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
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 07:12 · 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 08:20 — 2026-11-09 08:20（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 07:12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 07:10（北京时间）
新论文 · v1arXiv:2610.38445

DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences

Hugo Math, Maximilian Forstenhäusler, Christos Anagnostopoulos

原文摘要

Temporal foundation models such as Chronos and TimesFM generalize across domains through a shared numerical observation space. In contrast, discrete event sequences (DESs), including operational event logs or patient clinical-event trajectories, have domain-specific event vocabularies whose labels lack a consistent correspondence across domains. Beyond this lack of consistency, the number of distinct events in real-world settings is high enough to challenge both classical temporal point process modeling and current in-context foundation inference models such as FIM-PP. Critically, current foundation models for DESs are limited to a small, fixed number of event types, restricting their applicability to realistic, high-dimensional event streams. To address this, we propose two complementary modules: (i) DES-JEPA, a joint-embedding predictive architecture that learns a shared discrete vocabulary from synthetic stochastic processes with unaligned event vocabularies; and (ii) DES-PFN, a discrete event sequence prior-fitted network that reuses the learned vocabulary for in-context next-event prediction. Without task-specific fine-tuning, this framework achieves competitive zero-shot performance on eight unseen real-world datasets and scales up to 700 distinct event types.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36410

Expert lithological labels do not improve learning when used to predict marine sediment properties

John M. Aiken, William Gilpin, Thorsten W. Becker

原文摘要

Scientific drilling has produced large archives of physical, chemical and magnetic measurements linked to descriptions of the rock recovered. These archives are mostly incomplete: instruments sample at different intervals, recovery is partial, and destructive analyses preclude later measurement of the same material. We train an self-supervised embedding model on the LILY ocean drilling database using six routinely logged properties (bulk density, magnetic susceptibility, natural gamma radiation, and red, green and blue reflectance) across 236,963 observations from 296 boreholes, with a masked variational autoencoder that has a heteroscedastic Gaussian decoder and learnable mask tokens. The embeddings separate geologist-assigned lithologies as well as a variant trained with those labels, and increasing the weight on the labels degrades reconstruction while leaving classification unchanged. The labels are recoverable from the measurements geologists use to assign them, so training on them adds nothing. Lithological categories compress continuous measurements into classes, and compressing them discards what the measurements record about the processes that produced the rock. The embeddings also predict physical properties that were absent from training, on boreholes the model has never seen. While depth should account for this since sediments compact with burial, it does not. On held-out boreholes depth alone reaches a median $R^2$ of -0.02, against 0.20 for the embedding.

physics.geo-ph · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38439

Predict the Reward, Not the World: World Reward Models for ML Agents

Yuxiao Lee, Zherui Yang, Fan Liu, Hao Liu

原文摘要

Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing them, and keeping the best. Execution gives the search reliable feedback, but a single run can take hours, and most runs end in programs the agent discards. Recent agents try to save these runs by letting a large language model act as a world model that predicts how each program would perform. However, a wrong prediction feeds the search false information. We argue that an agent does not need to predict the outcome of execution, only the decision that execution would support. We propose World Reward Models (WRMs), which learn from real execution results to choose directly which candidate will perform better, without predicting any intermediate outcome. We prove that a selector which predicts execution from the same inputs cannot outperform the best direct selector, that predicted outcomes add an error which can make a likelihood-trained world model prefer the worse program on every instance, and that cross-entropy on executed winners drives a WRM toward the optimum. Our WRM, ForeCritic, adapts a 9B typed decision model to 5k executed program pairs. On 12,438 held-out pairs from 26 ML tasks, it picks the better program 79.4% of the time, while general-purpose LLM judges reach 53--62%, and its probabilities are calibrated. Inside AIDE, ML-Master, and ForeAgent, it cuts mean task time by 4.4--7.5 times while keeping their mean scores within 0.01 or raising them.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38438

RoleFUZZER: User-Behaviour Fuzzing for Role-Specification Adherence in Large Language Models

Kshitish Ghate, Michael Saxon, Tadayoshi Kohno, Aylin Caliskan

原文摘要

Large language models (LLMs) are often conditioned into specific roles such as tutors, interviewers, or agents acting for an organisation, through system prompts that specify how they should behave. The extent to which they can actually adhere to these role specifications under multi-turn interactions with realistic and potentially problematic users is understudied. To address this, we propose user behaviour fuzzing, a guided search over plausible user behaviours that can lead a model to violate its role specification, and introduce RoleFUZZER, a framework that adapts coverage-guided fuzzing from software testing to operationalise the search. RoleFUZZER constructs scenarios guided by a user-behaviour coverage grid that crosses a grounded taxonomy of user interaction types and the role specification of the model under test i.e. what is under pressure. With RoleFUZZER, we evaluate LLMs across five role specifications, including tutor, financial advisor, AI interviewer, antagonistic roleplay character, and web agent under organisational policies. Across simulated and validated conversations in 15 campaigns, the framework reaches >= 89% coverage of the 64-cell behaviour grid for every model and role tested, and surfaces specification-grounded failure patterns. At an equal budget of conversations, removing the RoleFUZZER grid and asking an LLM to generate specification targeting users free-form lowers coverage to 39-69% with fewer kinds of violations. The same specification can also fail in opposite directions. For e.g., on the antagonist, open-weight target models override the player's safety signals, while Claude Haiku 4.5 breaks character instead. RoleFUZZER offers a tractable way to uncover vulnerabilities in LLMs across role specifications by testing diverse user behaviours that are likely to violate them.

