跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 04:46 — 2026-11-17 04:46(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:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2605.13716

SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems

Xinyuan Song, Hongji Pu, Liang Zhao

原文摘要

Large language model agents increasingly rely on skill libraries for multi-step tasks, yet these libraries can accumulate persistent defects as skills are added, reused, patched, and linked to changing dependencies. We call this failure mode skill technical debt: library-level defects that may not break a single skill locally but can harm future retrieval, composition, and execution. Existing skill-based agents mainly focus on task-time retrieval, planning, and repair, while library-time maintenance remains underexplored. We propose SkillOps, a method-agnostic plug-in framework for maintaining skill libraries. SkillOps represents each skill as a typed Skill Contract (P, O, A, V, F), organizes skills with a Hierarchical Skill Ecosystem Graph, and diagnoses library health across utility, compatibility, risk, and validation dimensions. Given a raw skill library, SkillOps produces a maintained library that can be used by existing retrieval or planning agents without changing their internal code. On ALFWorld, SkillOps achieves 79.5 percent task success as a standalone agent, outperforming the strongest baseline by 8.8 percentage points with no additional task-time large language model calls. As a plug-in layer, it improves retrieval-heavy baselines by 0.68 to 2.90 percentage points. The current rule-based maintenance implementation uses nearly zero library-time large language model calls or tokens, showing that skill-library maintenance can be added as a low-overhead architectural layer.

cs.SE · cs.MA

版本更新 · v3arXiv:2605.12863

Language-Based Agent Control

Timothy Zhou, Loris D'Antoni, Nadia Polikarpova

原文摘要

This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional programming, combinations of static typing and runtime enforcement have long been used to guarantee that well-typed programs satisfy user-specified policies, including policies for access control, information flow, data provenance, and more. The key idea behind LBAC is to extend these guarantees to agentic applications by requiring agents to generate programs that are themselves well-typed in the context of the surrounding scaffolding code. Unsafe programs are rejected by the typechecker before execution, allowing policies to apply uniformly across the entire application, including both agent-generated behavior and developer-written scaffolding. At the same time, LBAC preserves substantial expressiveness: agents may perform arbitrary side-effect-free computation and recursively invoke subagents, which retain full tool access subject to the same--or potentially more restrictive--policies. We demonstrate LBAC with three case studies: I/O sandboxing via filesystem capabilities, data provenance, and information-flow control.

cs.PL · cs.AI · cs.CR

新论文 · v1arXiv:2611.10397

Regularization Amplifies Subliminal Learning

Lawrence Feng, Jacob Mitchell Springer, Gaurav R. Ghosal, Ziqian Zhong, Aditi Raghunathan

原文摘要

Recent work has shown that hidden biases can be transferred through data with no apparent semantic relationship to those biases. Can regularization limit this covert influence? By constraining adaptation, regularization might be expected to suppress behavioral changes on seemingly unrelated inputs. We systematically study this hypothesis in subliminal learning, as well as in related settings of covert influence, including phantom transfer and logit-linear selection. We find the opposite: regularization amplifies the transfer of hidden biases. In particular, subliminal learning is typically absent under full fine-tuning, but low-rank adaptation or explicit penalties can induce strong transfer. Phantom transfer and logit-linear selection show similar trends. Adding more data, an implicit form of regularization, also strengthens covert influence. Together, these findings suggest that the simplicity biases induced by regularization may facilitate covert influence. We further hypothesize that the level of regularization that maximizes covert transfer depends on task complexity.

cs.LG

版本更新 · v2arXiv:2610.41191

When AI Investigators Cannot Trust Their Tools: Conflict-Aware Evidence Verification for Cyber Threat Investigation

