# Research Papers — 2026-10 · bundle page 31 of 156

> Full-text markdown of papers #1501–1550 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/31
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/30.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/32.md)

### Model-Based Online Decision Making via Generative Trajectory Planning

Authors: Haldun Balim, Yilun Du, Na Li
Published: 2026-10-13
Categories: cs.LG, cs.AI, cs.RO, eess.SY
arXiv: https://arxiv.org/abs/2610.18677v1

Online decision-making faces a tension between efficient inference and long-horizon reasoning. Value-based methods rely on short-horizon bootstrapping that limits the propagation of long-term information, while trajectory optimization methods plan explicitly but must solve a high-dimensional optimization problem at every decision step. We propose Generative Trajectory Planning (GTP), a model-based framework that addresses this tension by learning a generative model as a proposal distribution over action sequences. Instead of optimizing sequences from scratch, GTP samples candidate sequences from a diffusion prior and refines them using learned dynamics, reward, and value models, enabling efficient trajectory-level reasoning. Across continuous control and long-horizon manipulation tasks, GTP matches or exceeds state-of-the-art model-free, diffusion-policy, and model-based baselines, and remains stable in regimes where strong baselines degrade. Our results suggest that generative models are best understood not as policies, but as structured proposal distributions for planning, offering a new perspective on how to integrate generative modeling with model-based decision-making.

---

### From Relation-Specific Heads to Shared Interventions: Contextual Entrainment in Language Models

Authors: Jinghan Zheng, Jiajun Shi
Published: 2026-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.18674v1

Large language models rely on prompt context to perform in-context learning, follow formats, and adapt to local evidence. This ability, however, also raises a robustness concern: models may reuse irrelevant tokens from earlier context when answering a later query. Prior work identifies this behavior as contextual entrainment and finds attention heads whose ablation reduces it, arguing that these heads are largely task- or relation-specific. But are the mechanisms behind contextual entrainment truly isolated by relation, or do relation-conditioned searches recover reusable components shared across relations? Using factual-distractor relation-completion prompts across 19 lexical-semantic subtypes, we identify attention heads whose ablation reduces entrainment and test how the resulting head sets transfer recovery ability across exact relations, semantic families, and mixed relation distributions. Same-family transfer exceeds different-family transfer, family residuals weaken once globally shared heads are removed, and subtype-specific searches repeatedly rediscover many global heads. Clean-completion and context-use probes further suggest that this shared intervention can reduce harmful copying while preserving ordinary relation completion and simple in-context abilities. Our findings provide a more precise perspective on contextual entrainment and its mitigation: harmful context following is not best addressed by searching for isolated relation-specific circuits, but by using heterogeneous attack prompts to reveal reusable intervention targets whose effects are shaped by semantic relation structure.

---

### SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation

Authors: Ziyang Song, Lia Shen, Yixuan Li, Qincheng Lu, Weihao Li, Haoran Xu, He Zhu, Xinyu Wang, Yue Li
Published: 2026-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.18672v1

Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among medical concepts. This limitation is especially pronounced for rare and fine-grained clinical codes in long-tailed vocabularies, where hierarchy-agnostic LM representations become less informative as concept frequency decreases. We introduce Semantic Medical Identifier (SMI), a training-free framework for constructing ontology-grounded Semantic IDs and hierarchy-aware medical concept representations. For each diagnosis, procedure, or medication concept, SMI defines its Semantic ID as the coarse-to-fine path through an expert-defined medical ontology. SMI then aggregates frozen biomedical LM embeddings across the corresponding ontology levels to form hierarchy-aware medical concept representations that preserve coarse-to-fine clinical semantics. The base SMI uses uniform aggregation across ontology levels, while a level-weighted variant selects global level weights on validation data. Our theoretical analysis shows that SMI yields more informative medical concept representations than hierarchy-agnostic LM embeddings, particularly for rare and fine-grained clinical concepts. Experiments show that SMI captures meaningful hierarchical structure and improves clinical relation prediction. On MIMIC-IV, SMI improves mortality prediction, readmission prediction, drug recommendation, and rare drug prediction. On eICU, SMI yields more robust patient representations under cross-hospital distribution shift.

---

### Perception Beyond the Visible: Incompleteness-Aware Scene Understanding for Robot Autonomy

Authors: Rohit Mohan
Published: 2026-10-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2610.18670v1

Reliable robot autonomy requires reasoning about the world from partial and noisy observations. However, many perception systems model only visible scene regions, rely on fixed semantic categories, and assume reliable sensor measurements. These assumptions break under occlusion, novel object encounters, and sensor degradation. In this paper, I present a research vision for incompleteness-aware scene understanding. I organize this vision around three fundamental challenges: incomplete evidence, incomplete knowledge, and incomplete sensor reliability. I discuss my research contributions toward addressing these challenges through amodal perception, semantic occupancy forecasting, open-world scene understanding, label-efficient learning, and uncertainty-guided multi-modal fusion. Building on these contributions, I outline future research directions toward belief-centric 4D scene representations. These representations aim to jointly model geometry, semantics, motion, and uncertainty. I also discuss active sensing and safe adaptation strategies that allow robots to reduce uncertainty through interaction. The goal is to develop calibrated and actionable scene representations that support reliable autonomy in dynamic, open-world environments.

---

### Known-Voice Cloning and the Limits of Personality Transfer for Character Design

Authors: Johanna Magdalena Kuch, Maud van Lier, Daksitha Senel Withanage Don, Patrick Gebhard, Tanja Schneeberger, Elisabeth André
Published: 2026-10-13
Categories: cs.CL, cs.AI, cs.HC, cs.RO
arXiv: https://arxiv.org/abs/2610.18669v1

Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitrary virtual characters. Prior work suggests that familiar vocal identity can carry over associated personality impressions to new targets such as robots or virtual characters. However, these works have mainly examined familiarity and personalization effects rather than directly testing whether a cloned familiar voice systematically transfers personality impressions to an embodied virtual character. Such transference raises the concern that cloned voices could be used to manipulate people into engaging with virtual characters as capable social actors. Across two studies, we investigated whether personality impressions transfer when a virtual character speaks with the cloned voice of a familiar person. Study 1 examined this question in a real-world university setting using the cloned voice of a lecturer familiar to the participating students. Study 2 examined the same question online using voices of social media content creators and members of their communities. Drawing on the concepts of identity activation, trait transfer, and person reconstruction, we show that evidence of personality transfer was limited in both studies. Observed effects were selective and did not generalize across traits or study contexts. In the online study in particular, recognizable voice identity cues activated expectations about the speaker but did not reconstruct the broader person impression. Qualitative responses further indicated that judgments were frequently shaped by perceived artificiality and by whether voice and appearance fit together. Our findings moderate common concerns that cloned voices straightforwardly manipulate people into perceiving artificial characters as capable social actors.

---

### PlanPath: Exploration-Guided Orchestration for Patient-Level Pathology Reasoning

Authors: Jiusong Ge, Mingzhao He, Qidong Liu, Chunbao Wang, Chunze Yang, Di Zhang, Jiashuai Liu, Mireia Crispin-Ortuzar, Huazhu Fu, Chen Li, Zeyu Gao
Published: 2026-10-13
Categories: cs.CV, cs.MA
arXiv: https://arxiv.org/abs/2610.18664v1

A patient's pathology case spans tens of slides from distinct specimens and anatomical sites, each carrying non-redundant, site-specific evidence. Forming a patient-level conclusion therefore requires locating the slides relevant to a given question and integrating complementary findings across them. However, existing pathology agents analyze one slide at a time and describe morphology rather than measure it, leaving evidence acquisition across a patient's specimens and patient-level quantification underexplored. To address this gap, we propose PlanPath, an agentic framework for patient-level pathology visual question answering (VQA). PlanPath turns the question into an exploration plan that specifies the evidence required, routes to the slides likely to carry it, and drives coarse-to-fine acquisition from tissue architecture down to individual cells. Tissue- and cell-level tools supply the counts, proportions, and extents, which PlanPath aggregates across slides into a traceable answer. To enable evaluation, we build two patient-level VQA datasets for renal and gastric cancer, averaging 15 WSIs per patient, with pathologist-verified question-answer pairs derived from diagnostic reports. Experimental results show that PlanPath outperforms the strongest baseline by 9.4% and 12.1% in overall accuracy on the two datasets and further improves existing slide-level agents when plugged into our framework. The dataset and code are available at: https://github.com/JSGe-AI/PlanPath_1.