cs.CL · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38431

DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas

Tiantong Wu, Wei Yang Bryan Lim

原文摘要

Machine unlearning aims to reproduce the behavior of a model trained without designated data. For probabilistic decision models, this target also depends on the candidate options supplied at inference. We introduce DecisionUnlearn-Bench, an empirical framework that compares full, unlearned, and retain-only models across deletion granularities, label renderings, and candidate sets. Across 20 eligible model configurations on the BANKING77 dataset, full-to-oracle displacement increases consistently from example to association to class deletion. Replacing semantic option labels with opaque codes nearly eliminates the retrained oracle's recognition of deleted classes, even with successful acquisition of the full model, whereas changing the candidate set alters both the oracle and the measured unlearning progress. SimNPO satisfies the screening criterion in 19 of 20 configurations, but its gains vary substantially across seeds and deletion targets. Development tuning on the CLINC150 dataset does not establish a positive pooled effect across 48 intents. At approximately matched suppression, methods can differ markedly in oracle fidelity. Recovery experiments further distinguish initial forgetting from subsequent adaptation and show conclusions that depend on both architecture and metric. These results show that evaluating decision-model unlearning relative to a schema-specific retraining target, with separate reporting of effect size, utility, robustness, and recoverability.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38426

The Code Behind the Layout: AI Agents for Analog Layout Generators

Minxing Chu, Anhang Li, Martins Atilla, Ruichen Qi, Mehdi Saligane

原文摘要

Analog layout remains largely manual and hard to automate. Generator frameworks such as gLayout express layouts as programs, producing layouts from parameterized, design-rule-aware generators; however, writing such generators still takes expert effort. Large language models (LLMs) could now write generator code, and frontier models can even draw layout geometry from design intent. This raises a practical question: if a model can draw the layout itself, what does a generator framework still contribute, and is applying these models to a generator framework better than having them draw a layout from scratch? Through controlled experiments on gLayout in SKY130, we find that the main obstacle to drawing a layout directly is its time and token cost, and that the main advantage of a model building on a generator framework is reusability. Its verified primitives keep each model edit small enough to check, and its parameters allow a single edit to be evaluated across an entire family of layouts. Accordingly, a model is most effective when it develops the layout from the generator source of the family that the design intent belongs to, and tests each edit on the family members most likely to fail, so that one verified change improves every layout the generator produces. The results of these family tests can then serve as supervision for a local model, which learns edits that hold across the family at a fraction of the inference cost.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31710

Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents

Ruopei Sun, Jianfeng Cai, Kangwen Zhao, Wengang Zhou, Houqiang Li

原文摘要

Context compaction lets long-horizon coding agents continue beyond their context windows, but can erase the state needed to finish a task. Prior evaluations measure efficiency, retained information, or end-to-end success, leaving the effect of a specific history replacement difficult to isolate. Compact-Bench pairs full-history and summary-only continuations from a shared repository state, and evaluates recurring details and successive production compactions. It covers 35 SWE-bench repairs, 146 agentic sessions, and 106 production chains. Across 14 summarizer backbones, stable damage ranges from 5-64% of 22 full-history successes: Claude Opus 4.8 preserves the most repairs, while DeepSeek-Flash damages the most. With Kimi-K3 as summarizer, the Kimi Code prompt preserves the most task continuations (19/22), whereas Claude Code retains the most recurring details (15.0%). LLM summaries retain at most 16.0% of recurring details, compared with 79.1% for mechanical extraction; production summaries retain 15.7% at the first boundary. Failures recur across methods: one repair is damaged by 13/14 backbones, and another by all 5 prompts. These results show that reliable compaction requires preserving the progress needed to complete a task, and that retaining relevant information alone does not ensure successful continuation. Code is available at https://github.com/cai-jianfeng/compact-bench and data is available at https://huggingface.co/datasets/caijanfeng/compact-bench.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38411

Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI

Kiranmayee Janardhan, Karthick S, Madhusmita Panda, Bharathi Vokkaliga Ganesh, Syed Ahmed