Yuchen Zhang

原文摘要

LLM agents increasingly triage security alerts by combining the outputs of several detection tools, implicitly treating those tools as trustworthy. Unlike prior work on conflicts between a model's knowledge and its context, we study conflicts among the tools themselves: what happens when this machine-generated evidence is conflicting or wrong. On the corrected CIC-IDS2017 dataset, four heterogeneous detectors emit labels and confidences that we corrupt under a threat model varying the number of corrupted tools, the persistence of the corruption, and the confidence attached to wrong outputs. Across open-weight LLMs from 3B to 14B parameters, unverified investigators are fragile: one corrupted detector out of four lowers naive accuracy to .50-.72, three lower every unverified investigator to .13 or less, and honest disagreement alone makes them abstain on up to 63% of flows. We propose Conflict-Aware Evidence Verification (CAV), built from established components: an equal-weight vote that ignores reported confidences, an evidence-conflict gate, and an independent nearest-neighbour trust check that tests the leading candidates. With its prompt frozen before testing, CAV-LLM improves on the naive investigator in every corrupted condition ($p < 0.001$), reaching .84-.88 with three corrupted detectors against at most .08, while calling the LLM on 0.4% of clean traffic. A fixed verification rule is as accurate or better unless most tools are corrupted. When we make the independent channel itself noisy, CAV inherits its errors: it stays ahead when two or more tools are corrupted, but adding the channel as an extra voter is better when at most one is. Verification thus moves trust from the tools to the check, which must be measured and protected in turn.

cs.CR · cs.LG

新论文 · v1arXiv:2611.10395

The Limits of Information-Flow Control Enforcement for Agentic Systems

Jonathan Gregory, Kyle Domico, Kunyang Li, Jean-Charles Noirot Ferrand, Patrick McDaniel

原文摘要

Information-flow control (IFC) is a promising approach to enforce policy in agentic AI systems. However, IFC suffers from label creep, a phenomenon where monotonically increasing security labels propagate through a system and progressively limit its utility. Label creep in agentic AI systems can be mitigated using two major strategies: (1) improved system design and (2) label declassification. In this paper, we characterize how far system design alone can mitigate label creep in agentic systems. Specifically, we measure how system topology, scale, and agent composition affect utility loss and security enforcement cost proxies for conservative IFC enforcement in a stateful agentic system simulator. We develop a pipeline to systematically vary these features and measure their impacts on label propagation. Our results demonstrate strong associations between structural graph features and our IFC utility loss metric (up to a Spearman correlation $|ρ|$ of $0.96$) and show that system size and tool allocation substantially affect how labels propagate. These findings identify design choices to reduce IFC utility loss, but they also demonstrate that system design alone cannot fully prevent utility loss due to monotonic label propagation. This motivates the development of label declassification mechanisms that aid these design choices and diminish IFC utility cost.

cs.CR · cs.AI

新论文 · v1arXiv:2611.10394

Crustify: Repository-Level Generation of Safe Rust Bindings with LLM Agents and Coverage-Guided Testing

Marius Momeu, Marius Arvinte, Cory Cornelius, Koushik Sen

原文摘要

Wrapping C code in a safe Rust interface lets Rust applications use it without writing unsafe code, until the code itself is migrated to Rust. Such bindings are tedious and error-prone to write, however: their internals use unsafe code that the Rust compiler does not check, so a single mistake can introduce undefined behavior (UB), and they have so far been written mostly by hand. We present Crustify, an agentic co-translator that generates safe Rust bindings for repository-level C libraries. Crustify schedules a target's types and symbols into dependency-ordered waves of independent batches that agents bind concurrently. Its agents derive the ownership and lifecycle contract of every pointer and type they wrap, check each binding with coverage-guided equivalence and UB tests under sanitizers and Miri, and review every wave. They build on three tools that we contribute: (a) ffibox, Rust primitives for C/Rust interop that mirror Box, Arc, and Vec for C objects without ever forming a reference to memory that C may alias; (b) Wavefront, a neuro-symbolic static analyzer that orders a target's items by their dependencies, including those that casts and type-erased pointers hide; and (c) ffimap, a rustc-based analysis that maps the unsafe surface of bindings. On libgit2 and ffmpeg, with one developer in the loop, Crustify generated safe bindings for 41.9% and 42.8% of their public APIs in about 51.9 and 58.9 hours. On the interface consumers are expected to use, only 1.6% and 0.4% of the bindings' public functions are unsafe, and only 0.1% and 0.6% have a raw pointer in their signature. Their tests cover 98.92% and 99.07% of the Rust code and 45.95% and 67.20% of libgit2 and of ffmpeg's libavutil, and the reviewers fixed 8 and 13 defects that caused UB reachable from Rust. To our knowledge, this is the first work to automate the generation of safe Rust bindings for C libraries.