---

### BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling

Authors: Mengyu Li, Qianqian Qu, Jun S. Liu
Published: 2026-10-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.18658v1

Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reused as a prior and combined with a task-specific likelihood to sample from the corresponding posterior. While such training-free samplers have been developed for diffusion and flow models, their counterpart for Schrödinger bridge (SB) models remains unexplored, despite the growing appeal of SBs as flexible stochastic transport models between general source and target distributions. We propose BridgeTwist, a training-free conditional sampler for pretrained SB generative models, formulated as a tempered twisted sequential Monte Carlo scheme. Its twist is a closed-form plug-in surrogate, obtained by combining the velocity and score fields exposed by SB pretraining into an endpoint predictor and evaluating the likelihood there. Since this surrogate is less reliable near the source, we temper the twist with a time-varying exponent, downweighting its influence at early steps. We further introduce a bridge-shaped inference-time diffusion schedule that concentrates the proposal noise in the interior of the path. Telescoping importance weights then cancel all intermediate twist factors, yielding an asymptotically exact sampler for the posterior. Empirically, BridgeTwist outperforms training-free baselines on class-conditional and text-prompted image generation, and is competitive with specialized inverse problem solvers on inpainting, deblurring, and super-resolution.

---

### Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback

Authors: Weida Liang, Kenji Kawaguchi
Published: 2026-10-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.18656v1

Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses. Yet similarity is not unique: lexical, semantic, structural, and stylistic resemblance can point to different candidates, and the task-aligned notion can change across instances. We introduce BASIS (Bayesian Axis Selection via Interactive Signals), a training-free Bayesian method that uses weak test-time feedback to infer which criterion in a supplied, task-specific library governs the current decision. It maintains a joint posterior over candidate targets and criteria, updates it from scalar scores, pairwise preferences, or verifier outputs, and selects probes by expected information gain. In a finite noisy model, we characterize when the target-criterion pair is recoverable and show why fixed-criterion and fixed-mixture rules can fail under criterion shift. Across concept recovery, reasoning exemplar selection, and response refinement, BASIS improves six-probe concept-recovery Success@1 from 56.0% to 68.1%, reasoning accuracy from 72.3% to 73.1%, and refinement win rate from 61.4% to 63.8% over tuned static mixtures. It also exceeds compute-matched best-of-N selection on reasoning (72.1%) and refinement (61.2%). Gains are largest under criterion mismatch and with larger candidate pools, and matched controls indicate that adaptive criterion weighting explains much of the benefit, with joint target-criterion inference adding further value. BASIS selects only among supplied criteria and does not discover new ones.

---

### Texture Interpolation as Texton Matching

Authors: Ido Madar, Gal Oren, Shai Avidan
Published: 2026-10-13
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2610.18655v1

Texture interpolation asks what should lie between two textures. Standard methods typically blend pixels or features at corresponding spatial locations, implicitly assuming that co-located elements should be mixed. For unrelated textures, however, this correspondence is arbitrary: a crack at one location has no particular relationship to a fiber at the same location in another image. We study whether this hidden pairing choice is itself a major determinant of interpolation quality. We represent textures as collections of local appearance vectors, or textons, and replace positional pairing with appearance-aware matching while keeping the encoder, representation, and decoder fixed. This isolates the effect of correspondence from changes in model capacity or training. Across texture pairs, appearance-aware matching consistently improves the distributional quality of interpolated midpoints over positional feature blending. Soft matching produces the strongest midpoint statistics, whereas one-to-one assignments yield more balanced transitions and closer agreement with the target endpoint. The same intervention also improves a second pretrained texture interpolator without retraining. These results identify correspondence as a first-class design choice in texture interpolation: meaningful transitions depend not only on how strongly two textures are mixed, but also on which local appearances are mixed with one another.

---

### Kwai Summary Attention V2 Technical Report

Authors: OneRec Team, Chenglong Chu, Guohong Mu, Guowang Zhang, Hao Peng, Hui Wang, Jian Liang, Jiangxia Cao, Jiao Ou, Jiaxin Deng, Lu Ren, Muhao Wei et al.
Published: 2026-10-13
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2610.18654v1

Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave these layers with full attention to retain exact access to the original text. In such hybrid KSA-Full architecture, the interleaving inserted summary tokens are served as a streaming flow role across different layers. Although effective, however, it also introduce some bottlenecks: (1) the different layers summary compression chunk must be same, therefore hard to reach a flexible KV Cache compression, e.g., different layer set different summary compression chunk window. (2) in the full-attention layers, the summary token introduced additional computation cost, but such layer ignore them and still pay quadratic prefilling, therefore unfriendly to the computation side. Motivated by them, we developed the KSA V2, which not only achieves a more flexible KV cache memory compression but also reduces the computation cost in Full attention layer. Specifically, we found that the summary tokens can serve two roles: the KV memory and sparse indexer.

---

### AMemOps: Evaluating Memory Updates in Long Audio Streams

Authors: Peiwei Chang, Li Zhang, Mark D. Plumbley, Philip J. B. Jackson, Wenwu Wang
Published: 2026-10-13
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.18652v1

Audio memory must recognise recurring sources across acoustic changes while keeping their attributes up to date. Overall accuracy does not reveal how these demands interact. We introduce Audio Memory Operations (AMemOps), a benchmark for latest-attribute retrieval, preservation of unchanged attributes and absent-source rejection in long audio streams. Paired controls vary recordings, training identities and earlier events to examine their effects on updating. Training on other recordings of the test instruments increases a reference delta-rule memory's update advantage over matched attention by 13.4 percentage points. At retrieval delays of 120\,s, matched histories separate benefits of consistent repetition from costs of conflicting earlier values, while additive-memory controls identify benefits of erasure.

---

### Does Pretraining Teach Chemical Language Models Chemistry?

Authors: Leif Sieben, Yoel Zimmermann
Published: 2026-10-13
Categories: cs.LG, cs.CL, physics.chem-ph
arXiv: https://arxiv.org/abs/2610.18651v2

Chemical language models (CLMs) are pretrained on large corpora of molecules with the aim of learning representations that transfer to diverse downstream tasks. Here, we systematically study the effects of pretraining using a series of such CLMs across 64 molecular property prediction datasets. We find that the downstream gains of pretraining in CLMs do not scale and performance saturates below gradient-boosting baselines. Across the regimes evaluated, only supervised pretraining on traditional physico-chemical descriptors consistently improves downstream performance for the CLMs tested whereas some forms of pretraining result in models worse than a randomly initialized encoder. While models can resolve molecular structure well, they do so no better than a randomly initialized model, suggesting that, at best, CLMs learn descriptor-like properties in addition to low-level token statistics during pretraining, but surprisingly little chemistry beyond what classical molecular features already capture.