原文摘要

Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional FL provides limited runtime governance, evidence verification, fairness assessment, explainability monitoring, and auditability. This paper proposes Governance-Aware Federated Learning (GAFL), which combines independent governance-evidence verification, temporal trust, fairness and explanation assessment, anomaly detection, policy enforcement, normalized aggregation, and tamper-evident audit logging. Client-reported governance values are authenticated, bound to their submitted model updates, and independently recomputed before aggregation. A cross-silo prototype with 10 participants was evaluated on the Adult Income dataset under honest, benign non-IID, biased-data, malicious-update, non-compliant, falsified-evidence, and mixed-threat scenarios. Four methods were compared across five random seeds: FedAvg, FedAvg with anomaly filtering, GAFL without independent verification, and complete GAFL. Complete GAFL intervened on all affected participants at the final round across the evaluated risk scenarios, including identifying 100% of falsified-evidence participants, whereas GAFL without verification identified none of the falsified-evidence participants. Final macro-F1 ranged from 0.7520 to 0.7733 across GAFL scenarios. Complete GAFL required 173.67 plus or minus 26.94 ms of governance processing per round, compared with 3.82 plus or minus 0.79 ms for FedAvg. A strict demographic-parity threshold also caused frequent interventions for honest participants, demonstrating a significant fairness-policy and utility trade-off.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.08351

Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations

Zhiliang Chen, Alfred Wei Lun Leong, Shao Yong Ong, Apivich Hemachandra, Gregory Kang Ruey Lau, Chuan-Sheng Foo, Zhengyuan Liu, Nancy F. Chen 等 9 位作者

原文摘要

Fine-tuning an LLM to maximize performance on a downstream task requires finding the optimal data and model configuration. This is a black-box optimization problem that Bayesian optimization (BO) addresses by sequentially evaluating training configurations and using observed performance feedback to adaptively guide the search towards better configurations. However, directly applying BO to the joint data-model space suffers from two fundamental challenges: the prohibitive cost of full LLM training at each iteration, and the large number of BO iterations required for effective exploration due to the high problem dimensionality. This paper introduces JoBS, a BO-based approach that co-optimizes data and model configurations without requiring a full training run at every iteration. JoBS allocates an initial portion of the optimization budget to learn a scaling-law-inspired performance predictor that estimates fully trained LLM performance from only a small number of training steps. The remaining budget is then used to run BO with this predictor, eliminating the need for full training runs and enabling JoBS to explore significantly more data and model configurations within the same budget. We analyze JoBS's average regret and derive the optimal budget allocation between predictor learning and BO iterations. Empirically, JoBS outperforms independent data and model optimization methods and existing multi-fidelity BO baselines across a diverse set of downstream tasks. Our code is available at https://github.com/chenzhiliang94/BO-for-LLMs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38405

SpaceAct: Benchmarking 3D Spatial and Temporal Reasoning via Closed-Loop Action and Active Perception

Chenglong Shi, Zekai Yuan, Yue Song, Jon Pu, Will Wu

原文摘要

To solve problems in 3D space rather than merely describe images, multimodal large language models (MLLMs) need 3D spatiotemporal reasoning: reconstructing 3D geometry from occluded 2D views, anticipating physical dynamics, and executing precise, closed-loop actions. Prior studies test passive VQA on static images or symbolic planning, requiring no execution or supplying privileged coordinates while ignoring collision, statics, and timing. We introduce SpaceAct, an interactive benchmark evaluating 3D spatiotemporal reasoning via closed-loop physical action and active perception, with SAPA, a Spatiotemporal Active-Probing Agent framework. Built on interlocking bricks and mechanical puzzles, it has 108 verified instances across 36 task families in six categories, without privileged coordinates, and diagnostic modes (+plan, +state, no-camera, blind, L7 levers). In brick-bridging or aperture-threading, models rotate the camera to resolve occlusion, read in-scene rulers, output 6-DoF poses under swept-collision and statics checks, and self-correct via split-screen rollback feedback (dynamic tasks freeze time during deliberation and give five strobe frames). Across 10 frontier MLLMs on the 44 hardest instances, scores span 4.8-79.1 (seven solve at most 27.3% of 6-DoF tasks); for the top three, a reference plan (+plan) closes 44% of the gap while leaving collisions at 5.2 per episode, whereas adding exact 3D state (+state) closes 90% and cuts collisions to 0.5; for four others, +plan lifts the mean score from 10.9 to 35.3 and +state to 81.8; and 46% of failures are collision or observation loops. SpaceAct and SAPA advance evaluation to closed-loop physical interaction, showing that even with a valid plan, MLLMs remain bottlenecked by 3D visual grounding and action refinement, while offering a testbed for active multi-view exploration and explicit 3D grounding.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38402

LLMs as Judges and Examinees for Medical Item Difficulty Prediction

Xiaomeng Xiong, Marcus Walker, Yanlin Jiang

原文摘要

Predicting medical item difficulty from item text alone remains challenging. Prior work has largely relied on linguistic features or text representations derived from general-purpose and domain-specific language models, but predictive performance has remained modest. This study takes a different approach by using difficulty-related signals that emerge when open-weight large language models (LLMs) interact with test items. Using USMLE and PANCE medical licensure examination items, we examined LLMs in two roles. As judges, the models provided absolute difficulty ratings and pairwise difficulty comparisons. As simulated examinees, they generated response-based signals including correctness, keyed-option probability, response entropy, and the probability margin between the top two options. We then combined the strongest judgment and response signals with baseline item features in downstream prediction models. Pairwise difficulty judgment was the most consistent individual LLM signal across both datasets, while simulated-examinee signals and absolute judgments provided complementary information in some feature combinations. The best configurations reached a Spearman correlation of $ρ$ = .447 on USMLE, exceeding the best system in the 2024 BEA shared task ($ρ$ = .25), and $ρ$ = .494 on PANCE. These results were comparable to direct absolute judgments from the proprietary frontier model Claude Opus 5 ($ρ$ = .443 and .488, respectively). Overall, judgment and response signals from open-weight LLMs captured difficulty-related information beyond text representations. Because these models can be deployed locally, the approach offers a practical option for predicting the difficulty of unreleased or high-security test items.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38398

Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web

Yuqi Qiu, Zuyao Xu, Lu Sun, Xiang Li, Fasheng Miao, Fubin Wu, Haixin Duan, Zheli Liu

原文摘要

The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network connections and execution instances. Such interactions require stable communication entries, message reception when instances are offline, and source verification after delayed reading. How to organize these responsibilities so that cross domain communication does not depend on specific execution instances being continuously online is a key issue for building long term agent interaction infrastructure. We propose ATP (Agent Transfer Protocol), a cross organization agent communication protocol adopting a domain mediated architecture. In this architecture, administrative domains maintain stable addresses and receiving entries for logical agents. The domain servers of both parties continuously undertake cross domain transmission. The receiving domain verifies and saves messages for execution instances to read later. The sending domain signs the complete message envelope. This allows the receiving instance to independently reverify the domain source and content integrity after the original connection ends, provided the original verification public key is still trusted and obtainable. We implemented an ATP prototype and evaluated it through a controlled cross organization LLM agent workflow, mechanism checks and latency measurements. The workflow completed subsequent business processing after instances went offline or were replaced. The independent verifier successfully verified the domain source and content integrity of saved messages. Latency measurements further quantified the communication and processing overhead introduced by the continuous mediation of domain servers.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36820

An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning

Ngoc Luyen Le, Marie-Hélène Abel, Bertrand Laforge

原文摘要

Early-warning models in learning analytics can identify learners at risk of failure or withdrawal, but the resulting alerts are often only weakly connected to inspectable learning evidence. A risk score may indicate that intervention is needed without showing which traces, assessment events, or temporal patterns justify the alert. This paper introduces an incremental Learner Digital Twin for evidence-grounded early warning, implemented as a lightweight knowledge graph. The twin is updated at temporal checkpoints by replaying learning traces and assessment records, and it serves both as a feature-extraction substrate and as an explanation-grounding substrate. Predictive features are derived through graph-mediated queries, while features, attributions, alerts, evidence items, and raw records are represented as queryable graph entities. The framework is instantiated and evaluated on a public learning-analytics benchmark under a temporal protocol. The results show that graph-mediated feature extraction preserves the predictive behavior of equivalent raw-table features across model families and checkpoints. Generated alerts are materialized as evidence chains linking risk decisions to feature attributions, evidence items, and raw platform records. The study shows that early-warning prediction can be routed through a semantic and provenance-aware representation while preserving predictive performance and adding traceability, verifiability, and evidence-grounded explanation.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35229

Joint Latent Reasoning and Observation for Agentic Video Understanding

Junzhang Liu, Hao Yuan, Yiming Wu, Qi Zhang, Long Chen, Zhecan Wang

原文摘要

Effective video agents must learn not only how to answer, but also where to look next. Transferring this capability to smaller models is challenging because each observation serves two purposes: supporting an answer and guiding the search for further evidence. Textual descriptions may capture what is currently visible while omitting cues needed for subsequent acquisition. We introduce Latent Agentic Reasoning for Video Analysis (LARVA), a framework that distills multi-round video agents through jointly learned latent reasoning and visual observations. Rather than communicating through captions, an observer passes compact continuous representations to a reasoner that selects the next acquisition action or produces the final answer. Crucially, action and answer supervision propagate through this interface, training the observer to communicate information useful for downstream decisions. Observation reconstruction and reasoning-distribution alignment provide auxiliary supervision from textual teacher trajectories. Across five video-understanding benchmarks, LARVA achieves strong performance with 4B and 7B backbones. On VideoHolmes, Video-MME, and LVBench, the 7B model outperforms a textual CoT student trained on the same teacher trajectories by 5.1, 2.5, and 3.7 percentage points, respectively. These results highlight the value of jointly learning how agents represent evidence and act on it when distilling video-understanding capabilities.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38392

Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents

Hau-Sing So, Daixian Liu, Weicai Long

原文摘要

Self-improving LLM agents edit their own harness, the prompts and rules around a fixed model, and keep an edit only if an acceptance gate scores it higher on a batch of tasks. Such a gate sees what the harness does under the current model, not what it would still prevent if one safeguard failed. When safeguards overlap, deleting one is masked: the others still block the harm, so the gate decides on task success alone and redundancy erodes unseen. We measure harm for every subset of four written safeguards in two agent environments and run 411 improvement loops under ten gate rules, mostly as controlled deletion experiments, plus three runs of the GEPA optimizer. A deletion behind another working safeguard adds almost no observable harm. A paired significance test blocks deletions that pass by chance but not deletions that genuinely raise task success, and a larger evaluation batch lets it delete cheaper safeguards: at the same cost, 20-task batches kept every harness protected while 40-task batches lost all six. Large harm audits prevent exposure but not the loss of depth, which turns into harm when the harness is reused with a weaker model. GEPA kept every safety rule verbatim, yet two of its three final harnesses misused credentials under a weaker model. A statistical model frozen before the runs predicts where each gate's protection breaks as safeguard cost and batch size change, and freezing safety text or auditing one-layer ablations preserves depth.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38391

SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning

Qirui Liu, Wei Cao, Yu Mi, Yichen Sun, Xuekun Zhang, Lei Liu, Yue Shen, Zhixuan Chu

原文摘要

Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed trajectories may contain correct steps, while successful trajectories can contain errors. Trajectory-level skills can also shift teacher preferences at unrelated steps, introducing off-target distillation signals. We introduce SCOPE, a framework for Selective Critical-Step On-Policy Self-Distillation. After a supervised warm-up, the policy analyzes its own trajectories, generates step-specific hindsight skills, and distills their guidance only at selected error steps. A bounded signed teacher-student coefficient stabilizes auxiliary updates while preserving positive reinforcement and negative correction. A success-relative pairwise length reward further encourages efficient task completion. Experiments on ALFWorld and WebShop demonstrate consistent improvements across multiple model backbones. With Qwen2.5-3B, SCOPE achieves 97.7% success on ALFWorld and 85.2% on WebShop, outperforming SEED by 5.9 and 6.3 percentage points, respectively. On unseen ALFWorld tasks, SCOPE reaches 89.6% success, improving over GRPO by 23.2 percentage points with 46.7% fewer interactions. Scaling to Qwen3-32B, SCOPE achieves 99.2% success on seen ALFWorld tasks and 94.0% on unseen tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.12052

Representation and Reference Selection in Training-Free Synthetic Image Attribution

Meiling Li, Pietro Bongini, Benedetta Tondi, Mauro Barni

原文摘要

Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image. Training-free reference-based attribution methods are easily scalable, since newly emerging generators can be incorporated by adding source-specific references rather than retraining a task-specific classifier. Their performance depends on two coupled factors: the representation space used for comparison and the way source-specific references are constructed. However, the interaction between these two factors remains largely unexplored. In this paper, we provide a controlled analysis of this interaction using references and off-the-shelf pretrained representations. We study representations extracted from different layers of CLIP and DINOv2, along with three reference selection strategies with varying semantic constraints: arbitrary, semantically aligned, and resynthesis-based references. Our results show that attribution accuracy generally peaks at intermediate representation levels, indicating that source-discriminative cues are more accessible before strong semantic abstraction dominates. We further show that intermediate representations are not completely semantically neutral, making reference selection critical: semantically constrained references reduce query-reference mismatch and improve attribution, especially under limited reference budgets. Resynthesis is useful in low-reference regimes, while semantically aligned references provide a better accuracy-cost trade-off when a moderate-sized reference pool is available. Our findings show that training-free reference-based attribution should be understood as the interaction between where images are compared, how the reference set is constructed, and how many references are available. Code and datasets are available at https://github.com/meiling-fdu/RefPrint.

cs.CV · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.19985

Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification

Zhilong Zheng, Letian Tao, Yujie Yang, Wei Xiong, Kehua Sheng, Bo Zhang, Jingliang Duan, Keqiang Li 等 10 位作者

原文摘要

Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tuning methods, they adopted an overly restrictive Subspace Orthogonality condition. In this paper, we introduce a purely post-hoc and tuning-agnostic weight rectification framework that achieves Parameter Space Orthogonality, which is the necessary and sufficient condition for preserving historical performance to the first order. By projecting parameter updates into the JAcobian NUll Space (JANUS), our method significantly recovers compromised historical knowledge without interfering with the underlying fine-tuning process. To overcome the local validity of the Jacobian approximation, we further propose a Multi-step Adaptive Rectification mechanism that utilizes the JANUS shift to dynamically verify the valid trust region and adjust step sizes. Coupled with our proposed ghost projection, ghost orientation comparison, and sequence-level singular value decomposition compression techniques, JANUS also achieves great temporal and spatial efficiency. Experiments demonstrate that JANUS seamlessly integrates with various fine-tuning methods, significantly mitigating the stability-plasticity dilemma by recovering historical knowledge while preserving downstream task adaptation.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37369

Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories

Zirui Ding, Xinxin Fan, Hao Yuan, Shaoye Luo, Men Niu, Quanliang Jing, Yunfeng Lu

