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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 14:26 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 14:37 — 2026-11-09 14:37（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 14:26最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 3,653 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 14:25（北京时间）
版本更新 · v4arXiv:2407.18454

Fairness Definitions in Language Models Explained

Zhipeng Yin, Zichong Wang, Avash Palikhe, Wenbin Zhang

原文摘要

Language Models (LMs) have demonstrated exceptional performance across various Natural Language Processing (NLP) tasks. Despite these advancements, LMs can inherit and amplify societal biases related to sensitive attributes such as gender and race, limiting their adoption in real-world applications. Therefore, fairness has been extensively explored in LMs, leading to the proposal of various fairness notions. However, the lack of clear agreement on which fairness definition to apply in specific contexts and the complexity of understanding the distinctions between these definitions can create confusion and impede further progress. To this end, this paper proposes a systematic survey that clarifies the definitions of fairness as they apply to LMs. Specifically, we begin with a brief introduction to LMs and fairness in LMs, followed by a comprehensive, up-to-date overview of existing fairness notions in LMs and the introduction of a novel taxonomy that categorizes these concepts based on their transformer architecture: encoder-only, decoder-only, and encoder-decoder LMs. We further illustrate each definition through experiments, showcasing their practical implications and outcomes. Finally, we discuss current research challenges and open questions, aiming to foster innovative ideas and advance the field. The repository is publicly available online at https://github.com/vanbanTruong/Fairness-in-Large-Language-Models/tree/main/definitions.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.22976

LLM Code Smells: A Taxonomy and Detection Approach

Zacharie Chenail-Larcher, Brahim Mahmoudi, Naouel Moha, Quentin Stiévenart, Florent Avellaneda

原文摘要

Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and ability to simulate human reasoning to some extent. However, poor integration of LLM inference in source code can undermine software system quality. Therefore, inadequate LLM integration coding practices must be documented to help developers mitigate such issues. Following our earlier work on LLM code smells, this paper consolidates and refines the concept by presenting a self-contained taxonomy and a catalog of nine LLM code smells. We also create SpecDetect4LLM, a static source code analysis tool for their detection, and conduct extensive empirical evaluations of its detection effectiveness (precision and recall) as well as the prevalence of LLM code smells across 692 open-source software projects (171,194 source files). Our results show that LLM code smells affect 73.5% of the analyzed systems, with a detection precision of 91.3% and a recall of 71.8%.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36250

cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation

Philip Huang, Fabio Ramos, Jiaoyang Li, Caelan Garrett, Lars Johannsmeier

原文摘要

Multi-arm manipulation has the potential to dramatically improve the throughput, efficiency, and dexterity of many manipulation tasks. Recent work coordinates multiple robot arms in a shared workcell by allocating and scheduling tasks for greater parallelism, jointly planning multi-arm motions, or directly learning multi-arm policies. So far, these approaches are either too slow, rely on domain-specific assumptions, or scale poorly with the number of robots and task horizon. Thus, we introduce cuArms, a conflict-based planner co-designed with GPU parallelism that efficiently decomposes the search space using reusable multi-modal roadmaps for individual robots and resolves conflicts and deadlocks through a lazy search. To jointly optimize task assignment, schedules, motions, and manipulation skills, we integrate a high-level scheduler that proposes candidate skeletons for cuArms to ground into coordinated manipulation plans. Experimental results show that our method establishes a new state of the art, with real-time initial solutions and anytime improvements in both motion quality and scheduling, without days of domain-specific training required by learning approaches. Videos of both simulated and real-world industrial tasks are available on https://cuarms.github.io/.

cs.RO · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36247

Freeze, Don't Clone: Fine-Tuning with Expressive Policies Without Retaining Offline Data

Sami Nur Islam, Johan Obando-Ceron, Doina Precup, Aaron Courville, Pablo Samuel Castro

原文摘要

Offline-to-online reinforcement learning uses offline pretraining to accelerate subsequent online learning. While many methods assume the offline dataset remains available throughout fine-tuning, there are many settings where this is not the case. Prior work attributes failures in this setting primarily to critic recalibration under distribution shift. We identify a complementary actor-side failure: once the offline data disappears, continued behavioral cloning (BC) no longer preserves the offline behavior distribution and instead refits the behavioral model to the agent's limited, and nonstationary, online experience. We demonstrate that stopping online behavioral fitting while preserving the pretrained expressive prior substantially improves no-retention fine-tuning across implicit flow Q-learning (IFQL), flow Q-learning (FQL), and action-chunked RL (QC) on seven OGBench domains. We trace this failure to a behavioral feedback loop: continuing online behavioral cloning rapidly erases the pretrained prior, inducing representational collapse and action diversity loss that starves the critic of useful exploration. Freezing the prior breaks this cycle, preserving offline coverage while allowing value learning to drive continuous improvement.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36239

BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals

Aysenur Inan, Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Selene Xu, Kaushiki Nag, Jianpeng Xu, Sushant Kumar

原文摘要

Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term history and community signals is universally beneficial, we study when it actually helps. We propose BehaveRec, a three-signal framework combining a causal session transformer, a bidirectional User History Encoder over a 90-day window, and a GraphSAGE module over a user-user graph built from behavioral embedding similarity rather than item co-occurrence; a learned gate blends the three signals per user. On an industrial dataset of 137M sequences from 12.6M users, BehaveRec improves R@5 by +3.2% over SASRec, with a larger-capacity SASRec baseline (more parameters than BehaveRec) still trailing by +2.5%, ruling out capacity as the explanation. More importantly, a user-level stratification by history length reveals a clear dose-response relationship: BehaveRec's advantage is negligible below roughly 10 interactions and grows monotonically with history richness, reaching +0.017 R@5 for users with 101+ events. This pattern is corroborated across one industrial and three public datasets spanning history-rich to history-sparse regimes, where session-only models remain preferable. These headline results, and the resulting deployment threshold, are established for category-level intent prediction; a preliminary, single-run check on the full item-level vocabulary yields a directionally mixed result and is scoped as an open question rather than a claim. We use these results to derive a practical deployment rule -- roughly 20 interactions per user -- for when long-term history and behavioral-graph signals are worth their added complexity. Despite this added complexity, BehaveRec remains lightweight: it uses 5.67M parameters and trains on a single GPU in under two days.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36234

MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge

Jannatul Shefa, Alejandro Salado, Paul Wach, Taylan G. Topcu

原文摘要

Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes. Although large language models (LLMs) are promising for requirement quality assessment, prior work shows that off-the-shelf models miss a large share of expert-identified defects, perform unevenly across quality criteria, and vary across executions. This study investigates whether infusing expert-derived SE knowledge can improve LLM-based requirement quality evaluation beyond off-the-shelf capability. We present MARQ, a modular, LLM-agnostic prototype that supplements LLMs with a criterion-specific knowledge stack operationalizing INCOSE requirement quality criteria and evaluated against off-the-shelf baselines on an expert-labeled NASA requirement set using Claude Opus 5, GPT-5.6 Sol, and the open-weight Gemma 3 12B, with 100 executions per model. MARQ achieves median F1 scores of 0.80 for Claude Opus 5, 0.62 for GPT-5.6 Sol, and 0.53 for Gemma 3 12B, compared with off-the-shelf baselines of 0.55, 0.52, and 0.18, respectively. However, the nature of these gains is model-dependent. Claude Opus 5 improves defect detection and false-alarm control; GPT-5.6 Sol gains detection and better execution-level consistency at the cost of more false alarms; and Gemma 3 12B reaches the performance of off-the-shelf proprietary models, although it remains highly variable. Criterion-level analysis shows gains concentrated in Correctness and Conformance, trade-offs between misses and false alarms within individual criteria, and model-dependent responses across several criteria. These findings position SE knowledge infusion as a promising model-agnostic pathway for strengthening trustworthy LLM-based RE support while underscoring the need for criterion-specific interventions and human-in-the-loop review.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36229

Agent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures

Kosei Horikawa, Hao Li, Yutaro Kashiwa, Youssef Esseddiq Ouatiti, Mohammed Sayagh, Bram Adams, Hajimu Iida, Ahmed E. Hassan

原文摘要

AI coding agents such as Claude Code, GitHub Copilot coding agent, and Cursor now commit directly to open-source repositories. Empirical studies of these agents identify their commits through authorship signatures, such as bot accounts and Co-authored-by trailers. These signatures are optional, can be removed, and are often attached to pull requests rather than to individual commits. Hence, it is unclear whether Agent commits can be told apart from Human commits once the signatures are gone. We investigate the signals and limits of signature-free detection using 7,837,946 commits from 1,226 repositories, covering five coding agents and Human commits. After signatures are masked, detectors rank Agent commits above Human commits with a ROC AUC of up to 0.859, and most of this signal comes from message verbosity and change size rather than from the code itself. On the shared sample, gpt-6-sol without fine-tuning reaches AUCs similar to XGBoost and TF-IDF. At the observed Agent share, however, the best detector on the full test set reaches a precision of only 0.332. Detection transfers poorly to held-out Claude Code and Copilot, with TF-IDF reaching an AUC of only 0.524 for Claude Code. Temporal changes also depend on the agent, e.g., Copilot AUC drops and later recovers, while more training history helps Claude Code but not Copilot. These results indicate that signature-free detection can prioritize commits for review but cannot replace recorded attribution, and that studies relying on signature-based labels should treat them as a lower bound on agent activity.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36227