---

### Does Pretraining Teach Chemical Language Models Chemistry?

Authors: Leif Sieben, Yoel Zimmermann
Published: 2026-10-13
Categories: cs.LG, cs.CL, physics.chem-ph
arXiv: https://arxiv.org/abs/2610.18651v1

Chemical language models (CLMs) are pretrained on large corpora of molecules with the aim of learning representations that transfer to diverse downstream tasks. Here, we systematically study the effects of pretraining using a series of such CLMs across 64 molecular property prediction datasets. We find that the downstream gains of pretraining in CLMs do not scale and performance saturates below gradient-boosting baselines. Across the regimes evaluated, only supervised pretraining on traditional physico-chemical descriptors consistently improves downstream performance for the CLMs tested whereas some forms of pretraining result in models worse than a randomly initialized encoder. While models can resolve molecular structure well, they do so no better than a randomly initialized model, suggesting that, at best, CLMs learn descriptor-like properties in addition to low-level token statistics during pretraining, but surprisingly little chemistry beyond what classical molecular features already capture.

---

### Tiny Recursive Message Passing

Authors: Tommaso Salvatori, Matteo Forasassi, Alexis Toumi, Giovanni de Felice
Published: 2026-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.18649v1

Message passing neural networks have shown remarkable performance in algorithmic and constraint reasoning, due to their ability to encode the structure of the task directly in the architecture. Recent work has shown that better results can be achieved using recursive transformers trained with deep supervision and truncated recursions, which make extremely deep loops stable to train, and equipped with test-time procedures such as discrete deduction lattices. In this work, we apply the same procedures to message passing networks, and show that the two ingredients are complementary, and lead to parameter efficient models: we obtain about $99\%$ test accuracy on Sudoku-Extreme with a model of $16$k parameters that trains in about $10$ minutes on an H100, or in $9$ hours on a CPU. We further show that the cost of truncating gradients grows with the number of rounds information needs to cross the graph, making the choice of wiring a trade-off between robustness to truncation and transfer across problem sizes. We conclude by showing that our models transfer zero-shot to larger instances than those seen during training, outperforming popular neural baselines on N-queens and Boolean satisfiability with a fraction of their parameters.

---

### ST-GRU PredRNN-V2: A GRU-Based Reformulation of PredRNN-V2 for Video Prediction

Authors: Augusta van Haren, Hanna Hoogen, Luca Pattavina, Quincy Rommen
Published: 2026-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.18645v1

Video prediction requires models to capture complex spatiotemporal dependencies and to retain relevant information over long sequences. PredRNN and its successor PredRNN-V2 address this challenge with spatiotemporal Long Short-Term Memory (ST-LSTM) units that maintain two separate memory states, at the cost of a relatively complex recurrent building block. In this work, we investigate whether the simpler gating of Gated Recurrent Units (GRUs) can be transferred to spatiotemporal predictive learning. To this end, we develop a spatiotemporal GRU (ST-GRU) unit as a GRU-based alternative to the ST-LSTM. The ST-GRU replaces the ST-LSTM's three gates per memory state with two GRU-style gates (update and reset), and merges the temporal memory state into the hidden state, which reduces the number of parameters by about 5%. We incorporate the ST-GRU into PredRNN-V2 and evaluate the resulting model on the Moving MNIST video prediction benchmark, following the original experimental protocol. Averaged over ten predicted frames, the ST-GRU-based PredRNN-V2 achieves an MSE of 55.1, an SSIM of 0.883, an LPIPS of 0.065 and a PSNR of 19.53dB. It does not surpass the original ST-LSTM-based PredRNN-V2 on MSE, SSIM or PSNR, but it achieves a lower LPIPS and performs on par with the earlier ST-LSTM-based PredRNN, while using a simpler recurrent cell. These results suggest that ST-GRUs are a promising building block for spatiotemporal predictive learning and motivate further work on their design and integration.

---

### MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization

Authors: Yangchengyu Zhou, Zhiping Wu, Runchang Jiang, Dongdong Ren, Youfang Han, Wei Zhao, Dongqi Cai, Wenbin Li
Published: 2026-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.18642v1

The Key-Value (KV) cache constitutes a dominant source of memory consumption during large language model (LLM) inference, particularly in long-context and complex reasoning scenarios. Existing KV cache quantization methods have explored different compression granularities, including layer-wise precision adjustment and token-level information preservation. In practical deployment, however, the key challenge is not merely compression, but how to allocate limited quantization resources among heterogeneous precision preservation strategies under a fixed KV cache memory budget. We propose MultiAlloc, a profiling-guided precision allocation framework for KV cache quantization that adaptively distributes limited quantization resources between layer-wise precision enhancement and token-wise preservation. MultiAlloc employs lightweight offline profiling to characterize layer sensitivity and token importance, enabling adaptive precision allocation under a fixed memory constraint. Guided by the profiled memory--accuracy trade-off, it automatically derives an effective precision allocation strategy without online allocation search, and applies the resulting policy during inference. Extensive experiments on reasoning and long-context benchmarks demonstrate that MultiAlloc consistently improves over layer-wise, token-wise, and recent multi-granularity KV cache quantization methods under matched memory budgets across diverse models, including Mistral, Llama, DeepSeek-Qwen, and QwQ.

---

### To Align or Not To Align: Check Your COMPASS Before You Train

Authors: Fabian Gröger, Petar Damjanović, Maria Brbić
Published: 2026-10-13
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.18638v1

Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints. However, finding compatible pairs typically requires costly empirical search, as compatibility is known only after alignment or merging. We propose COMPASS (COMPatibility ASsessment Score), a theoretically motivated diagnostic that estimates whether a model pair will be compatible prior to alignment or merging. Building on the observation that representational convergence is most robust at the level of local neighborhoods, COMPASS decomposes model compatibility into two cheap-to-compute axes: a pair-specific ease, defined as the $k$-NN overlap between the two encoders, and a paradigm-level ceiling, capturing the maximum overlap their training paradigms allow. Together, these two axes provide a ranking of candidate model pairs and prescribe how to act on each pair: (i) prioritize pairs that already agree and whose paradigms are compatible, (ii) invest additional compute on pairs with compatible paradigms but low initial agreement, (iii) switch the pretraining paradigm when it cannot support sufficient agreement, or (iv) deprioritize pairs that score poorly on both axes. We apply COMPASS to $72$ cross-modal alignment experiments and $392$ task-arithmetic model merges and show that compatibility estimates by COMPASS strongly correlate with downstream success, achieving average Pearson correlation of $0.91$ on cross-modal alignment tasks and $0.70$ on model merging.

---

### Grid or Nodes? Probing Object Memory in World Models Under Partial Observability

Authors: Justin McMillen, Yasin Yilmaz
Published: 2026-10-13
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.18637v1

A robot's world model must remember objects that leave the camera's view. FloWM, a learned world model, keeps them in a spatial grid of features that it moves with five built-in velocities. A node memory instead keeps each object's position and velocity as numbers. We compare them in FloWM's own block world, with an oracle-fed Kalman tracker as the node memory. How the grid is read changes its score: a single-cell probe finds 66% of out-of-view blocks, while FloWM's own probe 89%. FloWM also scores 8 points higher in view although no frame is shown, which we attribute to its write-back of its own predictions. Out of view, the tracker reaches FloWM's range in 14KB against 5.6MB, with no probe. On diagonal motion, outside its five velocities, FloWM finds 11% of blocks even after fine-tuning, while the unchanged tracker keeps 93%. Faster blocks defeat both until one more allowed speed takes the tracker to 94%, where FloWM's built-in shifts would need 25 copies of its grid. A learned node memory must still replace the oracles and handle velocity under noise, long gaps, and the bounce.

