achieves an average rank of 1.63 among eleven methods and ranks first on four tasks, demonstrating its adaptability across response landscapes.

---

### Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded Representations

Authors: Vahid Yazdnian, Yasaman Ghasempour
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.22120v1

Knowing the layout of the physical world matters for many applications, yet the sensors we rely on for it (e.g., cameras and LiDAR) can fail in darkness, in adverse weather, or behind walls. Wireless signals do not face these limitations: every link between a base station and a user is shaped by the buildings it passes, reflects from, or is blocked by, leaving information about the surrounding scene embedded in the wireless channel measured at the endpoints. However, mapping channel measurements to the environment is a severely ill-posed problem: a measurement records only the structures that interact with the transmitted electromagnetic waves along its propagation paths, and even these observations can often be explained by multiple plausible scenes. We therefore formulate wireless scene reconstruction as posterior inference and develop a hierarchical framework with two complementary stages to approach this problem. A wireless foundation model, pretrained to respect propagation physics, transforms each channel measurement into a representation of the scene structure that shaped the observation. A diffusion model then jointly integrates representations from multiple measurements to model and sample the posterior over building occupancy, with consensus over samples producing the final reconstruction. We demonstrate that the framework can accurately recover building footprints from wireless channel measurements alone and show that its performance depends critically on both design components: physics-grounded representations expose scene-relevant information, while joint posterior inference coherently integrates complementary observations.

---

### Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa

Authors: Luis A. Mercado-Campos, Alexis Palmer
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.22110v1

In minoritized (low-resource) language technologies, a common response to data sparsity is to aggregate text across multiple varieties and treat the combined data as a single corpus. However, mixed corpora of closely related indigenous variants can produce an artificial register that is accountable to no single speaker community, a structural failure we call variant fragmentation. This issue is acute for minoritized languages native to Mexico, such as Nawatl. Building on a 70,000-pair multi-variant foundation, we specialize an mT5-large checkpoint to Masewalkopa (nhn), the Nawatl variety spoken in Santa Ana Tlacotenco. We curate 2,665 parallel pairs, reserve all sentence-level data for evaluation, and incorporate 192 elder-transcribed target sentences via asymmetric backtranslation. A custom finite-state analyzer reduces unanalyzed surface forms from 82.0% to 19.9% and supplies functional syntax tags as plain-text prefixes, allowing the model to reuse existing subword embeddings rather than relying on frozen special tokens. The resulting LoRA-v9c-b model achieves 58.46 dev chrF++ and 58.20/57.90 directional test chrF++. Finally, CTranslate2 int8 quantization reduces CPU latency from 137.5 to 1.8-2.6 seconds per request, enabling cost-bounded Cloud Run deployment.

---

### Patch where the text is new: a compression view of where byte-level models should spend compute

Authors: Nicolás Vera Zúñiga
Published: 2026-10-15
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.22100v1

Byte-level language models such as the Byte Latent Transformer (BLT) run their large global model once per patch and start a patch where a small model's next-byte entropy is high. This rule rarely starts a patch at in-line computed results, such as the number after "=" in a worked solution, and accuracy on them collapses under tight patch budgets. We propose novelty patching, motivated by LZ77-style compression: start a patch where the upcoming bytes are unlikely to repeat the recent context. The rule is a lookup table over the previous two bytes, fitted in seconds on raw text with no labels, reference model or losses. In BLT-style models trained from scratch on a 1.9 GB math corpus at a matched ~11% patch rate (3 seeds each), it has no clear effect at 1M parameters, raises final-answer accuracy from 47% to 72% at 12M, and at 50M raises computed-result accuracy from 21% to 57% and final-answer accuracy from 60% to 90%; a table fitted on the raw pretraining corpus keeps the gain. Outside math the advantage shrinks: novelty lowers bits per byte on prose and ties entropy on source code and on synthetic execution traces. An analysis of where boundaries fall explains the pattern. Computed results have ordinary surprisal for the patcher's model, so surprisal-seeking rules pass over them: entropy concentrates patch starts on high-surprisal bytes most strongly of all rules (boundary enrichment 1.61) and is the worst on computed results, while the best rules sit near chance enrichment. Novelty works where new content begins at segment starts close to the computation, as in written math; a learned chunker (H-Net) finds such structure on its own, in math and in code. We also report what did not work: typed uncertainty as a training rule, switching rules after training, and a context-aware novelty predictor.

---

### TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language Models

Authors: Ya-Shi Zhang, Jian Tang, Pierre-André Noël, Oleksiy Ostapenko
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.22099v1

Masked diffusion language models expose an inference-time choice: which positions become visible after each denoising pass. Many existing decoding methods use hand-designed rules or require visibility to grow monotonically. We present a $\textbf{T}$iny $\textbf{I}$nference-time $\textbf{P}$olicy for $\textbf{S}$caling ($\textbf{TIPS}$), an approximately $600$K-parameter controller that learns both unmasking and remasking while keeping the underlying language model frozen. TIPS uses visibility-aware confidence features and a shallow transformer to select which tokens should be visible, while a fixed schedule controls the expected visible fraction. We train the controller through supervised warmup followed by reinforcement learning from terminal correctness rewards. On GSM8K and MATH-500 with LLaDA-8B-Instruct, the full-canvas and two-block TIPS variants achieve $58.46\%$ and $57.97\%$ micro-averaged accuracy at a budget of $32$ decoder evaluations, exceeding the strongest baseline in our main comparison by $12.1$ and $11.6$ percentage points, respectively. Both variants are trained at a budget of $32$ evaluations and remain competitive at higher budgets without retraining. These results demonstrate that learning when to reveal and reconsider tokens can improve the accuracy-compute trade-off without updating the decoder backbone.