cs.PL · cs.AI · cs.CR · cs.SE

版本更新 · v11arXiv:2208.00335

Interpretable Machine Learning: Can the EnglishLike Programming Language be the Future of ChatIPC and ChatIPCv2?

Caleb Princewill Nwokocha

原文摘要

The development of interpretable machine learning requires more than the ability to produce predictions accompanied by explanations. It requires computational systems whose internal representations, decision procedures, constraints, and execution paths can be inspected, reproduced, and modified by humans. This paper investigates whether EnglishLike, an English-like, object-oriented programming language implemented in C++17, could provide the symbolic programming and execution foundation for the ChatIPC and its subsequent implementation, ChatIPCv2. The investigation is based on a comparative examination of the publicly available ChatIPC.cpp and ChatIPCv2.cpp implementations in the PCNTechnologyEnterprise Hugging Face repository, together with the EnglishLike 2.2 implementation available in the associated project materials. ChatIPC combines incrementally learned token-transition relationships with dictionary derived semantic information, part-of-speech information, Jaccard similarity, grammatical heuristics, repetition penalties, and deterministic candidate selection. ChatIPCv2 introduces a different generation strategy based on token identifiers, historical-context bitsets, multi-depth graph exploration, n-gram backoff, and parallel candidate evaluation. EnglishLike provides a complementary computational abstraction: a structured language for expressing declarations, functions, classes, interfaces, control flow, and executable rules. Its compiler, bytecode verifier, and virtual machine provide a potentially useful foundation for representing and executing symbolic reasoning procedures.

cs.LG

新论文 · v1arXiv:2611.10393

Finite Time Analysis of Risk-Sensitive RL via Noisy Power Iteration

Waqar Mirza, Yashaswini Murthy, Laixi Shi, Eric Mazumdar, Adam Wierman

原文摘要

Estimating the principal eigenpair of a positive operator from stochastic evaluations gives rise to a noisy form of normalized power iteration: each step applies a sampled operator estimate and then renormalizes. We establish finite-time stochastic-approximation guarantees for this procedure, working in Hilbert's projective metric, which is well-suited to the multiplicative geometry of Perron--Frobenius eigenproblems. Our main application is risk-sensitive average-cost reinforcement learning (RL) with exponential utility. In this setting the Bellman equations are multiplicative, and value functions are characterized by nonlinear eigenvalue problems rather than additive fixed points. We cast both policy evaluation and control in this framework, obtaining risk-sensitive TD- and Q-learning algorithms that learn from a single Markovian trajectory. Under explicit positivity, mixing, and linear function approximation assumptions, we prove finite-time bounds on the recovered eigenvector and eigenvalue with $\tilde{O}(ε^{-2})$ sample complexity up to problem-dependent constants. The results cover both tabular and linear function approximation regimes, and through the duality between exponential utility and KL-robust control yield finite-time guarantees for KL-robust average-cost RL as well.