---

### DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models

Authors: Kérian Fiter, Angelica Portocarrero, Bentley Oakes
Published: 2026-10-13
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.18635v1

The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the conceptual architecture for these digital twins as an artifact for discussion. However, we find that the activity of modeling the digital twin for visualization and consensus-building can be quite tedious and time-consuming. In this article, we explore the automation of model generation using large language models, targeting the model required for digital twin reporting. Our approach is designed to ingest digital twin documents and output both the conceptual architecture visualization and a reporting page for that digital twin. We first extract from the input the key details aligning with our twenty-one-characteristic Digital Twin Description Framework described in previous work. Then, we generate a description model in the Ontological Modeling Language, representing the digital twin as a constellation of models, data, enablers, and services. We utilize refinement loops with large language models acting as judges and ontological reasoning to increase artifact quality as measured by our metrics. We investigate how architectural and parameter choices affect artifact quality, such as how refinement loops enable local large language models to produce sufficiently high-quality results comparable to larger models. We also detail insights and lessons learned useful for practitioners, such that they can integrate our techniques to accelerate their digital twin reporting or for other model generation tasks. These insights include the use of medium-sized local models (around 20 billion parameters), the avoidance of large language models as judges and clustering for characteristic extraction, and the recommendation of at least two reasoner loops for Ontological Modeling Language refinement.

---

### Geometric Calibration of Supervised Fine-Tuning

Authors: Jianzhu Bao, Jia-Chen Gu, Qingyuan Liu, Haozhen Zhang, Kai-Wei Chang, Nanyun Peng, Wenya Wang
Published: 2026-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.18634v1

Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directions. Within this view, supervised fine-tuning (SFT) is shown to induce dense updates that perturb the spectral geometry of pre-SFT weights along their principal directions, potentially disrupting the model's prior knowledge. These observations motivate using the geometry of pre-SFT weights as a reference for refining learned SFT updates. We study this perspective as Geometric Calibration and develop SPACE Subspace Projection for Adapted Checkpoint Enhancement), a lightweight post-hoc method that selectively reverts SFT update components within the principal subspace of the pre-SFT weights while preserving those in its orthogonal complement. SPACE is a data-free, training-free method that requires only the pre- and post-SFT checkpoints. We evaluate SPACE on Qwen2.5, Qwen3, Qwen3.5, Llama-3.1, and Olmo-3 models ranging from 2B to 14B, across mathematical, coding, and medical SFT, as well as several SFT variants. Overall, SPACE mitigates out-of-domain (OOD) capability regression while further improving in-domain (ID) performance over the uncalibrated SFT checkpoints. For math SFT, SPACE yields average ID/OOD gains of 2.85/2.26 points on Qwen2.5-7B, and 2.41/1.52 points on Qwen3-14B-Base, respectively. These results highlight how the geometric relationship between SFT updates and pre-SFT weights shapes the adapted model's capabilities and, more broadly, motivate geometry-aware parameter updates for continual model improvement.

---

### Breakdown of Conversational Involvement: A Joint Multi-Modal Analysis of Conversation Floors and F-formation Detection with Multiple Features

Authors: Zonghuan Li, Chirag Raman, Hayley Hung
Published: 2026-10-13
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2610.18627v1

Interactions happen universally and spontaneously in daily lives. Studying involvement in interactions helps us analyze who can influence who and has a wide potential in applications. Specifically, we consider conversational involvement in free-standing conversations. We study two operationalizations of an FCG: F-formations and conversation floors, and propose that current assumption that F-formations capture single conversations is insufficient. To illustrate how different implementations could impact the detected F-formations, we employ three analyses. First, we propose that speaking status can be used for estimating conversation floors, and leveraged it to analyze floors within F-formations. Second, we analyze spatial characteristics of the detection results by applying different feature sets on chosen baselines, and find that groups resulting from head features are more likely to be subsumed by groups detected using other features. Finally, we do a joint analysis which combines the spatial features and floor patterns in the conversation. We observe that certain pipelines can detect groups with single floors from upper body features, while retaining F-formations with lower body features. We conclude that a more detailed theory and framework is needed to holistically demonstrate conversational involvement within interactions.

---

### Falsification-proof non-market allocation mechanisms

Authors: Eduardo Perez-Richet, Vasiliki Skreta
Published: 2026-10-13
Categories: econ.TH, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2610.18625v1

Relying on manipulable characteristics to target the allocation of resources is fraught with difficulties. Naively optimal rules lead to falsification and allocative inefficiency. Optimizing the rule for allocative efficiency while accounting for falsification typically induces falsification, at a heavy cost to the agents. Moreover, falsification generates negative externalities. We characterize optimal falsification-proof rules under a broad range of falsification technologies. We also provide an honesty condition under which they solve the unconstrained problem of a planner who maximizes a weighted sum of allocative surplus and agents' welfare.

---

### MajorTOM:Elliot Pretrain, A Multi-Sensor, Multi-Temporal Pretraining Dataset for Earth Observation

Authors: Carmen Oliver Huidobro, Mikolaj Czerkawski, Kevin Monsalvez-Pozo, Cesar Aybar, Gustau Camps-Valls, Oscar J. Pellicer-Valero
Published: 2026-10-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.18624v1

Pretraining generalist Earth observation foundation models requires data that combine several sensors, varied temporal sampling and, increasingly, text, yet open datasets rarely provide all three in one consistent, easily accessible form. We introduce MajorTOM:Elliot Pretrain, a collection of 279,166 tiles of 10 km drawn from the Major-TOM grid by clustering AlphaEarth embeddings. Each tile stacks Sentinel-2 L1C, Landsat-8/9, Sentinel-1 RTC, Copernicus DEM and ESA WorldCover on a shared 1056x1056-pixel, 10 m grid, complemented by cloud masks, OpenStreetMap entities and ERA5 weather. The tiles are partitioned into three temporal regimes, Monotemporal (250,000 tiles, one acquisition), Monthly (12,500 tiles, twelve acquisitions spread over the annual cycle) and Burst (16,666 tiles, six acquisitions within 30 days), and are released as 6.3 TB of Cloud Optimized GeoTIFFs indexed by TACO v3 Parquet metadata, a standard that allows cloud streaming, efficient data access, and filtering before any pixel is read. A companion library derives sensor-tagged fact sheets, captions and 16 families of vision-language tasks from these layers at load time. We test our design choices in short pretraining runs of OlmoEarth-Base. First, a 25% subset of Major-TOM Core-S2L2A curated with AlphaEarth embeddings matches or exceeds the full corpus on 8 of 9 benchmarks. Second, on Elliot-Pretrain, adding Landsat-8/9 improves or matches Sentinel-2 only pretraining on every benchmark. Third, using DEM and WorldCover as prediction targets during pretraining further improves 8 of 9 benchmarks, while giving the same maps to the encoder as inputs degrades 5 of 9. Fourth, Sentinel-1 helps on 7 of 9 benchmarks, particularly on benchmarks with radar inputs. Fifth, rule-based captions match a small language model at no cost. The dataset is openly available at https://source.coop/major-tom/elliot-pretrain.

---

### Minimax rates for pointwise CATE estimation: the role of design smoothness

Authors: Yuxuan Hou, Zhenghan Li
Published: 2026-10-13
Categories: math.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.18623v1

We study the role of design smoothness in the minimax estimation of conditional average treatment effects at a fixed covariate point. For design densities bounded above and away from zero, without further regularity, we derive upper and lower risk bounds with an arbitrarily small gap in the convergence-rate exponent. Under uniform design, we obtain matching upper and lower bounds at interior points in the regime of low nuisance smoothness. These results show that rough covariate designs can lead to slower rates than uniform designs, even under the same smoothness assumptions on the treatment effect and nuisance functions, highlighting the role of the covariate distribution in pointwise causal estimation.

---

### Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast

Authors: Jiajing Hu, Xu Han, Li-Ping Liu
Published: 2026-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.18621v1

Accurate uncertainty quantification is critical for many time series forecasting applications, and recent studies have increasingly adopted generative models to capture predictive uncertainty. Existing approaches often combine deterministic forecasting with generative modeling to improve predictive performance. However, their joint training is typically unstable because the deterministic model is embedded within the generative process, resulting in deep computational graphs and changing the probability transport path. In this work, we propose DV-Flow, a unified flow-matching formulation that incorporates the deterministic predictor as a parallel velocity component rather than as the endpoint of the transport path. This design enables stable end-to-end optimization while subsuming several existing formulations as special cases, allowing direct comparisons among them. Extensive experiments on six real-world datasets demonstrate that DV-Flow consistently improves probabilistic forecasting performance over strong baselines. Our code is available at https://github.com/tufts-ml/dv-flow-time-series.

