跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 04:05 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 04:37 — 2026-11-09 04:37（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 04:05最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 04:03（北京时间）
版本更新 · v2arXiv:2609.38850

Beyond Outcome Rewards: Post-Rationale Distribution Optimization for Selective Prediction in Reasoning Models

Zhimin Gao, Meibo Hu, Jiamian Wang, Zhiqiang Tao, Pichao Wang

原文摘要

Reasoning models are trained to produce correct answers, yet selective deployment requires ranking which answers to accept or defer, and outcome-reward training does not directly optimize the post-rationale distribution used for that decision. We identify two mismatches: expected correctness is mode-seeking rather than distribution-eliciting, and scoring an average across rationales rewards disagreement unavailable to a single-rationale decision. We introduce Post-Rationale Distribution Optimization (PRDO), which applies a proper score to the answer distribution after each sampled rationale, without target rationales or separate confidence labels. Across four 0.6--3.8-billion-parameter models on MMLU-Pro, PRDO improves Brier score, error ranking and secondary accuracy relative to budget-matched, temperature-scaled GRPO. At 20\% realized error, oracle coverage rises by \npj{Q3a_vs_grpo.qwen3-0.6b.mp.oracle_cov@0.2.ppabs}--\npj{Q3a_vs_grpo.phi-4-mini.mp.oracle_cov@0.2.ppabs} percentage points, and ranking gains transfer to unseen tasks. Matched controls identify proper, per-rationale scoring as the active design choices, while verification tasks show the boundary: better selective ranking can coexist with lower full-coverage accuracy. Code is available at https://github.com/ZimmyGao/openjev-rlcd

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02125

Semantic Interoperability in Federated Digital Twin Systems: A Systematic Review Through the Levels of Conceptual Interoperability Model

Manonmani Sekar, Nasim Nezamoddini

原文摘要

When two companies connect their digital twins, software models of their plants kept up to date with live data, each twin must translate the other's data into its own terms, and that translation rule, called a mapping, can stop being correct when one company changes the meaning of its data without telling the other. This PRISMA 2020 systematic review screened 5,833 records and read 119 full texts to determine whether any published system detects such a broken mapping and repairs it while the twins operate. In all 32 included studies the mapping is fixed before operation, and the two ingredients of run-time repair appear only separately: cross-company matching without any check that the match still holds, and detection and repair of changed meaning within a single company. The review turns this gap into six requirements, each illustrated on one running example, that a system claiming run-time semantic interoperability between independently owned twins should meet.

cs.SE · cs.AI · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.17439

InTAct: Interval-based Task Activation Consolidation for Continual Learning

Patryk Krukowski, Jan Miksa, Piotr Helm, Jacek Tabor, Paweł Wawrzyński, Przemysław Spurek

原文摘要

Continual learning seeks to acquire new knowledge while preserving previously learned representations. Despite the success of prompt-based methods, they remain fragile in domain-incremental learning scenarios, where shifts in the input distribution cause representation drift in shared layers and lead to forgetting. We introduce InTAct, a method that preserves functional behavior in shared representations without freezing parameters or retaining past data. InTAct constrains updates within activation regions associated with prior domains, while allowing flexible adaptation elsewhere, thereby stabilizing neuron functionality rather than directly restricting parameter values. The approach is architecture-agnostic, integrates seamlessly with existing prompt-based frameworks, and matches or outperforms state-of-the-art methods on domain-incremental benchmarks.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02107

ZT-DAC: ML-Driven Dynamic Access Control Policy for Zero Trust in DER Networks

Arun B. Chandrasekaran, Damilola Popoola, Souradeep Bhattacharya, Manimaran Govindarasu

原文摘要

The increasing penetration of Distributed Energy Resources (DERs) in the smart grid has significantly expanded the cyber-attack surface. Traditionally, DER networks rely on static role-based access control (RBAC) mechanisms that assume persistent trust after authentication. This limitation enables adversaries to maintain unauthorized privileges and move laterally across DER systems, disrupting grid operations. Although attribute-based access control (ABAC) enables fine-grained and context-aware access decisions, it does not fully eliminate implicit trust. Zero Trust (ZT) principles can be incorporated to enhance ABAC policies. This paper proposes a dynamic access control framework for implementing ZT in DER networks (ZT-DAC). The proposed solution employs a two-stage verification process and integrates an Open Policy Agent (OPA)-based RBAC with a machine learning (ML)-based ABAC to enforce continuous and adaptive trust score assessment. To support realistic DER operations, a DER-specific access control model is developed and used to generate a domain-informed dataset of access requests incorporating both legitimate and adversarial behaviors. Experimental results on the dataset show that the OPA-based decision layer achieves \(91.92\%\) accuracy, with a False Positive Rate of \(14.45\%\), while the ML model achieves a Mean Absolute Error of \(2.074\) and an \(R^2\) of \(0.891\) in trust-score prediction. The ABAC layer achieves \(93.27\%\) accuracy, with a FPR of \(3.88\%\), validating its practical feasibility within realistic DER environments.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.26350

OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents

Kaicheng Zhang, Wen Ge, Lei Jiang, Weixin Yang, Jordan Langham-Lopez, Jialin Yu, Lukasz Szpruch, Hao Ni

原文摘要

Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tasks, while the financial relevance of benchmark tasks is often overlooked. Yet financial workflows are inherently multi-stage, spanning interdependent tasks such as forecasting, strategy construction, risk management, and trading. Existing platforms typically focus on a single task, and can therefore overstate agent competence and fail to reveal weaknesses in generalization, real-market interaction, and financially meaningful decision-making. We introduce OpenFinGym, a unified gym environment for quantitative-finance agent development that covers forecasting, market generation, real-time trading, and fraud detection under a single execution and verification interface. OpenFinGym additionally provides an automated task-construction pipeline that turns quantitative finance publications into executable task packages; a containerised runtime with a host-side verifier service that supports scalable agent rollouts and prevents runtime train-test leakage; a paper trading engine with a low-latency data-stream design; deferred-resolution support for long-horizon and event-market forecasts; and integration for SFT and RL post-training.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02104

Consolidating Reasoning with Test-Time Training

Haotian Wu, Zeming Chen, Hao Zhao, Antoine Bosselut

原文摘要

Effective multi-agent collaboration requires finalizing solutions from reasoning that is distributed across the individual attempts of many agents. However, useful intermediate reasoning can remain unexploited when collaboration is limited to voting on conclusions reached among individual agents, or aggregating long, noisy collections of reasoning trajectories in context. In this work, we propose TTT-Consolidate, a framework that uses multi-agent reasoning trajectories as adaptation data to improve a model's subsequent reasoning. TTT-Consolidate jointly consolidates trajectories into parametric representations through test-time training, then generates a new solution by conditioning on the consolidated information. We meta-learn how to consolidate using bi-level optimization at training time, where an inner loop encodes reasoning trajectories into a lightweight LoRA adapter, and an outer loop learns meta-parameters for the inner loop such that the consolidation is helpful for the model to synthesize a final solution. As no large-scale corpus of diverse reasoning trajectories exists for training aggregation methods, we construct the OpenParallelThinking corpus composed of 12,810 math problems paired with a mixture of trajectories from six LLMs. Evaluated on challenging math and STEM benchmarks, TTT-Consolidate outperforms the best aggregation baselines by up to 20 percentage points, even under matched compute and runtime settings, with the gap widening at larger model scales. TTT-Consolidate also recovers from unsuccessful individual trajectories more robustly, an ability that improves as the number of available (even incorrect) trajectories increases. Finally, we demonstrate that TTT-Consolidate benefits from both SFT and RL-based outer loop objectives. We will release TTT-Consolidate and OpenParallelThinking for use in future work on reasoning aggregation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02096

EarthJev: Calibrated, Non-Generative Answers to Natural-Language Questions about Sentinel-2 Land Cover

Domenico Benfenati, Antonio Maria Rinaldi, Cristian Tommasino

原文摘要

Vision-language models for remote sensing answer questions about satellite images by generating text: every answer costs a decoding loop, has to be parsed back to an option, and comes without a usable probability. We present EarthJev, a 0.8B-parameter model that answers typed questions about multispectral Sentinel-2 patches without generating any token. All 12 bands enter the vision encoder of Qwen3.5-0.8B through a widened input layer initialised from the RGB kernels, and, following the open OneJev recipe, the answer is read from the logits of the option letters at a single position and trained with cross-entropy plus Brier score. Under a pre-specified analysis plan, we compare it with the same backbone fine-tuned to generate the answer and with three multimodal language models fine-tuned with LoRA, all trained on the same 70,890 questions from 5% of BigEarthNet v2.0 and timed in one job on the same GPU; VQA models that classify over a fixed answer vocabulary are reported as a reference for the cost of answering only the questions seen in training. EarthJev answers a question in 19.9 ms, 4.3 to 8.7 times faster than the multimodal language models and 6.8 times faster than its own backbone used generatively; when all the questions about an image are asked together, it answers them in 42.8 ms, 3.7 to 10.1 times faster than the batched generative models. On 36,028 test questions it reaches 86.0% accuracy (three seeds), 0.6 and 1.2 points below the two 2B multimodal models and 3.5 points below the remote-sensing EarthDial-4B, with answers that are valid by construction and calibrated probabilities (ECE 0.006). Replacing the nine non-RGB bands with their mean costs 4.5 points, so the model uses the multispectral input, and in an ablation training the whole vision encoder raises accuracy to 88.4% at the same cost. Code and model: https://github.com/CosmoIknosLab/EarthJev

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02091

HQNN-CL: Regime-Aware Hybrid Quantum Neural Network with Continual Learning for Financial Forecasting