---

### SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis

Authors: Ting Liu, Haoran Lai, HaobinChen, Ming Liu, S Kevin Zhou
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.22094v1

Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in a batch as a negative. In radiology, recurring findings across patients mean that instance mismatch need not imply semantic incompatibility, creating false-negative supervision that we term a semantic conflict. A training-trace audit shows that pair-observations selected by the online mask used during training are enriched for report-derived finding agreement, although this proxy analysis does not establish clinical equivalence. Fixed thresholds can become miscalibrated as similarity distributions evolve, while soft reweighting leaves residual repulsive gradients. We therefore propose Semantic-Conflict-Aware Contrastive Learning (SCCL), which tracks modality-specific similarity distributions with exponential-moving-average (EMA) statistics, derives adaptive thresholds, and hard-masks flagged candidates before softmax normalization. Inclusive (OR) and consensus (AND) rules define two SCCL teachers, whose bidirectional cross-modal rankings are consolidated through standard distillation into a single deployable student, SCCL-DT. Across five public chest X-ray benchmarks, SCCL-DT achieves a mean zero-shot AUC of $0.850$, compared with $0.837$ for the strongest evaluated baseline in our comparison. Code will be made publicly available soon.

---

### Beyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance Learning

Authors: Lubin Gan, Jing Zhang, Xinming Zhang, Chengpeng Xu, Siying Wu, Xiaoyan Sun
Published: 2026-10-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.22091v1

Whole-slide images may contain coexisting lesions, yet weak supervision typically provides only the most severe diagnosis. We formulate this setting as dominant-label multiple instance learning, where the observed label is the maximum-severity element of a latent lesion set. Standard multiclass MIL treats it as a complete one-hot description and therefore suppresses lower-severity evidence whenever it co-occurs with a dominant lesion. We propose DomSet-MIL, a label-aware framework that aligns the annotation mechanism across bag and instance levels. Dominant-Label Censored Likelihood models the reported diagnosis without declaring unreported lesions absent. Severity-Ordered Residual Routing assigns patch evidence from high to low severity and preserves residual support for secondary findings, while top-$q$ pooling links local routing scores to bag prediction. Experiments across natural and controlled settings show that DomSet-MIL achieves state-of-the-art performance in dominant-label prediction while more effectively recovering latent coexisting-lesion evidence. These findings demonstrate that modeling the dominant-label mechanism can improve diagnostic prediction without sacrificing clinically meaningful secondary findings.

---

### Pathology foundation models for training-free case retrieval in salivary gland tumors

Authors: Maximilian J. Roesel, Niklas Kiermeyer, Philipp Keyl, Frederick Klauschen
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.22087v1

In pathology, pattern recognition relies on a frame of reference built through extensive training and experience, which may still fall short when encountering rare cancer subtypes. Archives of previously diagnosed tumors often contain relevant precedents, yet identifying the most relevant cases remains challenging. Here we explore whether content-based retrieval with current pathology foundation models facilitates rare cancer diagnostics without any task-specific training. Pathologists can query a digitized archive using a region of interest (ROI) from a whole slide image (WSI) and retrieve morphologically similar cases, along with their ICD-O codes and corresponding WSIs. The ROI can be selected manually or automatically using a gated attention-based multiple instance learning model. We evaluate our approach by leave-one-case-out on an imbalanced dataset of 137 salivary gland tumor cases spanning 12 ICD-O morphology categories, comparing four pathology foundation models (Atlas2, Atlas2-B, Atlas2-S, and UNI2h). Top-1/3/5 retrieval was 62.5%/76.7%/81.3% for Atlas2, 50.2/66.6/72.9% for UNI2h, 52.3%/71.5%/77.6% for Atlas2-B and 54.4/65.2/73.7% for Atlas2-S. Macro-averaged F1 ranged from 69.0% for the smallest model Atlas2-S to 76.6% for the largest model Atlas2 across the five classes with at least ten cases. Our modified Chamfer similarity separated correct from incorrect matches among the Top-5 more reliably for Atlas2 (AUC 0.754) than for Atlas2-B (0.679, p = 0.020) and Atlas2-S (0.653, p = 0.003), but not UNI2h (0.697, p = 0.196). Requiring no additional training or manual annotation, this approach makes departmental archives searchable with pathology foundation models, providing a low-barrier route to case-based differential diagnosis and extending the individual frame of reference to the collective experience of the department.

---

### Multi-SFT: Permissively-Licensed Multilingual Instruction-Following

Authors: Daniela Baiamonte, Kamyar Zeinalipour, Elena Fano, Stefano Simonazzi, Andrea Zugarini
Published: 2026-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.22086v1

Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprietary models whose terms of service forbid training competing systems. We introduce Multi-SFT, a commercially permissive collection of 502,818 instruction-response pairs across five European languages, built via translation and regeneration pipelines for tasks where translation is insufficient. Human evaluation yields inter-annotator agreement of at least 0.87 across all datasets and languages. Fine-tuning nine models from three different families (EuroLLM, OLMo 2, Qwen3; 1B-32B) and evaluating them on 13 benchmarks shows that Multi-SFT alone is competitive with larger augmented mixes and official instruction-tuned releases, with decisive advantages on safety tasks.