---

### Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference

Authors: St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark Solms, Jonathan P. Shock
Published: 2026-10-13
Categories: cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2610.18617v1

An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of information about that need or by increasing its preference for outcomes that relieve it. We compare these two interventions, separately and together, in a foraging gridworld with three lethal needs, and ask how each changes survival, perception and the body model the agent learns. Precision sharpens interoceptive posteriors and improves survival. Preference reweighting keeps bodily states further from their lethal boundaries and changes the states from which the agent learns, so its learned model covers fewer need levels, with lower quality across all levels but slightly higher quality on the levels it visits. An experiment on 72 further layouts does not establish the predicted preference benefit on difficult layouts, but both interventions improve average survival there and their interaction is positive. Survival alone therefore gives an incomplete account of how a model prioritises needs and learns about its body.

---

### Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve

Authors: Yuyang Bai, Yu Wang, Yu Zhang
Published: 2026-10-13
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2610.18616v2

Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidence agents can access, even when they write code to combine tool calls or process retrieved subgraphs. We propose direct knowledge graph interaction (DKGI), a harness in which language model agents create graph access tools directly over complete node and edge files. The agent writes Python code to follow relations, combine node sets, and select textual evidence, interleaving execution with shell search and file inspection. This lets agents process large node sets in bulk while returning selected text for the model to assess. Execution feedback guides tool creation and revision, while the evolving tools determine what evidence the agent gathers next. On benchmark datasets spanning three domains, training-free DKGI exceeds the strongest published baseline by at least 6.7 Hit@1 points on every graph, even with a minimal harness. Controlled ablations show the benefits of multi-turn programming over shell-only access and predefined graph tools, while trajectories show agents revising code to extend searches or address errors. These findings highlight the value of allowing tool creation and tool use to co-evolve during graph search. Our code and data are available at https://github.com/leopoldwhite/DKGI.

---

### VideoJev: System One Model for Video Understanding and Interaction

Authors: Yuhan Zhu, Xiangyu Zeng, Qingyi Si, Chenxu Yang, Yifei Li, Luozheng Qin, Junhao Zhou, Dingyu Yao, Jun Zhang, Chuanyu Qin, Zhiqiu Zhang, Yuandong Yang et al.
Published: 2026-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.18615v1

Visual agents must turn video observations into timely decisions to track progress and choose what to do next. Building on the emerging System One paradigm, we introduce VideoJev, a family of models that cast video understanding and interaction as structured decision tasks. We adapt pretrained multimodal large language models (MLLMs) by replacing autoregressive answer decoding with a shared head that scores temporal intervals and textual options against video evidence. These scores yield event spans or answer choices, unifying temporal grounding and multiple-choice video question answering. This combines the semantic flexibility of MLLMs with efficient decisions that agents can use directly. As an interaction unfolds, new goals and intermediate results prompt further queries about the same visual history. VideoJev therefore reuses visual computation through Cached inference for queries as they arrive and Joint inference for multiple queries in a single forward pass. Across three temporal grounding benchmarks, VideoJev-4B and VideoJev-35B-A3B improve mean mIoU over their backbones by 6.7 and 10.8 points, respectively, with measured inference speedups of $2.8$-$3.1\times$. On four video QA benchmarks, both achieve performance comparable to their backbones in Thinking mode, with measured inference speedups exceeding $100\times$. These results offer a unified, reusable decision interface for composing structured visual judgments into complex, open-ended workflows.

---

### Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents

Authors: Ashutosh Hathidara
Published: 2026-10-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.18614v1

Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human. That decision needs a per-step confidence signal predicting whether the current rollout will eventually succeed. The agent's own self-reported verbalized confidence is the natural candidate, but existing reinforcement learning methods calibrate it against the correctness of a decision at the current step. We propose a method to calibrate it against the eventual outcome of a multi-step episode: under GRPO, the group of rollouts for a task supplies success labels, and a proper scoring rule scores each step's confidence against the realized outcome. In offline RL on recorded trajectories of a Qwen2.5-7B agent in ALFWorld, TextWorld, and WebShop environments, the AUROC of step confidence against episode outcome rises from near chance to 0.68-0.85, and the top-10% of steps the agent is most confident about succeed ~4.3x more often than average. In online RL on the live ALFWorld agent, four calibration rewards improve early-step AUROC, expected calibration error goes from 0.42 to below 0.12, and selective execution improves over both the untrained agent and a format-only RL control, without degrading task success. We also introduce an evaluation protocol that separates episode depth, task difficulty, and attempt-level foresight, which shows where the gain lies: the trained agent recognizes from its first step which tasks it will fail, while telling a succeeding attempt from a failing one at the same task is harder, with some early-window signal emerging on TextWorld.

---

### Does self-distillation improve reasoning?

Authors: Jason Ken Adhinarta, Raina Wu, Ashutosh Sharma, Avinash Balakrishnan, Rameswar Panda, Polina Golland, Yoon Kim, Zhang-Wei Hong
Published: 2026-10-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.18613v1

Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct answers or environmental feedback. Recent methods have reported better sample efficiency and generalization than reinforcement learning (RL), but it remains unclear whether these gains extend beyond in-distribution evaluations and whether they stem from privileged distillation. In this paper, we revisit two representative methods, Self-Distillation Policy Optimization (SDPO) and On-Policy Self-Distillation (OPSD), across code, science, tool use, and math reasoning tasks. We find that their reported gains do not consistently generalize to unseen problems and are largely explained by overfitting or transferring existing reasoning behavior, rather than effectively using privileged information. Moreover, self-distillation gradients show weak alignment with policy gradients that directly optimize expected reward, questioning whether they provide an effective direction for policy improvement. Our experiments across Qwen3 models (1.7B-14B) and OLMo-3-7B suggest that effectively leveraging privileged information to improve reasoning remains an open challenge. Our code is available at https://github.com/sleepypandu/does-sd-improve-reasoning

---

### Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications

Authors: Yang Luo, Tiantian Ji, Zifeng Kang, Yucheng Wang, Yong Liu, Zhiyi Yin, Xinran Liu
Published: 2026-10-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.18612v1

System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution. However, this paradigm introduces a new security risk, which we term Jev Program Decision Hijacking (JPDH): attacker-controlled contexts can redirect program decisions through schema-valid Jev judgments. Existing evaluations focus primarily on model-level attacks or predefined injection channels, leaving attack reachability and downstream security consequences in real-world Jev applications underexplored. In this paper, we present JevProbe, the first automated framework to evaluate JPDH by tracing adversarial influence from reachable context surfaces through program-consumed decisions to downstream security consequences in real-world Jev applications. Our key insight is that application logic maps diverse Jev judgments to observable decisions, enabling systematic, program-grounded attack evaluation. Across 228 popular real-world Jev applications and 2,273 test cases, 81.5% exhibit decision flips, of which 98.6% lead to potential downstream security impacts. Compared with the strongest adapted baseline, JevProbe improves macro-average Decision Flip Rate (DFR) by 50.4 percentage points, while existing defenses offer limited protection. We further construct JevProbeBench to support systematic evaluation of JPDH in real-world Jev applications. We have responsibly disclosed our findings to Jev application maintainers, pending their responses. The source code of JevProbe and the JevProbeBench dataset are publicly available on GitHub (https://github.com/xiaoxiaohg8d/JevProbe-).