Muhammad Atif Saeed, Akhtar Jamil, Subhan Ullah

原文摘要

Financial time-series forecasting is still difficult owing to the non-stationary nature of the market, regime changes, and catastrophic forgetting, which makes conventional deep learning models hard to adapt in the long term. To achieve uncertainty-aware robust financial forecasting in the face of changing market conditions, this study proposes a Hybrid Quantum-Classical Neural Network with Continual Learning (HQNN-CL). The proposed framework combines Gaussian Hidden Markov Model (HMM) based regime detection, BiLSTM temporal encoding, adaptive-depth parameterized quantum circuits, Elastic Weight Consolidation (EWC), experience replay, and probabilistic forecasting in a single architecture. The framework was tested on four real-time stock datasets: Microsoft, Systems Limited, Teradata and Tata Consultancy Services, and compared with seven state-of-the-art forecasting models, including recurrent and Transformer-based models. The experimental results show that HQNN-CL has outperformed other methods on the Systems Limited (RMSE = 3.0149) and Teradata (RMSE = 0.8909) datasets and is within 0.32% and 0.40% of the best baseline method for Microsoft and Tata Consultancy Services, respectively. The proposed framework also generates well-calibrated probabilistic forecasts within the range of 89.5% to 96.5% empirical coverage rate, has zero catastrophic forgetting (BWT = 0.0000) for all sequential learning tasks, and consistently shows positive forward transfer. Ablation and statistical significance analyses also validate the performance of adaptive quantum feature learning and continual adaptation under heterogeneous market conditions, regime-wise.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.20258

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Sangwoo Park, Woongyeong Yeo, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek, Seong Joon Oh 等 9 位作者

原文摘要

Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation strategies often degrade underlying task performance. To overcome this privacy-utility trade-off, we propose SELFCI, a complementary self-distillation framework that decouples information suppression from task resolution. SELFCI jointly optimizes two independent reverse KL divergences over distinct teacher distributions derived from feedback: one encourages preserving task-relevant information for utility, while the other enforces minimal and appropriate disclosure. This complementary formulation induces a Product-of-Experts (PoE) target, aligning the policy with the intersection of capability and privacy requirements. Empirical evaluations demonstrate that SELFCI, without relying on costly external supervision, consistently outperforms competitive baselines such as online reinforcement learning algorithms (e.g., GRPO). These trends further extend to out-of-domain settings involving agentic workflows and accumulated private context, suggesting that SELFCI provides a practical path toward CI alignment.

cs.LG · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2609.36279

Proofs Without Nominals: Gödel's Ontological Argument, its Shallow Embedding, and the Open Questions of the Monatshefte Notes

Christoph Benzmüller

原文摘要

The shallow embedding of higher-order modal logic in classical higher-order logic, used in Benzmüller and Scott's Notes on Gödel's and Scott's variants of the ontological argument, reaches beyond the modal object language: its quantifiers range over domains containing the nominals and satisfaction operators of hybrid logic. A proof using one proves a theorem of the embedding, not necessarily of the modal logic. Whether a result is one of the modal logic can be settled by replaying it in an explicit calculus, or, more cheaply and for all results at once, by analysing what the embedding's proofs substitute. Every statement the Notes prove has a proof in the embedding substituting nothing outside the object language, 294 of them explicit. The Notes' own proofs substitute none either; what it flags are terms a prover introduced. A soundness theorem over general models closed under the object language, and a sentence of that language the embedding proves but which fails in such a model, fix what the certificate says. The Notes' three open questions are settled too, without nominals, but by the empty instance of the conjunction axiom, too cheaply to convince. Generalised to Gödel's "any number of summands", the axiom covers the empty conjunction and the singleton. This article restricts it to at least two different conjuncts, a non-degenerate reading of Gödel's footnote, and settles them again without nominals. In effect only the empty conjunction is excluded; the singleton comes back with the other axioms. In one variant the restriction refutes the possible existence of a God-like being; the answers return, with no side condition, once the Notes' non-emptiness clause is confined to Gödel's essence. Every theorem here is verified in Isabelle/HOL and independently in Lean 4, the separating model in its propositional part; the countermodels are Nitpick's, checked by the build.

cs.LO · cs.AI · math.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38960

Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation

Yi Wang, Tianzi Wang, Peter Bell

原文摘要

Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed evidence. Omni-modal agents, which autonomously orchestrate perception tools to actively collect evidence, achieve strong performance, but it remains unclear whether active perception from both audio and visual modalities depends on broad specialized toolsets, especially audio or visual modality-specific tools. Such systems may also introduce long execution trajectories and substantial inference cost. We investigate whether comparable performance can be retained with a compact workflow exposing only essential perceptual capabilities. Starting from the specialized-tool OmniAgent, we conduct staged controlled experiments that prune the toolset and progressively consolidate modality-specific tools into omni-modal tools, motivating a two-tool agent comprising only Omni-modal captioning and Omni-modal QA. Across three widely used AVQA benchmarks, our compact agent achieves comparable or better accuracy than the specialized-tool agent while reducing inference cost by around 70%.

cs.AI · cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.22538

STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control

Mengxi Luo, Changjia Chen, An Cao, Wanyi Dai, Zirong Huang, Shixiong Gao, Ruoqi Shu, John Chen 等 9 位作者