cs.LG

版本更新 · v2arXiv:2604.03787

Dimension-Free Sinkhorn for Optimal Transport: Bypassing Extremal Costs

Kun He

原文摘要

The Sinkhorn--Knopp (SK) algorithm is a cornerstone method for matrix scaling and entropically regularized optimal transport (EOT). Despite its empirical efficiency, existing bounds for achieving marginal accuracy $\varepsilon$ deteriorate severely in the presence of extreme entries, bottlenecked either by the global maximum regularized cost $η\|C\|_\infty$ (where $η$ is the regularization parameter and $C$ the cost matrix) or the matrix's minimum-to-maximum entry ratio $ν$. These bounds may be overly sensitive to rare extreme entries that do not dominate the overall matrix structure. We identify a broad structural regime in which the dependence on the magnitude of global extreme entries can be circumvented. For EOT, we introduce well-boundedness, a local mass property that captures the row- and column-wise bulk structure of the underlying matrix while maintaining robustness against scattered entrywise outliers. We prove that, governed by this structural condition, SK converges to the target transport plan for a problem of dimension $n$ in $O(\log n + \log(1/\varepsilon))$ iterations. This complexity bound is independent of the maximum regularized cost $η\|C\|_\infty$. A computationally negligible pre-scaling step eliminates this dimensional dependence, reducing the iteration complexity to a strictly dimension-free $O(\log(1/\varepsilon))$. Beyond EOT, we establish a sharp phase transition for general $(\boldsymbol{u},\boldsymbol{v})$-scaling governed by a critical matrix density threshold. We prove that when a matrix's density exceeds this threshold, the iteration complexity is strictly independent of $ν$. Conversely, when the density falls below this threshold, the dependence on $ν$ becomes unavoidable; in this sub-critical regime, we construct instances where SK requires $Ω(n/\varepsilon)$ iterations.

cs.DS · cs.LG

版本更新 · v3arXiv:2602.11674

Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs

Longyuan Zhu, Hairan Hua, Linlin Miao, Wei Wang, Bing Zhao

原文摘要

Large Language Models (LLMs) are advancing rapidly, yet the benchmarks used to measure this progress are becoming increasingly unreliable. Score inflation and selective reporting have eroded the authority of standard benchmarks, leaving the community uncertain about which evaluation results remain trustworthy. We introduce the Benchmark Health Index (BHI), a pure data-driven framework for auditing evaluation sets along three orthogonal and complementary axes: (1) Capability Discrimination, measuring how sharply a benchmark separates model performance beyond noise; (2) Anti-Saturation, estimating remaining headroom before ceiling effects erode resolution and thus the benchmark's expected longevity; and (3) Impact, quantifying influence across academic and industrial ecosystems via adoption breadth and practice-shaping power. By distilling 106 validated benchmarks from the technical reports of 91 representative models in 2025, we systematically characterize the evaluation landscape. BHI is the first framework to quantify benchmark health at a macro level, providing a principled basis for benchmark selection and enabling dynamic lifecycle management for next-generation evaluation protocols.

cs.AI

版本更新 · v2arXiv:2602.12413

Soft Contamination Means Benchmarks Test Shallow Generalization

Ari Spiesberger, Juan J. Vazquez, Nicky Pochinkov, Tomáš Gavenčiak, Peli Grietzer, Gavin Leech, Nandi Schoots

原文摘要

Training on benchmark test items is a classic way to overestimate generalization to unseen problems. Standard decontamination methods miss semantic duplicates (SemDs): training items equivalent in content to a test item, but distant in string space. We call training on such items soft contamination; when the resulting gains extend to held-out items of the same benchmark (but not to related benchmarks), we call the result shallow generalization. We first embed Olmo 3's entire post-training dataset and search it for SemDs of benchmark items; we then finetune Olmo 3 and Qwen models on natural and synthetic semantic duplicates. We find (1) that soft contamination is widespread: the Olmo corpus contains SemDs of 76% of the CodeForces test set and 100% of MBPP's; (2) that finetuning on SemDs of a benchmark raises accuracy on its held-out items by up to 22pp in controlled experiments and 10-11pp at realistic contamination rates, though the effect varies across benchmarks; (3) that the gains from training on SemDs mostly do not transfer to conceptually similar benchmarks, i.e. we find shallow generalization; (4) that finetuning on items with similar embeddings that are not SemDs produces no such gain, indicating that the mechanism is not mere topical similarity; and (5) that at realistic contamination rates, soft contamination can raise held-out performance about as much as exact duplicates (or more). Benchmark gains here are therefore confounded - in a way that standard decontamination does not address.