---

### Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning

Authors: Huaiwen Pang, Jiale Han, Junying Chen, Wenjun Xiao, Benyou Wang
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.18611v1

Legal question answering requires answers that are not only plausible, but also grounded in legally valid and citable evidence. Standard retrieval-augmented generation often relies on one-shot semantic matching, which is insufficient when legal evidence must be selected according to authority, applicability, and diversity across heterogeneous sources. We introduce Legal-R1, an agentic retrieval framework for evidence-based legal reasoning. Legal-R1 decomposes legal reasoning into a multi-agent workflow, where a Lawyer agent learns when to retrieve, which legal source to query, what evidence to seek, and when the collected evidence is sufficient. A Legal Assistant agent retrieves from normative legal sources and precedent cases with authority-aware and diversity-aware selection, while a Judge agent generates the final answer from the complete evidence trajectory. We post-train only the Lawyer agent with masked supervised fine-tuning and trajectory-aware reinforcement learning. Experiments on multiple Chinese legal benchmarks show that Legal-R1 improves over general-purpose, legal-specific, and retrieval-augmented baselines.

---

### Jev-ToM: Evaluating Theory of Mind in Typed Decision Models

Authors: Kawai Chung, Chunkit Chan, Yuxuan Liu, Yauwai Yim, Xi Yang, Wenbin Hu, Huihao Jing, Chiu Yeung Tang, Changxuan Fan, Ki Sen Hung, Tsun On Kwok, Haoran Li
Published: 2026-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.18610v1

Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends. Typed decision models offer a potential alternative to generative large language models for bounded Theory of Mind (ToM) selection. We present Jev-ToM, comparing five typed decision models and seven generative baselines on 11,117 English text questions from nine ToM benchmarks across six capability groups. TypeSafe Jev reaches 73.2% source-balanced accuracy including native controls and ranks first or second across all six capabilities, leading beliefs, goals/desires/intentions, and emotions. Other typed models show distinct strengths across tasks. Separate resource comparisons suggest that Jev could reduce the cost and waiting time of repeated ToM selection. Confidence-based selection remains benchmark-dependent, and supplied reasons can repair errors or overturn correct answers depending on their attachment. Candidate expansion reveals distinct selection and output-validity problems. Related-question cues account for most of Jev's downstream gains, with task-dependent effects from predicted states. The findings motivate testing Jev as a ToM selection component in assistants, with task-specific confidence calibration, candidate design, and output validation as integration priorities.

---

### DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization

Authors: Chengtao Jian, Kai Yang
Published: 2026-10-13
Categories: cs.CR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.18609v1

Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal preference data remains largely unexplored. Existing preference poisoning attacks either corrupt explicit supervision signals or require visible triggers, making them detectable under human inspection. We introduce DPOison-VL, the first clean preference poisoning attack against VLM-DPO, which manipulates model alignment solely through imperceptible perturbations on a small fraction of training images, while leaving all prompts, responses, and preference annotations semantically intact. We formulate poison construction as a bilevel optimization and derive a gradient alignment surrogate that efficiently steers image perturbations toward the attacker-specified preference. We further introduce a preference displacement score for principled poison selection with provable first-order optimality under a fixed poison budget, and derive a sufficient condition for preference inversion. Extensive experiments across diverse attack tasks, different VLM architectures and scales, and baseline comparisons demonstrate that DPOison-VL achieves up to 98\% ASR with only 2\% poisoned data and exhibits cross-model transferability, while largely preserving clean accuracy and general utility. Our findings reveal a critical vulnerability in VLM-DPO, where imperceptible image perturbations in preference training data can silently redirect alignment.

---

### Recasting DiT for Extreme Image Compression with Hierarchical Visual Priors

Authors: Yunuo Chen, Jingnan Gao, Bing He, Jinjing Zhao, Chuqin Zhou, Xiaoyue Ling, Li Song, Guo Lu, Wenjun Zhang
Published: 2026-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.18607v1

Pretrained diffusion models provide powerful generative priors for extreme image compression, but their stochastic, iterative generation processes are not designed to decode compressed representations directly. We present PrismCodec, which recasts a pretrained Diffusion Transformer (DiT) as a bitstream-grounded one-step generative decoder. PrismCodec uses the decoded representation in two complementary roles: a projected codec state defines the starting state for generation, while hierarchical visual priors derived from the same decoded latent provide semantic and structural guidance. To bridge the gap between stochastic, iterative generation and deterministic one-step decoding, we develop a progressive adaptation strategy. We first learn codec-conditioned transport from a noisy neighborhood centered on the codec state, distill it into a one-step mapping, and finally anneal the source perturbation to zero during end-to-end optimization. The resulting decoder reconstructs deterministically from the received representation without additional conditioning bits. Across Kodak, CLIC, and DIV2K, PrismCodec consistently improves rate-perception performance over prior generative codecs, achieving BD-rate reductions of 70-75% in LPIPS and 75-81% in DISTS over StableCodec. Code will be released upon acceptance.

---

### Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces

Authors: Haotian Liu, Yingjian Chen, Xiaohang Xu, Lang Huang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
Published: 2026-10-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.18606v1

Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Self-consistency (SC) improves reasoning by voting over sampled final answers, but its vote leaves intermediate disagreements unresolved. To address this problem, we introduce DDRG (Disagreement-Driven Verification Guided by Reasoning Graphs), a framework for selective correction from a frozen bank of reasoning traces. Our insight is that graph alignment can expose claim-level disagreements and provide correction evidence without expanding the sampled trace bank. DDRG builds source-grounded claim graphs and sends localized conflicts to an answer-blind verifier. A verifier-supported refutation that reaches the majority answer's supporting path triggers one focused repair; otherwise, DDRG returns the exact SC vote. Experimental results across five benchmarks show that native zero-shot DDRG improves macro-average accuracy over direct answering by 8.65 and 15.83 percentage points for Qwen2.5-7B and Llama3.1-8B. It also exceeds CoT, the evaluated GoT and GoV question-answering adaptations, and SC on this macro metric. DDRG links local verification to selective correction without enlarging the initial candidate bank.

---

### From Hindsight to Foresight: Dissecting Clinical Evidence Acquisition in Large Language Models

Authors: Ziyang Ling
Published: 2026-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.18605v1

Large language models (LLMs) often diagnose full sight, static clinical cases well yet struggle in foresight, dynamic diagnosis. Prior work has improved this limitation by quantifying the information models acquire and by developing stronger follow-up strategies to improve diagnostic accuracy. In contrast, we introduce a distinctive hindsight to systematically dissect why LLMs fail to acquire diagnostically critical evidence, tracing the failure from evidence identification, utilization and downstream diagnostic updating through not only diagnostic accuracy, but also evidence coverage, trajectory dynamics, and elicited probability and information entropy. Starting experiments from the breakdown at the level of capabilities, to the diagnosis of the pre-event state before the evidence arrives, and to the post-event state transition after the evidence arrives, our research has revealed the profound limitations and internal causes existing in the dynamic diagnostic process. At the same time, we have also conducted sufficient verification and generalization experiments to prove that these limitations are widespread. Together, these findings shift the central challenge from whether LLMs possess relevant clinical knowledge to whether they can identify, acquire, and effectively use the right evidence under clinical diagnosis and conduct a more detailed mechanism analysis to identify the exact location of the capability gap.