---

### Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop

Authors: Vittorio Lippi
Published: 2026-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.22084v1

Neural networks offer critical adaptability for controlling complex systems where nominal modeling proves intractable. However, when offline-trained neural networks are deployed within closed-loop control systems, their actions fundamentally alter the state distribution upon which they were trained. This paper introduces a unified taxonomy to categorize these sequential failure modes: the initial Closed-Loop Identification Error, the deployment-induced Action Error, and the continuous Tracking Error. Through discrete-time sensitivity analysis, this work formalizes how offline-learned parameters locally guarantee a trajectory divergence upon deployment, degrading performance due to local loss geometry. To mitigate this distribution shift, we propose actionable design policies centered on time-scale separated online adaptation. These mechanisms are validated through ablation studies on a nonlinear Duffing oscillator, demonstrating that bounded continuous learning successfully mitigates trajectory divergence whereas static deployments fail, offering concrete guidelines for practitioners deploying machine learning components in safety-critical feedback systems.

---

### Beyond the Hamming Cliff: Compact Spatial Encodings Preserving Semantic Distance in Spiking Neural Networks

Authors: Sergio Davies, Muhammad Aitsam, Morgan-Tyler Stone, Alessandro Di Nuovo, Liangxiu Han
Published: 2026-10-15
Categories: cs.NE
arXiv: https://arxiv.org/abs/2610.22083v1

By pre-processing input signals with Gray, Thermometer, Johnson and hybrid encodings before passing them to spiking neural networks running on SpiNNaker hardware, Davies et al.(2025) address the semantic-spatial disparity that causes the ``Hamming cliff'' in standard binary representations. Continuous semantic patterns are presented as a set of simultaneous spikes at the input layer, preserving ultra-low latency processing. Training the network on multiple continuous values under each scheme, and measuring accuracy, required homeostatic scaling and false-positive rates, shows that removing the cliff is necessary but not sufficient: Gray encoding removes it yet retains little global distance structure, whereas Thermometer and Johnson preserve semantic distance at a code width that grows with the value range. The proposed hybrid encodings contain all three as limiting cases of a single parameter, recovering most of that structure at a fraction of the width. The homeostatic factor is shown to set a radius of tolerance around each trained pattern, so that the choice of encoding alone decides which values the network treats as similar.

---

### Learning from Unverified Peers via Shared Residual Distillation

Authors: Feiyang Chen, Runze Ma, Zichen Wang, Jiong Lou, Zihan Wang, Shuangjia Zheng, Jie Li
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22080v1

A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training methods turn these trajectories into learning signals using supervision from reference answers, verifiable feedback, or external teachers. Without such supervision, learning from the model's own generations becomes less straightforward, as their correctness cannot be reliably assessed. An incorrect solution may nevertheless contain useful intermediate reasoning, so its value as supervision need not be determined solely by its final answer. Can a model improve by learning from its unverified peer solutions without first determining which are correct? We propose Shared Residual Distillation (SRD), an on-policy self-distillation method that learns from the model's own unverified peer trajectories. SRD compares how peers change the prediction distribution relative to a control, retaining adjustments that agree in direction and are conservative in magnitude. This yields supervision without treating any complete solution as correct, and the trained model requires no peers at inference time. Starting from the corresponding base models, SRD raises mean AIME24--26 avg@12 from 11.02 to 16.20 on Qwen3-1.7B, from 19.07 to 45.46 on Qwen3-4B, and from 21.39 to 54.44 on Qwen3-8B. Controlled ablations support the value of the shared-residual construction, and we observe no degradation relative to the base models on two general-capability benchmarks.

---

### Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones

Authors: Nathan Chalumeau, Xavier Renard, Remi Meynadier, Hugo Rakotoarimanga, Marcin Detyniecki, Emmanuel de Bezenac
Published: 2026-10-15
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2610.22077v1

Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the computational cost. Yet, whether this success extends to extreme events remains contested. Earlier evaluations have exposed important shortcomings, but have largely focused on deterministic models and metrics, leaving the capabilities of the latest probabilistic models less understood. We conduct an extensive benchmark of tropical cyclone forecasting, comparing GenCast, FourCastNet 3, and FGN with ECMWF's operational physics-based ensemble, IFS-ENS. We develop a suite of probabilistic metrics and diagnostic analyses to assess cyclone tracking, intensity biases, uncertainty, and the wind-pressure relationship that characterizes storm structure. We find that, despite remaining limitations in intensity and ensemble spread, leading AI models substantially outperform IFS-ENS in cyclone tracking: FGN achieves better probabilistic location scores for 90% of evaluated storms in 2025. Further analyses reveal model-specific failure modes and suggest a lingering influence of pretraining data, pointing to opportunities for targeted improvement. Nonetheless, these results suggest that AI models are capable of capturing physical relationships that remain predictive well beyond typical weather conditions, motivating further investigation into how these capabilities emerge and how to strengthen them.

---

### Retrofitting Recurrent Vision-Language Models from Pretrained Backbones

Authors: Madhav Iyengar, Andreas Geiger, Hilde Kühne
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.22075v1

Recent work shows that depth recurrence can be retrofitted into pretrained language models. In this work, we adapt this paradigm for visual understanding, using depth recurrence to reduce the parameter footprint of a pretrained vision-language model (VLM). To this end, we prune layers from the language backbone of the VLM and loop over a subset of the remaining layers. At each step of the loop, a linear adapter merges the block's output with the token representations from the preceding layers and projects the fused representation back into the block. As the pruning impacts the original model performance, we propose a three-stage recovery training: first, we leverage a language-only pretraining to recover the performance of the language backbone, followed by an alignment of the vision-language projector, and a full fine-tuning of the model via visual instruction tuning. In the first and the last stage, we distill the outputs of the pretrained non-recurrent model into the recurrent model, which further improves the recovery. We evaluate the proposed approach on the TinyLLaVA-1.4B backbone without introducing any new vision-language data during retrofitting. Our experiments demonstrate that the retrofitted recurrent model outperforms the unpruned baseline trained with the same recovery data while storing 23.3% fewer language parameters. We further show that the proposed retrofitting recurrence outperforms the setup of converting a recurrent LM into a VLM on the same data. Additionally, our ablations show how design choices, such as the adapter between recurrences and a larger recurrent block, lead to the improved performance of our approach. Finally, we find that our proposed model gains on reasoning-oriented benchmarks, whereas its performance on basic visual understanding benchmarks remains on par with the baseline.