Directional Statistics on Circles and Spheres: A New Angle on Data

Siddhesh Kulkarni

原文摘要

Two compass bearings near north can have an ordinary arithmetic mean pointing south: the difficulty is that angles live on a circle, not a straight line. Using real wind observations, diffusion-MRI orientations, and geometric examples from machine learning, this article introduces circular and axial averages, directional variability, and probability models on circles and spheres. The guiding principle is to identify the geometry and symmetries of the observations before choosing a statistical method.

stat.ME · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36226

Structure, Not Sequence: Tracking and Validating Folding Mechanisms in ESMFold's Trunk with Sparse Autoencoders

Bohan Liu, Xiaohan Fan, Wenqian Ye, Aidong Zhang

原文摘要

Structure predictors like ESMFold fold proteins using neural network computation and have transformed structural biology. However, the driving mechanism from amino-acid (AA) sequence to 3D structure is insufficiently understood, and biological meaning remains locked in the dense network. Sparse autoencoders (SAEs) have shown promising results in obtaining interpretable concept features over an overcomplete basis of intermediate protein sequence-model representations. Yet folding models, which predict physical shape from AA sequence semantics, have no such account. We hypothesize that the features carrying the folding computation evolve in the 3D structural regression process. In this paper, we interpret the folding trunk in three steps. First, a pilot analysis on the representation distribution across modules and recycles locates distinct spatial computation in the trunk. Second, the dictionaries expose a division of labor: the single representation carries inherited semantics, and the pair representation computes the pairwise geometry. Third, we interpret the dictionary at scale with a reasoning language model, trace how the concepts compose across blocks by gradient-based attribution, and follow the interpreted code to the model's folding output, verifying where the computation aligns with, or departs from, known biochemistry. Together, the sparse dictionaries we train capture the relational geometry the trunk computes beyond the sequence model, and their concept activations forecast the model's own fold quality, turning the black-box folding trunk into a sparse, interpretable, and scientifically verifiable circuit.

q-bio.QM · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.19698

Data-Driven Maintenance Optimization: Aligning Prognostic Learning with Decision Objective

Zhuojun Xie, Adam Abdin, Yiping Fang

原文摘要

Estimation error in machine learning prognostic models can propagate into poor maintenance decisions. We study a data-driven predictive maintenance problem coupling health-condition estimation with a joint ordering-replacement model. We show that the conventional Estimate-Then-Optimize (ETO) approach yields inconsistent, suboptimal decisions for a broad class of such problems. To bridge the gap, we propose an Integrated Estimate-Optimize (IEO) framework that directly targets maintenance cost as the prognostic learning objective, bypassing surrogate statistical accuracy metrics such as Kullback--Leibler divergence or mean squared error. Theoretically, we prove out-of-sample performance guarantees of the IEO framework under certain conditions, including i.i.d. and sliding-window data-generating processes. Computationally, we develop a training procedure combining Monte Carlo dropout, central-difference gradient approximation, and an ETO warm-start to handle discrete maintenance decisions and nonlinear costs. Experiments on the four CMAPSS subsets demonstrate that, under the nominal setting, IEO reduces mean maintenance cost by 14.8--22.7% relative to ETO and by 7.2--11.8% relative to a decision-oriented baseline, while also reducing failure rates and cost variation. These improvements are obtained despite higher prediction errors. Increasing the ratio of unplanned-downtime costs to planned-downtime costs makes this tradeoff more pronounced: IEO shifts predictions further toward RUL underestimation, accompanied by greater cost savings and fewer failures. These findings support aligning prognostic learning with maintenance objectives when imperfect predictions must guide decisions under costly unplanned downtime.

cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.23018

AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI

Mohammad Sadegh Salehi, Alexander J. P. Perkins, Igor Pardo Maurell, Ashkan Dabbagh, Raymond Wong

原文摘要

Web-scale 3D asset collections are abundant but rarely ready to ingest without cleanup, suffering from arbitrary metric scaling, incorrect pivots, brittle geometry, and incomplete textures, defects that limit their use in embodied AI, robotics, and spatial computing. We present AmaraSpatial-10K, a dataset of 10,071 synthetic 3D assets standardised for direct ingestion. Each asset ships as a metric-scaled, deterministically anchored .glb with separated PBR maps, a convex collision hull, a paired reference image, and multi-sentence text metadata. Alongside the dataset we introduce a reusable evaluation suite for 3D asset banks, a continuous Scale Plausibility Score (SPS), a keyword-based Concept Density metric, anchor-error auditing, and a cross-modal CLIP coherence protocol, and apply it to AmaraSpatial-10K alongside matched subsets of Objaverse, HSSD, ABO, and GSO. We check the annotations independently of the LLM/VLM pipeline that produced them: measured ABO object heights fall inside our scale intervals 88.7-90.7% of the time, and three non-author raters auditing a stratified sample of 314 assets judge 95.5% plausibly scaled and 99.7% correctly anchored. AmaraSpatial-10K improves CLIP Recall@5 by 3.4x over Objaverse (0.612 vs. 0.181, median rank 267 -> 3), achieves a 99.1% settling-stability rate under Habitat-Sim in static placement and collision tests, with ~20x lower per-load wall time, and as a drop-in Holodeck asset bank improves planned-scale matching and is preferred by blinded human raters in 27 of 40 paired scenes. Controlled ablations on the same asset bank attribute the retrieval gain to description richness.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36208