原文摘要

Large language models (LLMs) are usually evaluated by final-output correctness or safety, yet an endpoint label does not reveal how a failure develops throughout the reasoning process. We therefore ask whether ordinary reasoning failures and adversarially induced failures can be characterized using the same internal coordinates. Towards this end, we in this paper study a white-box diagnostic framework CauTrace to disclose the root-cause of why LLM fails from three fundamental inspections: Functional States, Propagation of Representation, Temporal-State Coordination and Reasoning Trajectory. First, seven functional states are creatively defined to represent the support and constraint processing in LLMs. Second, the propagation of representation change measures how the changes among the seven states persist across subsequent Transformer blocks. Third, temporal-state coordination and trajectory topology characterize when the commitment and verification occur relative to the support, and how the dominant state sequence evolves over the full inference process. Finally, we evaluate CauTrace on both clean reasoning failures and paired adversarial perturbations. Across Qwen and LLaMA-family models, the failed traces show weaker Attention-MLP agreement on support-state updates and less verification activity relative to commitment, while the exact representation-level signatures and timing shifts vary by architecture. Held-out repair and steering tests demonstrate consistent operational signals that were in line with our claims for certain models and specific settings, with aligned steering producing the predicted directional changes in process measures. Overall, CauTrace provides a unified diagnostic framework for analyzing failure dynamics through changes in support, commitment, and verification, which would shed light on the in-depth research on LLM security.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38382

Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs

Junxi Wu, Yiwen Guo, Shu-Tao Xia

原文摘要

Test-time scaling improves large language models through additional computation, but how to adapt the topology of internal computation to individual inputs remains underexplored. Existing approaches largely fix recurrent or parallel architectures during training, or reconfigure frozen models along a single structural axis. We introduce SelfMorph, which makes computational shape an input-dependent inference-time decision. It unifies the original forward path (BASE), serial reuse of a layer span (REPEAT), and local branching and merging of perturbed hidden states (BRANCH) in a unified space parameterized by type, location, and intensity. Since they offer complementary benefits rather than uniform dominance, we use a lightweight selector that reads the backbone's depth-wise hidden state trajectory on the prompt to choose a morphology before response generation. We train the selector by distilling utility-based distribution from offline morphing that jointly account for task performance and computational cost. Evaluated on three LLMs spanning 4B-27B, SelfMorph achieves a 8.06% mean relative improvement on five in-distribution benchmarks and 4.45% on four unseen benchmarks. It achieves the strongest performance in 24 of 27 settings. These findings identify input-adaptive computational topology as a complementary axis of test-time scaling beyond generating more tokens. Our code is available at https://github.com/creator-xi/SelfMorph.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38361

Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation

Gangzhen Qian, Kainan Zhou, Chuhong Xu, Hang Xiao, Zhi Jing, Rong Bao, Lu Yi, Zhaoyi Li

原文摘要

The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of consuming /llms.txt while ordinary retrieval remained fixed. The initial audit covered 39 sources through August 16, 2026, with later targeted updates through October 14. A purposive 15-tool study observed no automatic requests in 45 trials at one endpoint; a non-probability log study found that 97% of domains with detected files received no recorded requests in May 2026. We separate publication, fetch, model use, and action; define five operational threat paths and paired security-utility estimands; and exercise deterministic pre-model controls with 30 author-defined parser fixtures. We also execute a reduced pilot: 24 tasks across eight sites, five conditions, and 120 real model responses, with ordinary evidence held fixed. Frozen automatic scoring identifies attacker-target adoption in $21/24$ raw adversarial responses, with one further response unresolved; the adversarial URLs-only condition has no known adoptions and one unresolved response. The pilot measures output changes conditional on supplied evidence, without live retrieval or external actions. Together, the framework and pilot distinguish manifest-content effects from publication, discovery, and downstream execution, while leaving full retrieval and agent evaluation open.

cs.CR · cs.AI · cs.CE · cs.CL · cs.DB · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38360

SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool

Zihan Deng, Zhenzhen Gong, Yujie Liu, Jiaxin Gong, Dingkun Liu, Kexian Xie, Yixing Huang, Peng Jin 等 13 位作者

原文摘要

Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts. Feed-forward Gaussian methods transfer the reconstruction cost to training and decode each coordinate from projection-aligned features and neighboring anchors. However, information from the whole scan is written only when the field is constructed and cannot be retrieved during coordinate decoding, leaving the volume inconsistent within the scan. This is a common limitation of such methods: once the field is fixed, decoding uses only local features and reconstruction quality drops substantially. We propose SparseTokenGS, a Gaussian-based method for sparse-view cone-beam computed tomography reconstruction via a reusable token pool. Anchor Token Fusion and Point-Token Attention query this shared pool at the anchors and at the query coordinates, respectively. The local Gaussian prior is retained, and the volume is reconstructed in one forward pass, without per-scan optimization or a projection-domain loss. On three public chest and dental datasets, SparseTokenGS achieves the highest reconstruction performance among the compared methods. On clinical dental scans, reconstruction from only six projections reaches 29.51 decibels in peak signal-to-noise ratio and a structural similarity of 0.842 against the full-view reference, and off-the-shelf tooth-and-pulp segmentation keeps these structures separable for root-canal localization. Experiments on volcanic rock and chicken show performance after same-object adaptation. A reusable token pool gives feed-forward reconstruction a mechanism that keeps scan-wide context available through decoding and can benefit future rapid clinical lesion localization and analysis. The code is available at: https://github.com/FrankDengAI/SparseTokenGS.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38352HF 社区推荐

WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video

Chenyu Mu, Wenming Weng, Qinrui Wang, Xingsong Ye, Hao Yu, Jun He, Chong Sun, Chen Li 等 11 位作者

原文摘要

Producing long-form videos from narration requires interdependent decisions that remain coherent across shots. Existing agentic editors often use multi-stage workflows driven by general models, leaving the quality-cost trade-off of compact, task-adapted policies unclear. We address this gap with WeVisCut, a long-form script-to-video system that connects tool execution with policy learning. Its agent harness maintains shared production state so that tool feedback informs subsequent decisions and repairs. Because finished videos do not expose these decisions, our four-stage data pipeline combines editing inversion with verified replay to turn recovered editing intent into executable supervision. Applied to 3,750 finished videos, this pipeline yields over 130K training examples. We use this supervision to train a single 9B policy that coordinates production and recovers from failures within the same harness. Moreover, we introduce a 100-task benchmark and five metrics assessing editing quality and delivery reliability. Under a shared tool environment, WeVisCut substantially outperforms its base model and achieves comparable performance to Claude Opus 5 while using nearly 33x fewer generated tokens per successful output minute. It also outperforms task-matched native editors on our proposed metrics.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38349

Aligning Misaligned Benchmarks for Single-View Novel View Synthesis

Yang-Che Tseng, Erqun Dong, Jeong-gi Kwak, Gopal Sharma, Shakiba Kheradmand, Stephan Garbin, Hossam Isack, Kwang Moo Yi

原文摘要

While single-view novel view synthesis methods have been dramatically enhanced recently, how to quantify their performance has yet to be standardized. In this work, we demonstrate that an important factor lies in how each method's own reference frame is aligned with the so-called ground-truth pose. Existing methods often rely on test-time optimization of target poses for this alignment, which inherently is ill-posed due to the complexity of the optimization landscape of camera poses vs render accuracy, leading to methods being evaluated at an arbitrary local optimum. Some recognize this limitation and thus rely on 3D reconstructions of entire scenes using training and test views to align poses, which may be infeasible. In this work, instead, we propose to use traditional 2D-to-2D and 2D-to-3D image matching techniques to align 3D reconstructions. We also evaluate only within co-visible regions, between different views, which is the only place where a `correct' ground truth can be defined. Our evaluations show that with proper coordinate alignment, novel-view synthesis methods that use explicit 3D Gaussians achieve the state of the art, despite being previously reported in the literature to be outperformed by pure image-based 2D methods. We further provide a simple baseline that directly utilizes an off-the-shelf video generator and a feed-forward geometry estimator. Our simple baseline is already comparable to state-of-the-art methods specifically trained for novel-view synthesis, without any task-specific training.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38342HF 社区推荐

Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?

Huangfei Jiang, Anning Hu, Kai Sheng, Yuchen Cai, Rui Ge, Xiangyu Kong, Jianghao Lin, Shuzi Chen 等 10 位作者

原文摘要

Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge, research workflows, or forecasting, but evaluating the full research process requires a strictly frozen information set and professional evaluation criteria. We introduce Investor's Last Exam (ILE), an equity-research benchmark led by experienced buy-side investors and fund managers. Its three components are a versioned financial database spanning 3.43 million document versions and nine source categories, supplemented by structured market data, with validated timestamps governing retrieval and computation; a task taxonomy organized around professional analyst deliverables; and an expert-led framework linking scoring criteria to sources, calculations, and assumptions through financial dependency graphs. Evaluation spans 86 assignments and jointly assesses research quality, forecast accuracy, and simulated investment performance. GPT-6 Astra and Claude Opus 5.5 lead overall at 68.1 and 66.9 out of 100, yet even Astra scores only 52.5 on Forecast & Model. Our results show that even state-of-the-art models fail to translate overall research capability into predictive performance. ILE shifts the evaluation unit from isolated capabilities to the evidence--assumption--judgment chain, allowing researchers to locate where analytical advantages fail to translate into forecasts and investment judgments, and providing a traceable, diagnostic foundation for training and evaluating financial agents.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38336

Statutory Article Retrieval from Arabic Judicial Narratives: Family Law and Law of Evidence in Saudi Arabia

Zarah Shibli, Areej Alhothali, Lulwah Alharigy

原文摘要

Reliable legal information retrieval must ground legal reasoning in authoritative statutory sources. In Arabic judicial settings, long factual narratives must be mapped to concise articles that express abstract legal rules, creating a narrative-to-legal-rule abstraction gap. Using a benchmark of 200 synthetic Saudi Arabic judicial cases and 381 articles from the Family Law and the Law of Evidence, we compare word-level and char-4 BM25, zero-shot dense encoders, per-law retrieval, dense-sparse reciprocal rank fusion (RRF), and a proposed Decompose-and-Refine (DaR) pipeline. In DaR, a large language model splits each narrative into disputed legal issues and generates, for each issue, three retrieval channels: a statute-style paraphrase, legal keywords, and a candidate taxonomy chapter. On the whole corpus, the instructed Qwen3-Embedding-8B dense encoder reaches an MRR@10 of 0.849, the best result of any non-decomposed system. Under per-law scoring, this advantage reflects Family Law only: restricted to Evidence articles, the same encoder drops to an MRR@10 of 0.087, and fusion with BM25 raises it only to 0.207. DaR changes this picture, raising Evidence MRR@10 to 0.696 and Family MRR@10 to 0.864. Without decomposition, the two laws favor different strategies; under DaR, the same retriever achieves the best MRR@10 on both.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38332