---

### The Right Byte First: How UTF-16 Helps Multilingual Boundary Prediction

Authors: Hyunsik Kim
Published: 2026-10-15
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.22071v1

Many hierarchical byte-level language models group bytes into patches using a learned boundary predictor whose view of the next codepoint depends on encoding and lookahead. In UTF-8, codepoints of many scripts take three bytes: 8 of 24 bits mark length and continuation, and the first byte carries only 4 high codepoint bits. After the same left context, a mark extending a grapheme cluster and a letter starting the next can thus share their first byte. Universal Byte-Level Encoding (UBE) keeps one- and two-byte UTF-8 encodings but writes these codepoints as two UTF-16 bytes, low byte first, so its first symbol carries 8 low codepoint bits that can distinguish such continuations. We train small causal predictors on matched FineWeb-2 text and evaluate on FLORES-200 under UTF-8, UBE, and UBE's same-length big-endian variant. At one-symbol lookahead, balanced grapheme-boundary error at codepoint boundaries across 17 languages in 13 Brahmic scripts is 8.76% with UTF-8, 8.62% with the big-endian variant, and 0.06% with UBE. When the target instead retains a parent tokenizer's subword cuts at grapheme boundaries, UBE lowers the mean error relative to UTF-8 at the same lookahead by 72.91% in Korean, 35.29% in Chinese, and 67.32-99.55% in eight more scripts. In the seven of them whose main Unicode block fits on one 256-codepoint page, the big-endian variant stays within 3.0% of UTF-8, so the gain follows byte order, not length. In Korean and Chinese, UBE's mean error falls below UTF-8's final mean error after only 25% and 37.5% of training. Which byte comes first thus affects how much lookahead a byte-level boundary predictor needs.

---

### Memory as Weights: Internalizing Long-Term History for Streaming Videos

Authors: Zhuoming Liu, Jinhong Lin, Lin Zhang, Yiwu Zhong, Yin Li
Published: 2026-10-15
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.22070v1

Streaming vision-language models (VLMs) must continuously integrate information from the past while remaining responsive to current observations and user queries. Existing memory mechanisms typically compress, retrieve, or cache historical observations and reintroduce them into the input context, forcing historical memory and current observations to compete for limited context. We propose MaLoW, a streaming memory framework that instead internalizes historical context into evolving lightweight parameter updates. MaLoW uses a recurrent HyperNetwork to incrementally consolidate incoming video observations into fixed-size LoRA weights, allowing historical information to be carried forward without revisiting the full video stream. In doing so, MaLoW represents history as weights, while keeping the current observation as input. To support training, we further construct MaLoW-Instruct, a large-scale streaming video dataset containing 381K question-answer pairs over 56K videos. We conduct extensive experiments to demonstrate that MaLoW achieves strong performance on OVO-Bench, StreamingBench, and StreamArena. On the backward split of OVO-Bench, MaLoW outperforms prior memory approaches by 3.9% to 11.8% across different video backbones while incurring only modest latency overhead. Beyond streaming video understanding, MaLoW also generalizes to vision-language-action models, improving the action success rate on Simpler WidowX by 9.3%.

---

### When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models

Authors: Wei Cai, Jian Zhao, Yuchen Yuan, Xuelong Li
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22068v1

Multimodal large language models (MLLMs) can act unsafely when individually benign images and texts are interpreted jointly. Beyond implicit reasoning risk, where reasoning drifts toward harm, we identify intent-level risk, where cross-modal ambiguity silently commits the model to a hazardous premise that path-level optimization alone cannot correct. We propose SAFE-PRO, which uses a Risk-Conditioned Uncertainty (RCU) signal, combining predictive entropy with a learned cross-modal risk score, to decide when to ask safety-grounded clarifying questions and where to apply path optimization, under a reward that prioritizes safety and penalizes over-refusal. We also build SSUI-Dialog, a multimodal multi-turn dataset with dual-intent supervision, and theoretically analyze gradient variance and unsafe-completion risk under RCU. Across seven benchmarks and two base MLLMs, SAFE-PRO consistently improves safety over SRPO, roughly halves its over-refusal, and surpasses GPT-4o and Claude-3.5-Sonnet in average single-turn safety.

---

### Beyond Context Length: Characterising the Difficulty of Long-Context Reasoning

Authors: Shiwen Qin, Cameron Barker, Henry Gouk, Elliot J. Crowley, Shay B. Cohen, Mirella Lapata, Miao Li
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.22067v1

Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. However, context length alone cannot explain why models fail on long-context tasks that require reasoning over complex information. Contexts of equal length can pose very different challenges: a task may be solvable from a single local passage, or it may require integrating evidence distributed across the full context. We quantitatively characterise this difficulty through three properties: evidence scope, how much necessary information must be found; evidence dispersion, how widely that information is scattered within the context; and reasoning depth, how many dependent steps are needed to derive an answer from it. We construct LURCH, a multi-domain question-answering benchmark of 6,550 instances with supporting evidence and reasoning graphs, enabling all three properties to be quantified. Evaluations of proprietary and open-weight models show that: (1) at fixed context length, all our three properties are strongly negatively correlated with model performance; (2) as context length increases, performance degrades sharply on samples with dispersed evidence, whereas it remains relatively stable on samples with localised evidence; and (3) difficulty compounds across properties, as questions with moderately high values on all three are harder than those with an extreme value on just one. These findings establish evidence scope, dispersion and reasoning depth as measures of long-context reasoning difficulty that complement context length.