原文摘要

Enterprise agents are expected to deliver correct and consistent outcomes while executing complex procedures, adhering to governing policies, and operating within practical resource budgets. We present \textsc{Stage}, an integrated execution framework combining typed task nodes, shared execution memory, document tools, and deterministic orchestration. We evaluate \textsc{Stage} on SOP-Bench Referral Abuse, the Retail and Telecom domains of $τ^2$-bench, and two proprietary banking workflows, Smart Dispute and Paystub Fraud Detection. Using the same underlying model in each comparison, \textsc{Stage} improves single-run success and repeated-run reliability over the baseline in all 18 benchmark--model pairs. Success across all three runs (\(\mathrm{Pass}^{3}\)) increases by 7.5--66.0 percentage points. Fixed-graph ablations demonstrate the contributions of localized policy context and coordinator-owned routing. Further analysis of Smart Dispute shows improved coverage of required operations across procedure lengths. These findings show that integrating local reasoning, persistent state, and procedural control can improve reliable enterprise workflow completion without changing the underlying model.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02079

ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost

Xingzhi Qian, Sungho Park, Rongyuan Tan, Jianbo Yu, Jue Zhang, Lorenzo Cavallaro, Menglin Xia, Yanzhi Chen 等 16 位作者

原文摘要

Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality. Extending them to joint quality--cost optimization introduces a challenge: applying the deployment preference during intermediate updates can prematurely reject candidates that are valuable for later improvements. We introduce ParetoSaddler, which addresses this mismatch by separating intermediate candidate promotion from final deployment selection. At each iteration, an optimizer updates a parent harness to produce a candidate, and then compares the two over repeated executions and uses Bayesian bootstrap Pareto support to promote candidates showing credible progress in either quality or cost. Promoted candidates receive broader development evaluation and remain available as parents for later optimization steps. We evaluate ParetoSaddler on ClawMark and GAIA2 using domain-disjoint splits. On ClawMark, ParetoSaddler improves quality from 70.86\% to 81.35\% while reducing cost from \$1.17 to \$1.01 per task; on GAIA2, it improves quality from 56.22\% to 62.89\% while reducing cost from \$0.78 to \$0.45 per task. The Pareto-selected harnesses also achieve higher quality at lower cost than quality-only harness optimization. Analysis shows that Pareto-aware optimization retains intermediate candidates that would be discarded by deployment preference but can support later improvements, while Bayesian bootstrap screening filters out candidates whose gains are weakly supported across runs.

cs.AI · cs.CL · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02076

Scene-Adaptive Readout and Decoding in Diffusion Driving VLAs

Seungjun Yu, Jiho Choi, Inha Kang, Hojun Choi, Seungwook Kim, Hyunjung Shim

原文摘要

Diffusion driving vision-language-action models repeatedly execute the backbone at every denoising stage, incurring substantial inference cost, while it remains unclear whether all scenes require the same decoding computation. To distinguish when a trajectory becomes readable from how much further refinement it requires, we analyze trajectory readout across network depth and decoding progress. We identify a depth-decoding dissociation in which late-layer representations already support useful trajectory readout after the first forward sweep, whereas early-layer representations benefit more from continued decoding. We further find that both the preferred readout layer and decoding depth vary across scenes. Based on these observations, we propose a scene-adaptive readout and decoding framework. A scene-conditioned readout MoE adaptively weights and combines trajectory predictions from layer-specific late-layer representations after a single backbone sweep, while an adaptive decoding policy applies additional native refinement only when required by the scene. We evaluate our framework on two diffusion driving VLAs across the Waymo E2E and nuScenes benchmarks. Our method improves validation RFS by up to 0.56 while also improving test performance, and achieves an end-to-end speedup of up to $6.0\times$ on Waymo E2E, while consistently reducing trajectory error on nuScenes. These results demonstrate that scene-level readout and decoding allocation improves planning quality while avoiding unnecessary decoding. Our code is available at https://github.com/sjyu001/SARD

cs.CV · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02075

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

Lang Mo, Xingxuan Zhang, Qi Wang, Mingchao Hao, Hao Yuan, Chunjing Gan, Wang Lu, Peng Cui

原文摘要

Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner. Language models provide semantic representations of current and historical records, while a general-purpose conditional predictor predicts task-defined targets from the represented evidence. Pretraining supplies reusable inference capability; deployment evidence instantiates problem-specific predictions without updating either model's neural parameters. Tool judgments, candidate preferences, and reasoning assessments share an evidence-and-query interface, with predictions mapped to choices by a decision rule. This architecture establishes complementary sources of agent capability: semantic knowledge acquired through language pretraining and empirical inference acquired through structured-data pretraining. A single frozen LimiX-2 predictor serves all five task categories. With Qwen3.5-27B as the semantic encoder, DPDM raises mean accuracy across 50 benchmarks from 78.80% with few-shot prompting to 84.92% under their respective evaluated history budgets, and reaches 82.33% with identical histories and queries. On ToolPRMBench's BFCL and ToolSandbox tasks, absolute accuracy gains are 34.26% and 28.87%, respectively, at the methods' respective evaluated history budgets. Accuracy improves as history grows. With identical imbalanced histories, mean balanced accuracy improves by an absolute 14.51% across five reasoning-step assessment tasks and four encoders. DPDM makes learning from experience an independently improvable foundation-model capability, creating a shared route for advances in conditional prediction to improve decisions across agent tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02074

SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training

Ziming Li, Lu Yu, Jiatan Huang, Qing Cui, Jun Zhou, Chuxu Zhang

原文摘要

Coding agents solve repository issues through long sequences of exploration, editing, and validation. These trajectories are increasingly used as post-training data, so how they are collected shapes what the trained model learns. A common approach is to sample multiple trajectories independently for each issue and then select or curate them. However, as more trajectories are sampled independently, later trajectories become increasingly redundant, even though earlier trajectories could guide where subsequent collection effort should be spent. A natural way to use this history is to expose it to the coding agent as advice. But training on such trajectories can make the model rely on advice that is unavailable at test time, creating a train-test mismatch. Instead, we argue that history should guide where collection effort is spent, while the coding agent decides what to generate. We introduce SWE-Trail, a trajectory collector that uses earlier trajectories to guide subsequent collection while keeping that history outside the coding agent's context. During a new rollout, SWE-Trail uses history to identify a state where additional collection effort may be useful. There, the coding agent proposes candidate next actions from its ordinary context, and SWE-Trail briefly executes them from the same checkpoint to decide which route continues. We evaluate collection approaches by training student models on the trajectories they produce. For a 124B student initialized from Ling-3.0-flash-base, SWE-Trail improves mean resolution over independent sampling by 2.33 and 1.60 percentage points on SWE-bench Multilingual and SWE-bench Pro, respectively. Without history, the same pipeline produces more resolved trajectories than independent sampling, but improves by only 0.11 points on Multilingual. These results show the value of using history to guide collection without exposing it to the coding agent.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02067

State-Aware Virtual Patient Simulation for Training Psychiatrists in Challenging Clinical Scenarios

Harsh Mohta, C Chandrahas Reddy, Sunhith Reddy Bojja, Manik Inder Singh Sethi, Vinesh Gupta, Raghuram Bharadwaj Diddigi

原文摘要

Psychiatrists must be prepared to manage patients exhibiting challenging psychological states, including suicidal ideation, hallucinations, and other high-risk behaviors. However, opportunities to safely practice such interactions are limited. While recent conversational agents can simulate patients, existing approaches largely rely on large language models (LLMs) to determine patient responses, making it difficult to consistently maintain psychological state, adapt to the clinician's responses, and generate clinically plausible challenges that meaningfully test the clinician. We present a state-aware virtual patient simulation pipeline for training psychiatrists in challenging clinical scenarios. The proposed system maintains an evolving patient state throughout the interaction and orchestrates patient behavior rather than leaving response generation entirely to an LLM. At each interaction, a learning-based behavioral strategy selector determines the type and level of challenge appropriate to the current patient and clinician context. The selected strategy, patient state, clinician response, interaction history, and relevant clinical knowledge are then provided as grounded context to an LLM to generate a semantically relevant and psychologically consistent patient response. Following each session, the system analyzes the interaction and provides feedback to the clinician on their communication and management of the virtual patient.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02056

Do Embodied VLMs Actually Use Their Scene-Graph Memory?

Shubh Garg, Divyansh Pandey, Vedant Khandelwal, Niyati Rawal, Amit Sheth

原文摘要

Embodied agents that answer questions about their route need a memory of what they saw, and scene graphs are a natural form for it. A vision-language model (VLM) can receive such a graph as text or through a graph encoder, but accuracy alone cannot show whether the graph holds the episode's facts, reaches the model, or is actually relied on. In this diagnostic study, we introduce a graph-swap test for the last of these: each episode is given another episode's graph, and we count how many answers change. On an embodied question-answering benchmark with routes through two to seven rooms, we use it to compare ways of delivering scene-graph memory to a fine-tuned VLM. As text, the memory is used strongly, adding 30 points on route questions. As a graph, it is not, and we trace why: the encoder preserves the information, but standard pooled and late fusion discard it. Giving each node its own input token recovers part of it, a gain of 8.3 points on route questions that the swap test confirms comes from the graph. The test also exposes a shortcut that accuracy hides: when the same facts appear in the text, the model ignores its graph. The test thus offers a cheap check of whether a VLM uses its scene-graph memory, and our analysis points to how that memory should be delivered.