---

### LLM2R: From Large Language Models to 3D Reassemblers

Authors: Zhouhan Zhong, Qiuhong Shen, Xingyi Yang, Jinyi Xu, Xinchao Wang
Published: 2026-10-13
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2610.18604v1

3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part. Because the placement of a part is rarely determined by its own geometry, the task demands reasoning over the entire part set, and existing methods, which rely on pairwise relations or iterative generation and verification, scale poorly to objects with many parts. We present LLM2R, which casts part assembly as sequence modeling with a pretrained decoder-only large language model (LLM): a Point-BERT encoder and a Q-Former compress each part into a block of geometric tokens, the blocks of all parts are concatenated, and a causal LLM adapted with Low-Rank Adaptation (LoRA) processes the sequence in one forward pass. Causal attention, however, lets the hidden states of a part observe only the parts that precede it. LLM2R therefore appends a block of learnable summary tokens after the last part: these tokens follow every part, so their states aggregate the whole assembly at a constant token cost, and a part-aware pose head fuses each part's states with them before predicting its rotation and translation. One architecture thus handles semantic and geometric assembly and predicts all poses in a single non-autoregressive pass. LLM2R achieves the highest part accuracy and success rate on all three PartNet categories, the best rotation error, translation error, and part accuracy on PartNeXt, and the lowest translation error and fastest inference on Breaking Bad, where only a fracture-specialized method is more accurate. Its advantage grows with the number of parts: at 100 parts it exceeds GARF by 33.5 points in part accuracy on Breaking Bad and Assembler by 29.1 points on PartNet, and it transfers zero-shot to unseen categories with more than 16 points higher part accuracy than the strongest of three baselines.

---

### AgentStripes: An Evidence-Graded Maturity Model for AI Agents

Authors: Nutan Kumar Naik, Vijay Prasad Poudel, Aditya Kumar Saroj, Saurav Samantray, Abhishek Patel
Published: 2026-10-13
Categories: cs.AI, cs.CY, eess.SY
arXiv: https://arxiv.org/abs/2610.18603v1

Benchmarks report what an Artificial Intelligence (AI) agent can do on a task suite, but not whether one released version has been engineered with the controls that make it reliable, safe and observable, or how strongly that is shown. This paper proposes AgentStripes, an evidence-graded maturity model for AI agents. It defines levels (0 to 7 stripes), process areas (12 areas holding 40 capabilities), three gates (basic, safety, proof) that hold an agent at a level however high its score, and evidence grades E0 to E5. Each applicable capability receives a rating from 0 to 3 and a separate evidence level; these are combined into a credit, aggregated into a severity-weighted score and converted into stripes that the gates limit. Instruments gather evidence, language-model judges interpret it under explicit criteria, and the arithmetic is deterministic. The model is compared with standards at topic level without a claim of conformance, and an unexecuted validation protocol is specified. An empirical evaluation (exploratory, non-confirmatory) of 30 public Python agent repositories, with static evidence only, is a demonstration and not a validation: static evidence caps every final stripe at 2, 26 repositories end at one stripe and 4 at two, and this distinction is unreliable, since re-judging changed the final stripe of 4 of 22 repositories (engine, dossier and panel changed), whereas none of 8 panel-only repeats, all at stripe 1, changed. The parameters are expert conventions without outcome based calibration, and the stripes have not been shown to predict reliability or safety.

---

### Auditing Future-Memory Use in Point-in-Time Language Agents

Authors: Rongtian Ye
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.18602v1

Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access predicts evidence gathering in 48 historical company-comparison tasks. Independent closed-book revenue probes identify the better-remembered company for each model on tasks with unequal recall, fixing the predicted direction before agent runs. We then compare paired runs with real or anonymized company identities while keeping external evidence PIT-valid. Both Qwen and DeepSeek recalled future facts, but neither supported the prespecified shift toward the better-remembered company. Qwen's four allocation estimates on 28 unequal-recall tasks were negative, with descriptive intervals spanning zero. A prospective DeepSeek replication showed an inverse pattern across all four metrics on 20 such tasks, with intervals below zero. These estimates remained negative after each company, pair, and future-fact omission, and all four post-hoc max-T-adjusted sign-flip p-values were below .05. In a prospectively specified follow-up, explicit future facts produced small estimated shifts away from the supplied-fact company, with intervals spanning zero, while final choices shifted toward it. The mechanism behind the natural inverse pattern remains unresolved. These findings support separate assessments of memory accessibility, search allocation, and final outputs alongside cutoff checks on external evidence.

---

### Rethinking Projector Training in Multimodal LLMs

Authors: Fabian Gröger, Naël Ouerghemi, Shuo Wen, Maria Brbić
Published: 2026-10-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.18598v1

Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, followed by joint training of the full multimodal model. Despite its widespread use, the role of the projector training stage remains poorly understood. We find that (i) using only $10$ to $20\%$ of the data for training the projector already recovers most downstream performance gains, and (ii) projectors trained on different datasets can be linearly interpolated while largely preserving performance. These results suggest that projector training mainly performs a coarse alignment, which many different projectors achieve equally well. Motivated by these findings, we propose PORTAL, a training-free projector initialization that requires neither paired image-caption data nor gradient-based optimization, but only per-modality summary statistics. PORTAL computes an optimal-transport-based map between Gaussian approximations of the vision and language feature distributions on a shared principal subspace, so that the projector training stage can be skipped entirely. Without any paired data, PORTAL matches the standard pipeline trained on 558k image-caption pairs across six LLM backbones, two vision encoders, and 16 benchmarks. It outperforms that pipeline in $3$ of $7$ (vision encoder, LLM) settings and reaches an average $98\%$ of its score across the other four.

---

### PhysicsSliders: Learning Physical Controls for Audio Foley Generation

Authors: Peiwei Chang, Yongqiang Chen, Yuelan Cheng, Liting Gao, Yishun Lu, Li Zhang, Mark D. Plumbley, Philip J. B. Jackson, Wenwu Wang
Published: 2026-10-13
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.18597v1

Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictably to these controls, both individually and in combination. We present \method\ (PXS), trained on simulated contact sounds with 15 material, geometry and contact parameters. Two separately trained variants accept direct parameter inputs or numerical captions. PXS controls hardness, size, speed and damping, supports room descriptions and produces spectrally distinct outputs at fixed targets. When controlling damping and size together, specifying thickness improves frequency accuracy and joint target delivery. Measurements from real recordings define effective-damping targets, which simulator inversion maps to generation inputs without real-audio fine-tuning. Across 18 impact classes from five real-audio datasets, PXS-Physical follows these targets with mean grouped Spearman correlation $ρ=0.976$ and class-median error 0.094 dex (a factor of 1.24).

---

### ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models

Authors: Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo
Published: 2026-10-13
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.18596v1

Reinforcement learning (RL) post-training improves robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more: learning new tasks efficiently while retaining previously acquired behaviors. Existing continual RL methods on top of VLAs mitigate forgetting but rely on on-policy updates with limited forward transfer, whereas off-policy methods improve single-task sample efficiency without addressing learner persistence across tasks. We propose ACCRUE, a continual off-policy RL framework that carries lightweight actor and critic networks across tasks, allowing each stage to reuse behavioral and value knowledge acquired through prior RL. The inherited critic adapts only on current-task transitions and guides current-task actor learning, while prior behavior is preserved by distilling the actor toward cached targets on a small number of retained episodes. Fixed visual features keep the inherited learner and its replay compatible with base-policy updates. Across contact-rich assembly sequences in simulation and on real-robot hardware, ACCRUE accelerates subsequent-task learning with near-zero forgetting and significantly reduces real-robot training time by 31.0\% to 68.5\%.

---

### Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence

Authors: Tobias Hürten, Johannes F. Loevenich, Florian Spelter, Erik Adler, Laurin Holz, Maxime Schwarzer, Thies Moehlenhof, Roberto Rigolin F. Lopes
Published: 2026-10-13
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2610.18594v1

This paper proposes an Autonomous Cyber Operations (ACO) gym, a unified framework integrating high-fidelity network emulation, realistic user behaviour modelling for benign network traffic and adversarial profiles, and the generation of cybersecurity scenarios through open toolkits. By supporting live and deferred feature extraction at the packet and flow levels, the gym facilitates the creation of labelled synthetic datasets for training Deep Neural Network (DNN)-based Intrusion Detection Systems (IDSs), as well as developing and evaluating modular components for autonomous defence agents through emulated interactions. While evaluation of a DNN classifier within the gym shows high in-domain performance, achieving near-perfect recall on adversarial network flows, our experiments reveal a significant sensitivity to domain shift, showing that even minor changes in network composition, such as variations in traffic protocol distribution, can lead to a catastrophic collapse in model transferability and detection performance.