---

### Prism-1: Position- and Rival-Independent Scoring for System One Models

Authors: Yao Long Teng, Jianguo Huang, Yanchen Deng, Jiayi Cai, Bo An
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22066v1

Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in one forward pass, without generated reasoning. Web systems increasingly build them by reading decisions from language models. Two axioms of rational choice are natural requirements for such decisions, because in web systems the listing and the option set are determined by other components and can change or be manipulated: the order in which the options are listed should not matter, and adding an option should not change the relative odds of the others (Luce's choice axiom). We test the standard reads, namely single-choice question (SCQ) prompting, with shuffled-order training, order averaging or sorted options, and invariant set architectures, and find that each violates at least one axiom: one shuffle changes 12-20% of SCQ answers, sorting only freezes an arbitrary convention, and a well-chosen added option steers 4-34% of decisions. By Luce's theorem, a read satisfies both axioms only if it is a softmax over scores that each depend on one option alone, so in a transformer they hold by construction only if no token that scores an option sees another. We implement this as Prism-1 (Position- and Rival-Independent Scoring for System One Models): every option is read in its own block at shared positions, with the model's usual left-to-right attention, in one forward pass. On five benchmark sets with Qwen3-8B and Gemma 4 12B, SCQ prompting trained on the same data still changes 7% of its answers under one shuffle, and an added irrelevant option steers 12% of its decisions. Prism-1 stays within one point of that baseline's accuracy and is 2-4 points more accurate once only answers that survive a reordering are counted, while no shuffle changes any of its answers and no added irrelevant option moves its choice among the others.

---

### ABNAT: Attention-Based Noise-Aware Training for Robust Transformers on Analog Compute-in-Memory Systems

Authors: Wenshuai Yao, Wenyong Zhou, Hanyong Shao, Zhiyuan Ning, Yizhe Chen, Yuannuo Feng, Kechao Tang, Ru Huang
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.22065v1

Transformer-based models have become the backbone of a wide range of tasks, but their intensive computation and data movement incur substantial energy overhead. Analog compute-in-memory (CIM) offers an energy-efficient alternative, yet its inherent hardware non-idealities perturb stored weights and can significantly degrade model performance. Although existing noise-aware training (NAT) methods improve robustness by injecting noise during training, they largely overlook the critical role of attention mechanisms in Transformer inference.To bridge this gap, we analyze how CIM-induced noise reshapes attention in Transformers and identify two key observations: (1) the divergence between clean and noisy attention maps increases substantially in deeper layers, and (2) conventional NAT can remain overconfident even when its attention routes deviate markedly from the clean reference. Motivated by these findings, we propose ABNAT, an attention-based noise-aware training framework that teaches the noisy student to preserve the clean teacher's headwise attention routes rather than merely reproduce answers, without hardware changes or inference overhead; selective variants further reduce training cost.Extensive experiments across vision, language, and multimodal Transformers show that ABNAT consistently improves robustness over corresponding NAT baselines, improving noise-degraded accuracy by up to 11.28% and reducing attention deviation by up to 85.77%.

---

### Documenting Trofinetide Treatment Phenotypes in Rett Syndrome with a Dual-LLM Consensus Pipeline

Authors: Daniel Palacios, Guantong Qi, Mikael Guzman Karlsson, Shawntel K. David, Mohammed Sameeruddin, Bernhard Suter, Zhandong Liu, Davut Pehlivan, Hu Chen
Published: 2026-10-15
Categories: q-bio.QM, cs.CL
arXiv: https://arxiv.org/abs/2610.22062v1

Objective: Trofinetide, approved in 2023 as the first Rett syndrome treatment, lacks scalable real-world monitoring because chart review is labor-intensive. We developed a dual large language model (LLM) consensus pipeline to extract 18 treatment-response phenotypes, comprising 4 adverse effects, 13 Rett clinical features, and medication refusal, from clinical notes. Materials and Methods: We analyzed 26,763 notes from 108 patients with confirmed sustained trofinetide exposure at Texas Children's Hospital. The pipeline filters notes by keyword, classifies each through two LLMs requiring consensus, and aggregates a patient-by-timepoint matrix. Architecture and prompt were selected on a diarrhea development set, then frozen and applied to the other 17 phenotypes with the phenotype definition substituted, as an out-of-sample test. The reported prompt comparison scores 183 expert-labeled cells. Results: A prompt requiring diarrhea to be active and severe performed best (84.2 $\pm$ 0.0% accuracy; F1 = 0.674), 47 percentage points above regular-expression matching ($p < 0.0001$). Expert reviewers judged six of the pipeline's calls per phenotype, three positive and three negative, and agreed with 90.2% (92/102). The 13 Rett clinical features are manifestations of the disorder itself rather than adverse effects of trofinetide. Gross and fine motor impairment, language/communication, and stereotypy were documented present in 92-100% of patients at every visit. Discussion: In-context LLM extraction captured multi-domain treatment responses. The outcome is documented presence at each visit, not a direction-of-change judgment. Conclusion: Coupling in-context LLM reasoning with a consensus architecture offers a scalable alternative to keyword and regular-expression extraction for real-world evidence, adapting to new phenotypes and medications through configuration alone.