Counterfactual Profile Perturbations for Recommendation Explanations: A Reproducibility Study

Meysam Varasteh, Elizabeth McKinnie, Robin Burke

原文摘要

This reproducibility paper explores the counterfactual explanation technique known as Learning to eXplain Recommendations (LXR). Prior work has shown that LXR can reliably identify perturbations that, if applied to a user's profile, cause the user's top ranked item to no longer be recommended, thereby explaining the item's recommendation as a function of the user's rating choices. In this paper, we extend this work in multiple ways. We expand the scope of the original LXR study to look at explanations for items other than the most highly recommended item, finding that LXR is also effective at this version of the task. We consider alternate baselines for LXR, including item popularity and latent factor similarity, and we see that for some tasks these alternatives work surprisingly well. We also examine the impact of item popularity, finding that LXR offers better explanation quality (shorter perturbations) when less popular items are being explained. Finally, we conduct a brute-force exploration of a subset of the perturbation space in order to estimate a lower bound for optimal perturbation size against which LXR and other such methods can be compared.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2601.03222

The Fake Friend Dilemma: Relational Trust and the Political Economy of Conversational AI

Jacob Erickson

原文摘要

As conversational AI systems become a larger part of the media landscape, they raise questions about whose interests they serve and the risks they may pose to users. These systems do more than provide information: they increasingly offer advice and companionship through interfaces that can appear supportive and socially responsive. A pressing concern is that users may form perceived social relationships with these systems and place relational trust in them, even when the interests shaping interactions do not fully align with their own. The Fake Friend Dilemma (FFD) describes the problem that follows: the same relational trust that makes conversational AI useful can also leave users open to manipulation and exploitation when institutional interests conflict with their own. Drawing on work on relational trust, AI alignment, extractive design, and the political economy of communication, the paper considers how the FFD can manifest through product sales, propaganda and biased information, surveillance, and behavioral nudging. It also considers possible structural and technical mitigation strategies. The FFD is not simply about AI misleading users. The problem it surfaces is that the trust people place in these systems can itself become a resource for institutional actors seeking to influence behavior or extract information. The FFD is therefore as much a problem of media governance and political economy as it is a technological one.

cs.CY · cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36204

Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization

Ege Demirci, Ambuj Singh

原文摘要

Link prediction remains difficult in sparse graphs, where diffusion heuristics lack connectivity and geometric methods suffer spectral instability when coupling learned representations with diffusion operators. We introduce Concorde, an energy-based framework that resolves this by decomposing link likelihood into three structurally decoupled branches: (i) a parameter-free spectral anchor that establishes permutation-invariant topological stability; (ii) a mixed-curvature residual on a learnable $\mathbb{H}^{d_h}_{c_h} \times \mathbb{S}^{d_s}_{c_s}$ product manifold, regularized by a feature-aware Ollivier-Ricci curvature proxy; and (iii) a continuous vector field on the tangent bundle of hyperbolic space for non-local structural alignment across topological gaps. The branches are fused via learned gating and trained with an N-pair ranking loss aligned with retrieval-style evaluation. Across five benchmarks spanning sparse, dense, featureless, and attributed regimes, Concorde establishes state-of-the-art early retrieval precision, nearly doubling P@10% over leading baselines in sparse settings.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36202

Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss

Oz Amram

原文摘要

The Persona Selection Model (PSM) posits that post-training selects a persona the model learned during pre-training. Work on subliminal learning has shown that models can impart covert signals (like "love of owls") into semantically unrelated outputs like strings of numbers, and that students trained on these outputs inherit those traits. In this work I show that by evaluating the likelihood of such outputs under the base pre-trained model with an appropriate header, a method I call persona-header likelihood evaluation (PHLE), one can decode these subliminal signals and classify between them. For example, PHLE distinguishes number sequences generated by a post-trained model prompted with "You love owls" from those prompted with "You love eagles", and distinguishes answers from a model with a secret desire to harm the user, filtered to remove any noticeable misalignment, from those of a model with no system prompt. In both cases prompted classifiers, including the generating model itself, remain near chance. The signal partially persists across model families, with the Qwen base model reading signals generated by Olmo and vice versa. This is evidence for a non-trivial prediction of the PSM, and the method may be practically useful for auditing the hidden objectives of models.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.15113

Legislating World-Model-Based Planning with Legal Reasoning

Dylan Waldner, Yiannis Kantaros, Guido Governatori, Risto Miikkulainen, Amir Banifatemi