---

### Fairness under Prediction Error in Predict-then-Optimize Pipelines

Authors: Hilda Adwubi Osei
Published: 2026-10-13
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2610.18593v1

Fairness constraints in predict-then-optimize pipelines are necessarily enforced on predicted outcomes $\hat{y}$, since true outcomes $y$ are unobserved at decision time. We study whether a demographic parity constraint enforced this way continues to hold against $y$, and how the resulting violation scales with prediction error. Using a budget-constrained allocation problem solved as a linear program, we show empirically that the true-outcome fairness gap grows with prediction error $σ$ and saturates, well fit by $c(1 - e^{-σ/τ})$ with $c = 0.1545 \pm 0.0103$ and $τ= 3.9045 \pm 0.3745$; its mean is invariant to sample size while its variance decays at the standard $O(1/\sqrt{n})$ rate. We derive a two-part theoretical bound: a closed-form local sensitivity result showing the gap's first-order response to prediction error depends on only two individuals per group, validated against the solver to within three significant figures; and a universal, error-independent ceiling following from the boundedness of the decision variable, confirmed consistent with but looser than the empirical saturation level. On US Census income data, enforcing demographic parity on a trained predictor's output reduces an unconstrained disparity in true income to roughly one-third of its original size, leaving 34.4% $\pm$ 3.3% (California) and 35.7% $\pm$ 1.8% (Texas) of the disparity intact and undetectable from the predictions alone -- consistent not only in mechanism but in approximate magnitude across two states with different demographics and income distributions, and stable across ten independent train/test splits in each. A fairness constraint that appears fully satisfied at decision time can mask a substantial, systematic violation of the outcome it was meant to protect.

---

### Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages

Authors: Irem Ecem Yelkanat, Faeze Ghorbanpour, Alexander Fraser
Published: 2026-10-13
Categories: cs.CL, cs.CY, cs.MM
arXiv: https://arxiv.org/abs/2610.18588v1

Annotator disagreement is increasingly recognized as a meaningful property of subjective tasks, rather than merely noise to be removed. Predicting which items are likely to be contested could help allocate annotation effort and route difficult cases to human review. We propose predicting disagreement from interpretable semantic properties of the text. An LLM answers a set of binary questions covering harmful-content characteristics, disagreement-related cues such as borderline severity and missing context, and language-sensitive cues such as local slurs. A classifier predicts disagreement from these answers, and we analyze which questions contribute most to the predictions. Across four datasets in English, German, and Turkish and three open-weight LLMs, our structured question features outperform direct prompting by 10.5 ROC-AUC points and the strongest text-based baselines by 5.0 points. A compact subset of eight questions performs within 1.5 ROC-AUC points of the full twenty-question set. In leave-one-dataset-out evaluation, models retain roughly 90-95% of their in-domain ROC-AUC. Across models and datasets, questions about derogation, missing context, and decision boundaries serve as the strongest predictors, suggesting that what makes harmful content contested is partly observable in the text.

---

### GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition

Authors: Ting Zhu, Huizhi Liang, Boguslaw Obara, Shufei Duan, Varun Ojha
Published: 2026-10-13
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2610.18587v1

Multimodal Emotion Recognition (MER) aims to understand human emotions by integrating information from multiple modalities such as speech and text. Psychological studies suggest that emotions exhibit latent hierarchical structured relationships in their semantic representations. However, most MER approaches rely on Euclidean representations, which capture fine-grained cross-modal interactions but do not explicitly provide a geometric prior for organizing hierarchical emotional structures. To mitigate this gap, we propose GeoMER, a joint Euclidean-Hyperbolic modeling framework that introduces hyperbolic emotion-core routing to capture higher-level, abstract emotional representations for MER. The proposed framework jointly models token-level cross-modal semantic interactions and latent emotion representations in two complementary geometric spaces. Specifically, GeoMER consists of a Euclidean Multimodal Fusion Module (EuclFusion) for multimodal representation fusion and a Hyperbolic Geometric Core Routing (HypGeoRoute) module that performs geometry-aware core assignment and aggregation in a hyperbolic manifold to capture more abstract feature representations. The HypGeoRoute module complements the Euclidean token-level modeling. We experiment on the IEMOCAP multimodal MER benchmark and demonstrate that the proposed method achieves the best performance, with 83.54% weighted accuracy and 83.35% unweighted accuracy, outperforming Euclidean baselines, including MemoCMT.

---

### Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling

Authors: Cong Hua, Qianqian Xu, Zitai Wang, Zhiyong Yang, Shilong Bao, Linchao Zhang, Qingming Huang
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.18583v1

Sampling-based test-time scaling enhances LLM reasoning by aggregating multiple reasoning paths for the same query. Existing methods use answer frequencies or path confidence to compute candidate scores, which do not explicitly characterize comparisons between competing answers. Inspired by the Condorcet principle in social choice theory, we introduce pairwise confidence comparisons between paths supporting different answers to capture answer-level comparative advantage. We combine this comparative evidence with voting support through a KL-regularized objective. Theoretically, we show that this comparative-advantage is equivalent to the adjustment to the traditional voting logits. In this way, our proposed Pairwise-Guided Logit Adjustment (PGLA) framework allows comparative evidence to compensate for weaker voting support and correct voting-based ranking errors. Experiments on 10 challenging benchmarks including mathematical reasoning, knowledge reasoning, and code generation with 7 models ranging from 1.7B to 32B parameters speak to the effectiveness of this plug-and-play term. Additional evaluations with external reward scores and online sampling further demonstrate its applicability.

---

### Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops

Authors: Yubo Li, Ramayya Krishnan, Rema Padman
Published: 2026-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.18579v1

System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they choose wrongly there is nothing to inspect: did the model misread what the agent has seen, or read it correctly and still act wrongly? We answer behaviorally. On a frozen benchmark of agent decision states from simulated environments, customer-service policies, tool use, web navigation and coding, we pair every next-action question with factual probes about the same state, each answered independently. Across seventeen fast systems and a reasoning model, the answer is consistent: most wrong actions follow correct reading, and the more accurate a system, the more of its errors take this form. These errors are not noise; they gather on the same states across systems of every kind. Where the probed facts provably determine the action, models that read every fact still fail to combine them, and their own answers, composed by code, repair the failure. On real states, what is missing is often not a fact but the next sub-goal.

---

### When More Objectives Make Identification Easier: The Role of Preferences and Feedback

Authors: Bo Xue, Ji Cheng, Yuanyu Wan, Shuang Qiu
Published: 2026-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.18577v1

Best-arm identification (BAI) aims to identify the optimal arm using as few samples as possible. While most existing work focuses on a single objective, many real-world applications involve multiple criteria, which motivates the study of BAI in multi-objective bandits. Intuitively, multi-objective identification seems harder, since the learner must identify optimal arms in a higher-dimensional reward space; however, the additional objectives also provide richer feedback that can reduce the required exploration. In this paper, we characterize when and why multiple objectives can make BAI easier. For Gaussian bandits, we establish a characteristic-time lower bound for fixed-confidence identification that holds uniformly across preference orders. Through explicit comparisons under Pareto, linear, and lexicographic preferences, we reveal three phenomena: (i) identifying a larger optimal set can require fewer samples than identifying a unique optimum; (ii) the advantage of vector feedback over coordinate feedback depends fundamentally on the preference order; and (iii) multi-objective identification can require fewer samples than even the easiest corresponding single-objective problem. Finally, we propose Order-Aware Track-and-Stop (OATS), an algorithm that is correct at any prescribed confidence level and asymptotically matches the lower bound.

---