---

### FAOPs: Normal Forms and an Algebra for AI Agent Workflows

Authors: Ali Mohammadi Shanghooshabad
Published: 2026-10-15
Categories: cs.AI, cs.DB, cs.PL
arXiv: https://arxiv.org/abs/2610.22061v1

Organizations increasingly encode operational procedures as multi-step agent skills, here called Agent Operating Procedures (AOPs), that must be traceable, auditable, reproducible, access-controlled, and bounded in time and cost, requirements that regulated sectors make mandatory. Yet AOPs are typically kept as coarse-grained files, in which steps bundle actions, copied procedures drift apart, any step may reach any tool, and refactoring goes unchecked. We present Functional Agent Operating Procedures (FAOP), a formal theory that brings database-grade discipline to AI agent workflows. FAOP recasts each workflow as a typed function over scoped state and subjects an entire library to four progressive normal forms: Decomposed (FNF-1) splits a workflow into atomic steps, Typed (FNF-2) makes its data flow explicit and type-checked, Factored (FNF-3) gives each shared procedure a single canonical definition so a change propagates instead of drifting, and Scoped (FNF-4) confines every step to least-privilege tool access. Once normalized, every atomic step is a separate entity with a declared contract and can be type-checked, scope-confined, bounded, tested, traced, and audited on its own. A FAOP algebra of provably sound equalities turns refactoring and parallelization into compiler rewrites; orthogonal extensions add verified termination (+V), optimization (+O), and time and cost bounds (+B); and an architectural-level classifier (0-3) determines whether a workflow needs AI at all. Together, these make integrity, isolation, typing, termination, cost, and optimization compile-time concerns across the whole library, not runtime hopes. We implement the theory in SkillBase, an AOP management system (what PostgreSQL is to data, SkillBase is to AOPs), together with a separate executor that enforces these guarantees at run time. A worked financial workflow illustrates the approach end to end.

---

### FeaTok: Feature-Loss Tokenization for Image Generation

Authors: Zhang Xiaofeng, Samuel Lavoie, Nicolas Beltran-Velez, Jianhao Yuan, Felix Friedrich, Jakob Verbeek, Aaron Courville, Michal Drozdzal, Adriana Romero-Soriano
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.22060v1

Discrete image generators learn the distribution of tokens produced by an image tokenizer. These token representations should be easy for generators to model, not merely enable faithful image reconstruction. Yet these tokenizers are commonly trained to reconstruct pixels, which prioritizes low-level fidelity and may disrupt representation structure useful for generation. Motivated by feature-predictive self-supervised learning, we introduce feature-loss tokenization (FeaTok), which trains discrete tokens by reconstructing pretrained features rather than pixels. Ablations across SigLIP, SigLIP2, DINOv2, and DINOv3 show better generative performance with FeaTok. In class-conditional generation, FeaTok advances the quality-compute Pareto frontier, reducing gFDr6 at 256x256 by up to 29 percent over the strongest discrete baselines and outperforming the strongest unguided continuous baseline (RAEv2) with 38 times less sampling compute. FeaTok also achieves higher human-preference reward-model scores than prior art without reward-based training and surpasses continuous and discrete text-conditional baselines on three benchmarks with only 500 fine-tuning updates after pre-training.

---

### Progress Reward Model for Reinforcement Learning via Large Language Models

Authors: Xiuhui Zhang, Ning Gao, Xingyu Jiang, Yihui Chen, Yuheng Pan, Mohan Zhang, Yue Deng
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22056v1

Traditional reinforcement learning (RL) algorithms face significant limitations in handling long-term tasks with sparse rewards. Recent advancements have leveraged large language models (LLMs) to enhance RL by utilizing their world knowledge for task planning and reward generation. However, planning-based approaches often depend on pre-defined skill libraries and fail to optimize low-level control policies, while reward-based methods require extensive human feedback or exhaustive searching due to the complexity of tasks. In this paper, we propose the Progress Reward Model for RL (PRM4RL), a novel framework that integrates task planning and dense reward to enhance RL. For high-level planning, a complex task is decomposed into a series of simple manageable subtasks, with a subtask-oriented, fine-grained progress function designed to monitor task execution progress. For low-level reward generation, inspired by potential-based reward shaping, we use the progress function to construct a Progress Reward Model (PRM), providing theoretically grounded optimality and convergence guarantees, thereby enabling effective policy optimization. Experimental results on robotics control tasks demonstrate that our approach outperforms both LLM-based planning and reward methods, achieving state-of-the-art performance. Code is available at https://github.com/deng-ai-lab/PRM4RL.

---

### Name-Bias in Large Language Models

Authors: Kalyan Bhetwal, Ceren Mert, Ian Whitehouse
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.22053v1

Names carry demographic indicators such as age, gender, and race, which makes them a subtle but strong target of bias in large language models (LLMs). In this work, we present an evaluation of name-based bias across 6 local large language models spanning multiple providers and parameter scales. Using a fill-in-the-blank task, we prompt these models to choose between pairs of first names drawn from U.S. Social Security Administration datasets and a race classification dataset by Rosenman et al.. Our experimental de- sign isolates age and gender effects through balanced name pairings and sentence templates that share a fixed syntactic structure. Across 300,000 local LLM responses, we find consistent and measurable name bias. Models prefer names that are less stereotypically male, older, popular, and white. Furthermore, we find that name-bias is highly sentence-dependent, but not more than associated stereotypes, and gender is the most significant bias, followed by age, name popularity, and race. Our results demonstrate that name-based bias remains pervasive even in local LLMs, highlighting the necessity for standardized evaluation methods and mitigation strategies.