原文摘要

As robotic systems grow more general, legal norms are needed to integrate them into society. This paper extends the isomorphism problem of aligning legal source texts with their encodings, and measures two key challenges to robot normative control: (1) the grounding isomorphism gap, where perception error grounds false atoms for legal reasoning, and (2) the ontological isomorphism gap, where one legal conclusion admits many faithful translations into planning constraints. The paper introduces a legal planning stack that employs Defeasible Deontic Logic (DDL) to constrain a motion planner. The stack leverages learned world models to plan and to provide legal context, enabling ex ante governance that intervenes before an illegal action is executed. It was deployed on a simulated robot arm pushing a cube across a 3x3 grid. The findings were (1) the legislated agent abided substantially more often than the non-legislated one, and modeling perception uncertainty lifted abidance even further, (2) the legal reasoning ran efficiently at runtime and its verdicts were auditable, and (3) the stack adapted to exogenous signals and endogenous rule changes. Both gaps were measured: (4) world model and probe error corrupted the factual input for the DDL reasoner, and (5) a single law admitted several faithful metric interpretations yielding drastically different abidance. Thus, ex ante legislation functions as intended, and closing these gaps with a standardized mapping from the law to runtime constraints and improved fact grounding from perception will yield robust laws that align robot behavior with society's norms. Project page: https://dylanwaldner-cail.github.io/Legislated-Planner/.

cs.RO · cs.AI · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36196

count-catcher: Lean Theorems from Model Counting Certificates

Johannes K. Fichte, Stefan Szeider

原文摘要

We present count-catcher, a tool that turns a CPOG certificate of a count by the exact model counter d4 into a Lean theorem that a CNF formula defined in Lean has exactly N models over V variables. With an encoding lemma, this theorem becomes a theorem about the number of combinatorial objects. A CPOG certificate consists of a Boolean circuit equivalent to the formula and a proof of equivalence. count-catcher checks in Lean that the formula implies the circuit (forward check) and the circuit implies the formula (reverse check). For the forward check, lrat-catcher streams a refutation through the LRAT checker of Lean's standard library. The reverse check and the validity check of the circuit are computations proved correct in Lean. Lean runs all three checks as compiled code, so the theorem depends on Lean's kernel, compiler and runtime, as does CPOG's verified checker. We combine the theorem with results from Mathlib, for instance with Burnside's lemma to count graphs up to isomorphism. We prove the number of Latin squares of order 8 as a weighted sum of hundreds of certified counts from about eight terabytes of certificates. We turn about half of the 2022 Model Counting Competition formulas into theorems, with the three checks taking about a quarter of the time of CPOG's verified checker. We found that CPOG's unverified checker reported wrong counts, and removed its verified checker's dependence on two unproved lemmas. End to end, a theorem costs about the same as a checked count.

cs.LO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.08634

Suan: Rectifying Direct Preference Safety Alignment in Large Language Models

Oleksandr Cherednichenko, Roman Klypa

原文摘要

Integrating robust safety guardrails into Large Language Models (LLMs) is essential for delivering helpful yet harmless responses. While proprietary systems exhibit reliable safety controls, their underlying methodologies and trade-offs remain largely undisclosed. Achieving comparable security in open-weight models remains a persistent challenge, as post-trained variants frequently suffer from over-refusal and degraded general quality. To overcome these drawbacks, we introduce Suan, a novel preference optimization algorithm. Unlike existing methods, we formulate the optimization objective directly at the gradient level, bypassing the standard variational derivation. As a result, we obtain more interpretable and robust training dynamics. Extensive evaluations across a diverse suite of competitive baselines and benchmarks demonstrate that Suan achieves superior safety alignment while fully preserving response utility.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36192HF 社区推荐

Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models

Ziqiao Wang, Yang You

原文摘要

Learning velocity fields directly in pixel space is difficult and slow. We show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with gains extending beyond the linear predictions they explicitly provide. Moreover, we observe similar but complementary gains from frozen bases and pixel decoding. These observations motivate Wiener-informed Decoding (WiD), which uses statistical knowledge both for direct prediction and to organize decoder computation without modifying native blocks. WiD combines a trainable Wiener prediction path with coefficient interfaces that inject features into the native decoder and return its predicted coefficient corrections, with these components initialized with data statistics. All introduced parameters, including the spectrum and coordinate transforms, are trained jointly under the original pixel-space velocity objective. Across model scales and decoder architectures, WiD accelerates training and improves generation quality with modest parameter overhead. It also yields smoother gradient trajectories and remains effective with representation alignment. WiD improves class-conditional and text-to-image generation across different resolutions. On ImageNet 256 x 256, PixelDiT-XL with WiD reaches FID 1.53 after 500 epochs, achieving comparable quality to PixelDiT with 37.5% fewer training epochs. Statistical denoisers contribute beyond the estimate: their computational structure can also ease pixel-space training.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36188