MUSE: Multi-Level Memory with Selective Runtime Injection for Scientific Coding Agents

Haoran Jin, Defu Lian, Xiting Wang, Hong Xie

原文摘要

Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution. We introduce MUSE, a memory management framework combining multi-level memory with selective runtime injection for scientific coding agents. MUSE builds global, approach-level, and implementation-level memory from historical trajectories. At initialization, the agent receives global memory and problem-matched approach-level memory. During execution, current interactions are used to retrieve implementation-level memory. An LLM gate selects relevant experience and generates specific review advice, or skips injection. Across four benchmarks spanning numerical problem solving, kernel optimization, and scientific software repair, MUSE outperforms retrieval and memory baselines on all evaluation metrics. Ablations support the multi-level design and gated injection, while transfer experiments show that memory remains useful across kernel benchmarks. These results show that multi-level memory and selective runtime injection enable effective reuse of experience in scientific coding. Code is available at https://github.com/hr-jin/MUSE.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38329

A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator

Byonggon Chun

原文摘要

Frontier large language models write correct CUDA kernels for most single-operator benchmark tasks, yet their accuracy collapses on accelerators whose architecture and programming language they have rarely seen. We present a case study of an LLM agent loop built for such accelerators. Our example is the FuriosaAI RNGD NPU, programmed in a recent, sparsely documented Rust DSL, where the loop optimized three Gemma-4-12B decode kernels over 12 days on a shared, scarce device. The loop builds its own target knowledge: it writes and checks a summary of the DSL documentation, measures the chip with microbenchmarks, records compiler-derived legality rules, and revisits this knowledge when the toolchain changes, rechecking rules and measurements where it can. A role-based search over per-kernel Design Trees explores whole-kernel designs and accumulates small accepted changes in the best version of each kernel. Because device time is scarce and readings are noisy, cheap checks screen new designs before any device run, and late in the run a change was accepted only after repeated comparisons with the best kernel on the device. The final kernels reach a 9.293x geomean speedup over the official baseline, each within 1.25x of the cycles needed just to move its weights. Our prompts, profiler and acceptance test are available at https://github.com/bgchun-fs/multi-agent-kernel-gen-loop.

cs.LG · cs.AI · cs.AR · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38326

Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study

Bohui Zhang, Albert Meroño-Peñuela, Elena Simperl

原文摘要

Ontological knowledge underpins large language model (LLM) performance on knowledge-intensive tasks. However, existing evaluations of LLMs' ontological understanding largely rely on behavioral correctness, leaving the underlying mechanisms unexplained. Existing mechanistic interpretability work has largely focused on instance-level factual knowledge, leaving ontological knowledge under-explored. To bridge this gap, we introduce MIOE, a causal-abstraction benchmark that evaluates interchange interventions for two ontology engineering tasks: entity typing and subsumption prediction. MIOE tests whether learned internal intervention targets can change an ontology-level target answer while preserving class-specific auxiliary information. Across Qwen3-8B and Qwen3-4B, we evaluate SAE-, DBM-, and DAS-based methods, including multi-task and multi-layer variants. Distributed subspace methods give the strongest results and generalize across prompt settings, but the induced changes remain only partially separated from auxiliary class-specific information. Multi-task objectives and contiguous layer-window interventions improve this balance, while class-level analyses reveal substantial variation across ontology classes. These results suggest that ontological predictions are mechanistically accessible in LLMs, although current methods do not yet isolate a cleanly disentangled causal mechanism for ontological knowledge.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38319

Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors

Linrui Dai, Jinxiu Liang, Chu Zhou, Mae Yamaguchi, Ryuya Takahashi, Imari Sato

原文摘要

Extremely sparse-view computed tomography (xSV-CT) is critical when scanning time, motion, or radiation tolerance limits each scan to only a few projections. In many such scenarios, the same acquisition limits also constrain dataset construction, making pre-reconstructed 3D volumes from dense scans unavailable. This exposes a gap in current sparse-view approaches: Optimization-based methods, which use the sparse measurements directly but lack data-driven priors to suppress artifacts, and learning-based methods, which use strong priors but usually require densely scanned training volumes acquired outside the xSV-CT regime. We study this train-sparse / infer-sparse setting by learning a pose-aware diffusion prior from one 2D projection per training sample, then guiding diffusion sampling with measured-view fidelity, shared-volume reprojection, and projection-physics consistency for tomographic reconstruction. On two public CT datasets across 1-, 4-, and 8-view settings, the proposed method achieves the best novel-view synthesis scores and best or competitive reconstruction quality compared with baselines that use dense-volume supervision.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