---

### Rethinking Successive Rejects Algorithms

Authors: Mohamed Khair, Junpei Komiyama
Published: 2026-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.22051v1

In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward. Successive Rejects (SR) is a simple fixed-budget best-arm identification algorithm that eliminates one candidate arm at each phase. At first glance, SR seems to have limited adaptivity, since it follows predetermined phase lengths. However, for Gaussian arms with common variance, SR's worst-instance error exponent normalized by the popular complexity measure $H_1(P)$ is optimal up to a constant factor, which partly explains why SR's performance is competitive compared with state-of-the-art adaptive sampling algorithms. In this paper, we extend the framework of SR by optimizing its predefined schedule of phase lengths. We formulate phase-schedule design as an optimization problem for the normalized error exponent. Then, we introduce a version of SR with the optimized schedule, which we call $H_1$-balanced Successive Rejects ($H_1$-SR). This schedule is optimal within the class of SR-type algorithms with deterministic equal-count schedules. For Gaussian arms with common variance, $H_1$-SR achieves at least $11/12$ of the optimal normalized rate over all adaptive algorithms for every $K\ge2$, and this approximation ratio converges to one as $1-O(1/\log K)$ as $K\to\infty$. This is a significant improvement over original SR, whose corresponding fraction of the optimal normalized rate converges to $1/4$. Finally, experiments on ten synthetic instances and two dataset-derived Gaussian benchmarks compare the optimized schedule with original SR at finite horizons. They show substantial gains on many instances while also exposing a regime in which more aggressive early elimination is costly.

---

### Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data

Authors: Omer Imran
Published: 2026-10-15
Categories: astro-ph.IM, cs.LG, physics.pop-ph
arXiv: https://arxiv.org/abs/2610.22050v1

Radio technosignature searches rely on machine learning detectors to shrink the candidate pool before a human looks at it. They are validated on held-out data from the training distribution, which excludes the cases where they are most likely to fail: a technosignature has unknown morphology, and terrestrial interference is unbounded in variety. I trained a standard competition detector once, froze it, and probed it with 15,000 injections across ten morphologies and five amplitudes, placed into real Green Bank backgrounds. Two directions were tested: genuine signals with morphologies other than a straight narrowband line, and interference resembling the training data. Recall did not follow the predicted ordering, and it fell as signals brightened, even for a needle of the kind the detector was trained on (from 0.590 to 0.090). One interference morphology reached a false positive rate of 0.627, comparable to the detector's own baseline recall of 0.5525 on genuine signals. Gradient-weighted Class Activation Mapping (Grad-CAM) showed attention along the injected path in one missed family by a pre-specified test, and visually in a second. A pre-specified, time-averaged ON-OFF filter removed false alarms and genuine detections at the same rate. The detector reads only the ON panels. Since the only evidence distinguishing a genuine candidate from terrestrial interference lies in the discarded OFF panels, it cannot tell if a signal originates from the target star; it can only tell if it resembles the training data. This explains the false alarm directly; the missed signals reflect what the detector learned to recognise, which reading the OFF panels would not by itself change.

---

### Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal Alignment

Authors: Corentin Caris, Louis Jalouzot, Nona Rajabi, Géraud Ilinca, Ahmed Hassayoune, Asilbek Muminov, Thaddée Delebarre, Clara Fonteneau, Charles Maussion, Bertrand Thirion, Alexis Thual, Antoine Collas
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.22049v1

Reconstructing what a person perceives from their brain activity is a stringent test of whether neural recordings carry meaningful information. Naturalistic speech offers a rich testbed for this challenge: it unfolds over multiple timescales, but fMRI's noisy, temporally smeared measurements make this structure hard to recover. We introduce NOEMA, a temporal convolutional decoder that aligns windows of consecutive fMRI measurements with multimodal stimulus embeddings. These embeddings combine complementary text, audio, and speech representations of the same stimulus segment, enabling its retrieval directly from brain activity. On two naturalistic speech datasets, Cephalonauts One and LeBel, NOEMA retrieves the correct segment among 2,000 candidates within the top 10 for more than 42% of held-out queries. This substantially outperforms baseline decoders, an advantage that persists when the candidate pool is extended with thousands of distractors absent from training. Controlled ablations establish the contributions of temporal modeling and complementary stimulus representations.

---

### Effectiveness of Hidden-State Probes for Localizing Reasoning Failures

Authors: Shubham Subhnil, Yannis Belkhiter, Erik Miehling, Adam Dahlgren Lindström, Elizabeth M. Daly
Published: 2026-10-15
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.22046v1

Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capability, another attempt would succeed, or one step in an otherwise recoverable trace made the trace fail. Standard hidden-state probes are trained on final-answer correctness, a label that conflates these cases. Monte Carlo rollouts distinguish the cases and locate the failing step at additional inference cost. We test the hidden states of 4B and 8B reasoning models for the failure type and the failing step and compare each probe with the strongest baseline that uses no hidden states. On incorrect 8B traces, the confidence probe, a calibrated correctness probe at a midpoint cutoff, misses 81% of cases in which a single step makes the trace unrecoverable and 47% of cases in which another attempt would succeed. A probe with a different training design over the same states reverses the ordering of these two kinds of failure, so either ordering can be read from those states. At both scales, no single tested probe locates the failing step more accurately than a rule based only on trace length, and at 4B a probe trained to predict that step fails to outperform this rule in any of 10 runs on identical traces. The confidence probe therefore indicates that an answer is wrong, but its failure-type ordering depends on its training design.