Skill Dreaming: Evolving Repository Skills through Pull Request Streams

Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao

原文摘要

Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolution. To enable this co-evolution of PRs, repositories, and skills, we propose Skill Dreaming, a framework that learns from PR streams to guide continuous repository development and maintenance. Given a repository and its PR history, Skill Dreaming builds a repository-specific skill library by extracting executable knowledge from validated PRs and continuously refines the skills as new PR information becomes available. These skills guide coding agents not only in implementing requested features but also in maintaining associated tests, documentation, compatibility, and repository conventions. By integrating PR analysis, skill management, code execution, and continuous integration, Skill Dreaming provides an end-to-end workflow for applying learned skills to repository changes and incorporating subsequent PR outcomes into future skill updates.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.15796

DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

Artyom Mazur, Nina Konovalova, Aibek Alanov

原文摘要

While transcoder-based circuit tracing has recently enabled detailed causal analyses of large language models, it remains unclear how semantic information propagates across denoising steps and how text and image representations interact within multimodal diffusion transformers (MM-DiT) for image generation. Attention maps expose only a limited view of token interactions, and sparse autoencoders find interpretable features but do not reveal how nonlinear MLP layers transform and compose them. In this work, we extend transcoder-based circuit tracing to multimodal diffusion transformers. We train timestep-conditioned transcoders that faithfully approximate the input-output behavior of the MLP sublayers in the double-stream blocks of FLUX.1[schnell]. By replacing MLPs with transcoders and linearizing the remaining computation, we obtain exact feature-to-feature attribution and build compact attribution graphs over interpretable features. Empirically, our transcoders match or slightly outperform sparse autoencoders on the sparsity-faithfulness tradeoff. The graphs recover the known shift from prompt-driven to image-driven computation across denoising steps, point to candidate mechanisms of attribute binding and cross-stream semantic propagation, and yield intervention-testable explanations for systematic generation errors. On prompt grids labeled blind, graph-guided interventions reach effects that single-feature steering does not; at a matched budget, features chosen from the graph fix a color prior more often than the target feature alone and destroy the object less often than features chosen by co-activation. FLUX.1[dev] reproduces the temporal and color-prior results, and SD3.5-medium reproduces them in direction. Our results demonstrate that transcoder-based circuit analysis is feasible for state-of-the-art multimodal diffusion transformers.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2608.06621

NxN E-valuation: Hypothesis Certification via a Conformal CRT Null

Bin Wang, Yan Zhong, Zhengyu Zhang, Liang Luo, Buyun Zhang, Ellie Wen

原文摘要

Language models now propose hypotheses faster than anyone can check them, so the step that certifies them must need nothing from the proposer but the hypothesis. We state three requirements for such a step -- per-hypothesis automatable, attributable and diagnostic -- and introduce NxN e-valuation, which meets them. A hypothesis names a scope, the units it is about, and gives each of them a restriction that scores its outcome. The units of one scope serve as nulls for one another, so no resampling model is written per hypothesis; the algorithm certifies a stable, scope-level association and reports whether the scope, the restriction, or which unit receives which restriction carries the prediction. For independently drawn units, betting e-values bound the chance of a false certificate for each hypothesis in finite samples, under stated nulls. A betting lower bound on the share of units that carry the association gates every certificate, and an asymptotically valid equivalence test calls the restrictions shared only when it rejects differences between them above a declared noise ceiling. We test it on planted data, on randomized intervention data, and on real purchase data with 285 hypotheses that language models wrote without knowing our method or our classes, labeled by human experts. Meeting all three requirements costs no accuracy: NxN makes 692 correct decisions in 693 with one false certificate, against 659 with four for a composite of CRT tests that returns our verdicts but needs a resampling model per hypothesis, and 224 with 468 for held-out validation. Removing any of our statistics merges a verdict that certifies with one that rejects. The certificates concern predictive association, not causality.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36185

Can AI Guide Testing Without Generating Tests? A Comparative Study of AI-Assisted Unit Testing

Zihan Fang, Ron Asoulin-Handelman, Helen Wu, Yu Huang, Gina R. Bai

原文摘要

Recent advances in generative AI have enabled assistants to generate increasingly sophisticated executable unit tests. However, novices may accept these outputs without independently identifying what to test, evaluating test-suite completeness, or verifying correctness, potentially limiting opportunities to develop essential testing skills. Although prior work has explored AI-assisted test generation and feedback-oriented programming tutors, little is known about whether AI can support novices' testing practices without generating tests for them. To investigate this, we introduce TestCompass, a generative AI tutor that provides targeted feedback on weaknesses in students' test suites without generating executable tests. In a classroom study with 18 students, we compared TestCompass with a general AI assistant across two Java unit-testing tasks, examining students' testing behaviors, test-suite quality, and subjective experiences. We found that participants using the general-purpose AI assistant produced more tests, whereas TestCompass participants spent more time developing and verifying tests themselves. However, most test-suite quality measures were comparable between conditions, and TestCompass participants achieved similar requirement coverage with significantly fewer test methods ($p=0.012$) in one task. Neither group reported short-term improvements in perceived testing knowledge or confidence. These findings suggest that feedback-oriented AI can support meaningful testing outcomes while preserving opportunities for hands-on testing practice, offering a complementary approach to AI-assisted testing education.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36183

Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data

Marc Gutiérrez-Pérez, Antonio Agudo

原文摘要

We study time-to-arrival (TTA) in sports: the shortest plausible time a player needs to reach an arbitrary location on the pitch given their current kinematic state, estimated as the lower envelope of observed locomotion times. Rather than modeling space ownership through position density estimation or closed-form physics-based models, we cast TTA as a conditional quantile regression problem, estimating the lower quantile of locomotion time so the model learns a player's lower-envelope arrival time. We train the model on optical tracking data from all 64 matches of the PFF FC FIFA World Cup 2022 dataset, and evaluate a lightweight multilayer perceptron against six player-motion models from the literature, re-expressed as TTA predictors, and a learned reachable- hull baseline. Across our evaluation metrics, the MLP consistently outperforms every physics-based baseline. To probe the generality of the learned locomotion model, we further evaluate it on basketball tracking data and a single-game NFL tracking dataset, analyzing the transferability of player motion dynamics across sports. Our project is available at https://github.com/mguti97/TTA-Quantile.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36169

Don't Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule

Minh Pham Van, Cong Tran

原文摘要

A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model's memory. Each rule is confidently wrong in some deployment. In a decision-theoretic model of two sources, the score of any fixed rule is linear in the share of reliable contexts while the best attainable score is convex, so every fixed rule is beaten wherever it is not exactly optimal; and a symmetric divergence between the two sources, the signal adaptive decoding uses, carries no information about which one is right. Resolving a conflict therefore needs two inputs that no existing method keeps: evidence about each source separately, and a prior on how often the context is right. We test these claims on GRACE, a benchmark that intervenes on the knowledge-graph context of a fixed question, so that what the model knows, what the context says and what is true are measured separately. There, every baseline from four families is strong on right contexts or on wrong ones, never on both. We then build the two inputs: the model states its knowledge as notes, a small policy voices each note with a calibrated confidence, a reader answers in two voices, and a selector commits or abstains under a prior $π$ applied as an exact prior shift. With $π$ set to the true share of right contexts, the system is above the best baseline at every mixture of GRACE contexts, by up to 26 points. Its overall score is 45.3 and 35.0 (Qwen3.5-35B-A3B, Llama-3.1-8B), against 29.4 and 27.5 for the best baseline. On preregistered ClashEval it beats same-backbone CK-PLUG and TCR by 12 and 26 points. Where the model lacks the knowledge, the gains vanish, as the theory predicts.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.21819

Ctrl-A: Control-Driven Machine Learning using Adaptive Online Data Augmentation

Jesper B. Christensen, Ciaran Bench, Spencer A. Thomas, Hüsnü Aslan, David Balslev-Harder, Nadia A. S. Smith, Alessandra Manzin

原文摘要

We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually, adapted during training based on a control-loop architecture and what we define as relative operation response curves. Using an operation-dependent update procedure provides Ctrl-A with the potential to reduce the use of augmentation operations that negatively impact model performance, alleviating the need to manually engineer augmentation policies for new image classification tasks. Experiments on the CIFAR-10, CIFAR-100, SVHN-core, and Tiny ImageNet benchmark datasets using WideResNet-28-10 and ResNet architectures demonstrate that Ctrl-A provides competitive performance across a range of image classification benchmarks.

cs.CV · cs.AI · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.24816

First-Order LoRA Training with Phone NPUs

Xu Zheng, Wei Cheng, Zhuomin Chen, Dongkuan Xu, Mo Sha, Jingchao Ni, Dongsheng Luo

原文摘要

On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable parameters, but each first-order training step still multiplies by the frozen base-model weights during the forward pass, activation recomputation, and input-gradient computation. A phone's neural processing unit (NPU) already holds these weights for inference; using it for training also requires computing input gradients, which its inference interface does not support. We present a system that runs all three frozen-weight products on the NPU while keeping the training graph, adapters, and optimizer on the CPU. Its input-gradient kernels reuse the resident weight tiles and the forward dequantizer, avoiding a transposed weight copy and ensuring forward and backward use the same effective weights. To preserve usable gradients, the system selects precision by gradient sensitivity and applies a per-row range guard for half-precision (FP16) outputs. Its runtime fuses the remaining CPU operators and overlaps NPU execution with adapter computation, while resumable execution and thermal pacing let training proceed as a background job. We evaluate it on two Qualcomm Snapdragon platforms using four LLMs from the Qwen and Llama families. Our workloads cover nightly personalization with labels supplied on the phone and the public LaMP-2 benchmark; comparisons include an optimized CPU trainer, a phone-GPU trainer, forward-only training, and GPU-trained references.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36153