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03735

HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing

Snehasis Addy, Eduardo Calle Ortiz, Prashant Shenoy, Phuc Nguyen

原文摘要

We present HyVox, a hybrid neuromorphic--von Neumann system for low-energy open-set speaker identification under tight energy budgets. HyVox splits the workload at the speaker embedding. A neuromorphic processor embeds the speech with sparse, event-driven computation, and a von Neumann microcontroller holds the speaker gallery and makes every decision: it scores queries by cosine similarity, rejects unknown speakers, and enrolls new users by writing a prototype, with no weight update. On the neuromorphic processor, a hierarchical temporal abstraction (HTA) SNN backbone learns a synaptic time constant per leaky integrate-and-fire (LIF) neuron, allocating 832 neurons across fast, medium, and slow timescales. A 32-neuron spiking embedding extractor (SEE), pretrained on episodes that each enroll new speakers and reject outsiders, turns the backbone output into an embedding for speakers unseen in training; its 32 spike counts are the only interface between the two processors. To fit the chip's synapse and integer budgets, we compress the backbone 6.5x to 29.0k synapses, train it for integer bit-shift dynamics, and fine-tune it with chip-accurate spiking training (CAST). CAST trains through a differentiable replica of the chip's integer neuron update, derived from its cycle-accurate simulator, so that gradient descent optimizes the exact weights and thresholds the chip runs; it doubles the top-1 accuracy of the mapped backbone on unseen speakers. On 20 Common Voice households of unseen speakers, HyVox reaches 99.6\% top-1 and 5.5\% rejection EER with 2 members and 94.9\% and 13.2\% with 20, and the network deployed on the neuromorphic chip matches its trained model. Each inference on a 3-s window takes 0.96 s and 1.63 mJ of dynamic energy, 42\% lower latency than the fastest embedded ANN baseline and 13.5x less dynamic and 5.8x less total energy than the most energy-efficient one.

cs.NE · cs.AI · cs.LG · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02047

Beliefs in feedback: Factored representations of interacting agents in transformers

David A. Ehrlich, Manuel Baltieri, Fernando E. Rosas, Alexander B. Boyd

原文摘要

Complex systems, from ecosystems to brains, are usually modeled as modular components coupled through feedback rather than as indivisible wholes. Can a transformer trained on the joint behavior of a group of interacting agents be understood in the same way? In this work, we develop a computational-mechanics framework to study agents interacting in feedback loops. We formally prove that any joint stochastic process can be presented as resulting from the behavior of agents interacting in feedback, and the resulting process is generated by a hidden Markov model whose Bayesian beliefs factorize into separate components per agent. Furthermore, our experiments show that transformers trained on such feedback sequences make use of this separability, disentangling the beliefs about the underlying factors into separate subspaces of their residual stream. This representation is found to scale linearly (instead of exponentially) with the number of agents. Moreover, interventions show that these representations are causally efficacious, allowing for targeted steering of individual agents' beliefs by selectively inserting counterfactuals. However, coarse-graining the behavior is found to disrupt the factorization, and can force a higher-dimensional representation. Together, the results establish both the dimensional advantage of a factorized representation and the ability of transformers to exploit it, laying the groundwork for investigating traces of compositional predictive architecture in pretrained models.

cs.LG · cs.AI · cs.MA · nlin.AO

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2610.07766

OTel: Open Telco AI Datasets, Benchmarks, and Models

Farbod Tavakkoli, Gregory Diamos, Kenneth Church, Roderic Paulk, Ashish Vaswani, David Kanter, Jorden Terrazas, Mark Austin 等 13 位作者

原文摘要

We present Open Telco (OTel), an open telecom AI resource that releases derived telecom datasets for retrieval, reranking, instruction tuning, and safety/abstention, together with 30 full-parameter post-trained baselines spanning 10 embedding models, 3 rerankers, and 17 language models. The community has already engaged substantially with the resource: as of May 3, 2026, the released models have been downloaded over 16 million times and the project has received 157+ pieces of media coverage worldwide. Building on prior open telecom datasets and benchmarks, OTel provides documented telecom data sources, held-out evaluation partitions, trained embedding models, rerankers, context-grounded LLMs, and safety/abstention data in one unified resource. Each baseline starts from an open-weight model and is post-trained on OTel-derived data using an open training recipe, then evaluated on held-out OTel evaluation partitions. OTel post-training improves performance across all three model families: embedding retrieval reaches 93.1% NDCG@10, reranking reaches 0.947 MRR@10, and language-model correctness reaches 87.8%. We release OTel as a reproducible starting point and invite the community to expand the data, improve embedding and reranking models, and build stronger context-grounded telecom LLMs.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31090

Poolwise: Evaluating Reward Models for Selection across Prompts

Mateusz Modrzejewski, Tomasz Radzikowski

原文摘要

Reward models are used to select training data, but common benchmarks compare responses only within the same prompt. Selecting data across prompts also depends on how scores compare between prompts. We introduce Poolwise, a protocol that selects a fixed fraction of a response pool by score, measures the selected set's quality using external labels, and reports within-prompt ranking separately. In matched experiments on two rating sets and two model sizes, training each prompt's mean score to match its average response rating improves selection over permuted or omitted mean targets in every seed at 30 percent retention. In grouped HelpSteer experiments, the model with the highest within-prompt accuracy selects a lower-rated set than the correct-mean model. Subtracting prompt means estimated from separate reference responses preserves local rankings but lowers selected helpfulness for six open reward models and two closed judges on HelpSteer. Poolwise provides a direct way to compare reward models and score transformations for data selection.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02028

LARK: Lean-Assisted Reasoning for LLM-Generated GPU Kernels

Zixi Zhang, Jiayi Nie, Haoran Wu, Yujie Yan, Yann Herklotz, Rika Antonova, Robert Mullins, Yiren Zhao 等 10 位作者