---

### Momentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts

Authors: Alina Khaybullina
Published: 2026-10-15
Categories: cs.LG, cs.AI, cs.CL, q-fin.GN
arXiv: https://arxiv.org/abs/2610.22043v1

Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, non-informational commentary tone, and whether fixed actual EPS beats a manipulated consensus. Six instruction/chat checkpoint conversions from four families (0.49-7.61B base parameters) receive 2,016 prompts each under a direct-answer Q8_0 protocol. The design includes 24 numerical blocks, six commentary pairs, profits and losses, rising and falling annual EPS, and two surprise sizes. Both A/B answer assignments and U/D cover all 384 primary scenarios per conversion. We estimate matched changes in conditional answer-prefix scores, not calibrated market probabilities. Across these checkpoints, the primary EPS contrast ranges from -0.19 to 86.80 percentage points. The magnitude of the primary signed tone contrast exceeds that of EPS in 5 of six models, and momentum exceeds it in 5. Natural-word numerical diagnostic accuracy ranges from 51.0 to 95.8 percent. Answer-encoding, wording, context, and conversion controls qualify these results. The experiment measures observable input reliance and numerical recognition; it establishes neither an internal reasoning mechanism nor realized return predictability. Public benchmark prompts, recorded scores, and an interactive recorded-results explorer accompany the study.

---

### WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents

Authors: Weihao Li, Zihang Xu, Zhongqiu Wang, Songwei Yu, Wenqiang Zhu, Yuechen Luo, Jingxuan Xu, Yanan Wu, Haoyang Huang, Ken Deng
Published: 2026-10-15
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2610.22039v1

Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordinated modifications across a repository. Yet most executable repository-level benchmarks retain a single issue or PR as the task unit, while existing multi-PR settings rely on coarse aggregation and structure-agnostic evaluation. This mismatch obscures dependencies among changes and limits progress measurement and learning signals for long-horizon code agents. We introduce WEAVE, a framework that transforms verified PR histories into executable, dependency-structured tasks. WEAVE leverages repository-calibrated typed change loci to organize related PRs into bounded DAGs and instantiate each as a unified executable task. We further introduce Graph Credit, a deterministic, test-grounded metric that measures dependency-consistent partial progress and supports dense, verifiable rewards for reinforcement learning. Experiments on task construction, agent evaluation, supervised fine-tuning, and reinforcement learning show that WEAVE yields coherent executable tasks, enables more faithful progress measurement than flat scoring, and provides effective supervision and verifiable rewards for training code agents.

---

### ETH: Data-Balanced Heterogeneous Pipeline Parallelism for Training Large Models

Authors: Mianjie Yu, Zhongmin Zhao, Zizhao Mo, Jianxiong Liao, Wenxuan Li, Yulin Qiao, Huanle Xu, Wenquan Yang, Yongqiang Yang, Zeren Li, Ruifeng Tang, Chengzhong Xu
Published: 2026-10-15
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.22035v1

Current heterogeneity-aware training systems for large models balance workloads by assigning unequal numbers of layers across pipeline stages, a strategy aimed at equalizing execution time through a unique pipeline configuration. However, this approach fails to address critical memory constraints and suffers from inherently coarse balancing granularity. In this paper, we propose Heterogeneous Pipeline Parallelism (HPP), a novel approach enabling efficient and fine-grained data balance across heterogeneous pipelines. To address HPP's key challenges, prohibitive search overhead for optimal configurations and high communication overhead from asymmetric All-Reduce, we design the ETH training system. ETH employs a hierarchical workload balance framework that jointly optimizes balance across heterogeneous pipelines and within individual pipeline stages. To mitigate asymmetric communication costs, ETH implements block-wise gradient aggregation. Furthermore, it integrates specialized optimizations that dramatically reduce HPP configuration search overhead. Evaluations demonstrate ETH achieves up to 2x training speedup while reducing configuration generation overhead by up to 56x compared to state-of-the-art systems. The code is available at https://github.com/YuMJie/ETH.

---

### Designing Experiments for External Decision Makers

Authors: Sahel Iqbal, Tom Rainforth
Published: 2026-10-15
Categories: stat.ML, cs.LG, econ.TH
arXiv: https://arxiv.org/abs/2610.22032v1

Standard Bayesian experimental design (BED) methods assume the experimenter alone will act on the data, choosing the best action given their own beliefs and goals. In practice, data are often acted on by external parties whose procedures the experimenter cannot change and may not know, particularly when the data are released publicly. To extend BED to such settings, we introduce usage-aware experimental design, a framework in which an adaptive design policy is trained to minimise the usage risk: the experimenter's expected loss when one or more external rules act on the collected data. These rules may be non-Bayesian or black-box, and when several may apply, we either average over them or take the worst case. We show that, unlike in standard BED, more informative data can be harmful under such rules, so the usage risk cannot in general be expressed as an expected uncertainty reduction; our framework thus strictly generalises standard BED. We then use it to tackle a range of problems that are difficult to address with existing approaches.

---

### GraphACM: Graph-based Action Consistency Measurement for Uncertainty Quantification in LLM Agents

Authors: Yaxin Ma, Wenbo Zhang, Satya Krishna Pothapragada, Alina Zare
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.22031v1

Behavioral consistency across repeated executions provides an informative signal for assessing the reliability of large language model (LLM) agents. However, existing approaches typically summarize consistency with a single task-level score, without identifying where behavioral differences occur or whether actions are compared under equivalent decision contexts. We propose a graph-based framework for fine-grained behavioral consistency measurement and uncertainty quantification. Given multiple rollouts of the same task, we merge equivalent states into a directed, action-labeled graph, enabling action comparisons at shared decision states. We introduce node-level and global measures of action consistency, using the global consistency score as a proxy for uncertainty to predict task success or failure. Experiments across three LLMs on ALFWorld, AppWorld, and WebShop demonstrate that our measure is positively associated with task success and achieves an average AUROC of 0.811 for task-success prediction, outperforming the strongest behavioral-consistency baseline (0.729) and verbalized confidence (0.769). These results highlight the effectiveness of state-conditioned behavioral consistency and pinpoint where agent actions agree.

---