Stratum: Repository Memory for Coding Agents Beyond the Context Window

Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-Jivan

原文摘要

Context windows have grown a thousand-fold, yet coding agents still start every session with no memory of their past work. They re-read files, retry failed approaches, and forget root causes they established hours earlier. This is not a context-length problem but a memory-architecture problem. Our hypothesis: coding agents need persistent, experience-aware repository memory, so that knowledge survives from one session to the next. Three measurements on real repositories motivate the design. First, mid-size projects already exceed the largest production context windows, and storing knowledge inside the model's key-value (KV) cache costs $10^4$ to $10^5$ times more bytes than storing it as indexed text. Second, across 752 real bug-fix commits, the median fix edits two files, and these files plus their direct imports amount to less than 10% of the repository; the bottleneck is selection, not capacity. Third, even with transitive import reachability and test links, 47% of co-edited file pairs remain structurally disconnected; the knowledge needed for selection must be mined from history and experience. We sketch Stratum, a tiered memory that lives with the repository and serves it through page-safe tools: every response states what was returned, what remains, and what it cost. Retrieval over a store of one million nodes takes 1.7 ms at the median. In a multi-session experiment on eight real bugs, a fresh agent that inherited a prior session's memory, written by a different model, identified the root-cause file in 21 of 24 trials versus 6 of 24 for a retrieval-only baseline (Fisher $p<10^{-4}$), at 4.5x lower median token cost. With the notes of all eight investigations pooled in one store, success remained 8/8.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36151

Replication or Corroboration? An Axiomatic Framework for Evidential Dependence in Multi-Agent Debate

Hoang-Loc Cao, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Vo Thanh Khang Nguyen, Phuc Ho, Hung Nguyen, Duc Pham, Long Tran-Thanh 等 9 位作者

原文摘要

In multi-agent debates, matching reports can arise for two different reasons: agents may repeat the same evidence (replication), or they may provide separate evidential roots that support the same claim (corroboration). A judge must distinguish these two cases. Counting report occurrences gives extra weight to relays, paraphrases, alias resubmissions, and excerpt splits, while merging all matching content avoids this only by also removing genuine corroboration. We formalize this tension as a minimal judgment game in which acquiring new evidence is costly, but replication is cheap. We show that root replication invariance (RRI) is exactly threshold-uniform replication immunity. Under RRI, replication-only deviations cannot change the verdict, and positive-cost replication is strictly dominated, whereas occurrence-sensitive and content-keyed judges admit profitable deviations. We also establish an information boundary: if a judge's observation interface cannot distinguish a replica from a matched fresh root, no judge can both ignore the replica and respond strictly to the fresh root. To preserve this distinction, we introduce the lineage quotient, which removes wording, identity, occurrence multiplicity, and arbitrary root names while keeping distinct roots separate. On orbit-connected domains, it is the coarsest representation sufficient for every deterministic judge invariant to replication and root-label renaming. We further lift this construction to quantitative bipolar argumentation frameworks (QBAFs), characterize strict fresh-root response, prove its propagation along sign-consistent paths under DF-QuAD, and derive a tight closed-form response modulus. Exhaustive audits over 28,224 direct-star profiles, 2,052 multi-layer DAGs, with matched interventions on 277 AVeriTeC-derived profiles, show the predicted separation between replication and corroboration under a supplied partition.

cs.MA · cs.AI · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36146

From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors

Wentao Ye, Yali Ye, Zhiqing Xiao, Ru Peng, Xinpeng Ti, Liyao Li, Zhanming Shen, Peng Lu 等 10 位作者

原文摘要

Prompt optimization should improve the image a user receives without changing the scene the user requested. Yet stylistic rewriting can weaken object attributes and relations even when global text--image similarity remains high. We propose StruPO, a structure-aware prompt editor that uses a calibrated scene graph as a shared representation for policy conditioning and image-grounded supervision. The graph exposes what should be preserved, while deletion, reordering, and insertion provide a token-aligned way to modify the prompt. This turns structural feedback from an external critique into a training signal for a reusable editing policy. Learning from that signal requires handling both uncertain grounding and stochastic image generation. StruPO retains grounding confidence through smooth reward shaping and averages multiple images for each edit before computing group-relative advantages. Experiments span three disjoint 2K-prompt test sets and four frozen generation backbones, with comparisons to learned prompt optimizers, iterative structural feedback, diffusion-model fine-tuning, and inference-time attention control. StruPO improves the faithfulness--aesthetics trade-off, with consistent gains in relational fidelity. Independent automatic evaluators and a 15-annotator study provide complementary evidence, and human preference margins increase with relation complexity. Controlled ablations connect these gains to graph conditioning, local editing, and image-grounded learning. The resulting policy produces reusable optimized text in one pass after graph calibration, without an iterative critique--rewrite loop.

cs.AI

查看论文
arXiv ↗PDF ↗