原文摘要

Efficient GPU kernels are typically low-level and hardware-specific, and LLM agents can now generate them faster than experts can verify. Existing approaches rely on testing, which provides evidence but not a guarantee of correctness. We introduce LARK, an agentic framework that automatically and formally verifies GPU kernels against their PyTorch reference implementations. LARK proves equivalence in functional and memory behavior under exact arithmetic and establishes a new trust boundary: human effort is only needed to verify operator-level Lean semantics ahead of kernel generation time, instead of checking every single line of generated code. LARK formalizes the GPU machine model and the semantics of each operation in Lean 4 once per target language, and the Lean 4 semantics of any incoming kernel is derived from these pre-built definitions. LLM agents then automate the proof in two steps. First, an agent decomposes the whole kernel semantics into smaller segments and Lean 4 verifies this segmentation, which addresses the intractability of proving equivalence for large kernels directly. Second, agents write Lean proofs that each kernel segment matches its high-level PyTorch counterpart. Together, the two steps give whole-program equivalence. We demonstrate that LARK can be used 1) to ensure correctness in existing code-generation agents and 2) to automatically verify human-written kernel libraries. On the KernelCraft GPU tasks, combined with a simple ReAct agent, LARK enables GLM 5.3 to fully verify 10 of 12 Level-1 kernels and Opus 5.5 all 5 Level-2 kernels. Moreover, over 10 production kernels randomly sampled from popular open-source LLM serving frameworks, LARK verifies 9 and identifies a new data race bug in the tenth. We believe LARK represents a significant step toward verifiable code generation in the agentic era.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.02686

Fooling Reward Models with Gibberish: Adversarial Examples Beyond the Semantic Regime

Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang

原文摘要

Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF). We show that leading RMs can assign higher scores to gibberish than to meaningful reference answers. To systematically discover such inputs, we introduce Token Mapping Perturbation Attack (TOMPA), a framework that uses a perturbed token mapping to extend an attack LLM's search beyond natural language. The mapping changes the linguistic meaning of the attack LLM's natural language responses, producing non-linguistic text for the target RM to score. We then use these scalar scores as rewards to train the attack LLM through reinforcement learning to discover non-linguistic adversarial inputs. Experiments against Llama and Qwen RMs demonstrate such attacks using two instantiations: identity token mapping across different tokenizers and random permutation with a shared tokenizer. Against Skywork-Reward-V2-Llama-3.1-8B, ranked first on RewardBench 2, the two mappings achieve mean rewards of +33.64 and +43.78, respectively, compared with +17.48 for GPT-5 reference answers. Their attack success rates are 97.6% and 100%, measured as the percentages of individual responses scoring above their corresponding GPT-5 references. These results show that strong benchmark performance does not ensure robustness to non-linguistic adversarial inputs, exposing a fundamental vulnerability in using RMs as optimization targets.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02026

Reconstruction as Spatial Evaluation: Diagnosing Cross-View Spatial Intelligence in Large Vision-Language Models

Junfei Wu, Qiuyue Wang, Xuhong Huang, Qihang Peng, Mingsheng Li, Jian Guan, Qiang Liu, Shu Wu 等 11 位作者

原文摘要

The spatial intelligence of large vision-language models (LVLMs) requires the ability to combine local visual observations into a geometrically consistent representation of the physical world. Many static benchmarks assess isolated spatial judgments, such as relative direction or distance, while interactive embodied evaluations combine perception with exploration, planning, control, and simulator-specific execution. To bridge this gap, we introduce RECONSPATIAL, a benchmark centered on multi-view 3D scene reconstruction across indoor, tabletop, and outdoor environments. Given real multi-view images and target-object queries, LVLMs are required to jointly predict oriented 3D bounding boxes in a shared, camera-anchored metric coordinate frame. Reconstructions are evaluated along two complementary axes: Structure for relative layout and Metric for physical scale and camera-anchored placement. Nine atomic spatial QA tasks, grouped into Geometric Perception and Spatial Relations, probe spatial capabilities involved in joint reconstruction. Offline navigation extends evaluation to path planning. Evaluation of 18 frontier LVLMs reveals a consistent gap between relative scene structure and metric reconstruction; even GPT-6-Astra scores 81.4% on Structure but only 58.7% on Metric. Tracing this gap, diagnostic analyses link atomic spatial capabilities to reconstruction quality and show that relational consistency alone does not ensure metric accuracy. Experiments with 3D map injection further separate scene construction from path planning, revealing how these geometric errors limit navigation success. Finally, spatial fine-tuning yields broad transfer across both spatial and general vision-language benchmarks.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02021

ClickSight: An LLM Framework for Interpreting Student Clickstreams Through Learning Strategies

Bahar Radmehr, Lan Tran, Ekaterina Shved, Fatma Bet{ü}l G{ü}reş, Adish Singla, Tanja K{ä}ser

原文摘要

Digital learning environments produce rich clickstream data that can reveal how students approach learning tasks, yet interpreting these fine-grained traces often requires substantial expert effort. We introduce ClickSight, a framework for interpreting student clickstreams through learning strategies defined in the literature. Given a student clickstream and a predefined set of learning strategies, ClickSight uses a staged LLM-based pipeline to identify strategy-relevant evidence, assess adherence to each strategy, and generate an evidence-grounded interpretation of the student's behavior. We evaluate ClickSight across two learning environments, 365 students, and 12 model backbones using an expert-grounded quality rubric and an LLM judge calibrated with human-expert ratings. Our results show that ClickSight can generate high-quality strategy-based interpretations across different models and environments, with reasoning models performing more consistently than instruction-tuned counterparts. We further find that providing external clickstream-extracted guidance can improve interpretation quality for strategies that require precise quantitative information from the trace. By connecting fine-grained clickstreams with theoretically defined learning strategies and preserving the evidence underlying each judgment, ClickSight provides a flexible approach for studying student behavior in digital learning environments.

cs.AI · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02015

Scaling Makes It Possible: How Large Models Master Impossible Languages

Yaning Jia, Chunhui Zhang, Chiyu Ma, Zhongyu Ouyang, Ivory Yang, Soroush Vosoughi

原文摘要

While language models (LMs) excel in natural language tasks, their ability to learn impossible languages--those that violate the structural, cognitive, or logical constraints that make human languages learnable and functional--remains debatable. This controversy is further fueled by a divide between linguistic theorists and empirical researchers working with small-scale LMs. To address this controversy, we introduce semantic coherence. This concept measures how effectively semantic information is expressed in language structures and examines the learning capabilities of LMs across multiple scales. By fine-tuning billion-parameter LMs on impossible language samples, we demonstrate that larger LMs achieve similar performance on impossible and possible languages, whereas million-parameter LMs exhibit significant degradation when trained on impossible languages. This performance gap widens as semantic complexity increases. We further show that scaling up the LM size fundamentally shifts the learning focus from grammatical rules to semantic understanding, with billion-scale LMs exhibiting a threefold reduction in sensitivity to low-level linguistic perturbations while maintaining stable performance under high-level semantic perturbations.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02002

To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments

Bahar Radmehr, Jiaxu Zhao, Fatma Betül Güreş, Adish Singla, Tanja Käser

原文摘要

Simulated students offer a scalable way to test learning platforms and AI tutors before deployment with real students and to augment scarce data for studying learning at scale. Existing LLM-based simulators primarily target short, language-centered interactions. In open-ended learning environments, however, student behavior emerges from patterns across long-horizon interaction trajectories, where turn-level prompting can drift from an assigned behavior profile. We introduce ALPS (Align Long-term by Planning Short-term), a hierarchical simulated student conditioned on observable, environment-specific behavior profiles. Rather than selecting every action independently, ALPS alternates between planning profile-aligned task segments and generating the corresponding actions. We evaluate ALPS in both data-sufficient and data-scarce settings, where supervision comes either from real student trajectories or from a teacher LLM. Across both settings, we compare in-context learning (ICL), supervised fine-tuning (SFT), reward-ranked fine-tuning (RAFT), and their sequential combination (SFT followed by RAFT). Experiments in an inquiry-based physics game and a pharmacy simulation evaluate behavioral density and coverage against held-out real data, and profile consistency using a human-aligned LLM judge. Across both settings, ALPS consistently outperforms turn-level generation, achieving comparable density and judge pass rates under scarce supervision, although coverage remains lower. These results show that hierarchical planning enables faithful, profile-aligned simulation over long interaction horizons, even with limited real student data.

cs.AI · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02001

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue

Austin M. Y. Cheung, Harsh Vardhan Gupta, Go Nam Lui, Lok Kan Chan, Ginny Y. Wong, Simon See

原文摘要

Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumption: figures are revised, stances shift without being restated, rules stated once govern later questions, and a single company is discussed under several analytical lenses. Memory systems that retrieve the passages most similar to a question, or the most recent ones, therefore return superseded values, miss rules that share no wording with the question, and cannot recover a stance spread across sessions. We present TrackMem, a per-speaker graph memory that tracks the history of figures, separates perspectives by entity and lens, and preserves each speaker's actions in chronological order. To evaluate it, we introduce FinLoCoMo, a benchmark of 15 long-horizon investment conversations with 765 questions in two splits: one following the LoCoMo categories and one targeting four failure modes. With two readers, TrackMem outperforms existing memory systems on both splits. On the failure-mode split it reaches 73.9% macro accuracy against 69.4% for the strongest baseline, with the largest gains on questions about revised figures (86.5% against 73.4%).

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.22061

FAOPs: Normal Forms and an Algebra for AI Agent Workflows

Ali Mohammadi Shanghooshabad

原文摘要

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, as regulated sectors require. 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 sub-workflow a single canonical definition so a change propagates instead of drifting, and Scoped (FNF-4) checks that each FAOP lists resources used by its own actions and the FAOPs it calls, while guardrails declared by it and by FAOPs that call it remain attached to their sources. A FAOP algebra of provably sound equalities turns refactoring and parallelization into compiler rewrites; orthogonal extensions add optimization (+O), bounded completion with time and cost limits (+B), and reachability checks (+R); and an architectural-level classifier (0-3) determines whether a workflow needs AI at all. Together, these make integrity, isolation, typing, stopping limits, 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), and a separate executor that loads FAOPs from SkillBase and enforces these guarantees at run time. A worked financial workflow illustrates the approach end to end.

cs.AI · cs.DB · cs.PL

查看论文
arXiv ↗PDF ↗