cs.LG · cs.AI

版本更新 · v2arXiv:2604.16423

Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity

Satchel Grant, Victor Gillioz, Jake Ward, Thomas McGrath

原文摘要

Defensive training methods such as positive preventative steering (PPS) and inoculation prompting (IP) offer surprising results through seemingly similar processes: both add trait-inducing objects to large language models (LLMs) during training, and both defend the LLM against acquiring the trait. The success of these methods raises the questions: how do they work, and are they doing the same thing? We provide behavioral and mechanistic analyses of PPS and IP, using the acquisition of an ``evil'' persona by Qwen2.5-7B-Instruct as an in-depth case study and replicating key measurements across six traits and four models. Behaviorally, neither method operates through a purely associative mechanism, and both methods prevent trait acquisition; but PPS can also substantially reduce pre-existing trait expression, whereas IP does so only modestly. Mechanistically, PPS induces a concentrated change in the activation gradient and shifts the signal along the trait direction from amplifying to attenuating, whereas IP changes the gradient more diffusely and shifts it close to zero along the trait direction. Gradient manipulations show that the direction of this component is causally relevant to trait acquisition, although it is one effect rather than a complete account of either defense. We then show that IP lowers the next-token prediction loss on trait-expressing data, whereas PPS can raise it at the intensities at which it defends; we show how this analysis raises the possibility that the loss changes and the gradient shift are two summaries of the same training signal rather than completely separate mechanisms. Together, our results show that PPS and IP are not interchangeable, and they highlight open questions about a complete mechanistic picture.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10392

Tiresias: Towards Language-Conditioned World Models

Fengyi Wu, Yifei Dong, Yetong Sha, Lingdong Kong, Qiyu Hu, Bohan Xiong, Qi Dai, Alexander G. Hauptmann 等 9 位作者

原文摘要

World models enable planning through internal simulation, while natural language provides intuitive task specification. Yet, language-conditioned world modeling remains fragmented across domains with disparate action spaces, datasets, and evaluation protocols. We introduce LCWM, a shared task that maps an initial agent-view observation and a language instruction to an action sequence that fulfills the instruction. Its accompanying benchmark, LCWM-Bench, integrates 15 datasets across navigation, robotics, 3D gaming, and driving under a shared action interface and evaluation protocol, pairing 142,987 episodes with 428,961 instructions in three styles. We further propose Tiresias, an agent that plans via selective imagination: a language-conditioned diffusion policy generates candidate trajectories, a trajectory ranker shortlists them, and a video-pretrained world model imagines their visual consequences. A visual ranker evaluates these rollouts, complementing trajectory scores to select the final plan. Tiresias achieves competitive planning and imagination performance on LCWM-Bench. Ablations demonstrate the complementary benefits of trajectory ranking and visual verification, while experiments with alternative proposal methods show that the trained rankers remain effective beyond our diffusion policy. Together, LCWM-Bench and Tiresias provide a unified evaluation setting and an effective starting point for studying language-guided planning through world models.

cs.CV

版本更新 · v3arXiv:2602.05214

Disentangled Representation Learning via Flow Matching

Jinjin Chi, Taoping Liu, Mengtao Yin, Ximing Li, Yongcheng Jing, Jialie Shen, Leszek Rutkowski, Dacheng Tao

原文摘要

Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new paradigms for learning such representations. However, existing diffusion-based methods encourage factor independence via inductive biases, yet frequently lack strong semantic alignment. In this work, we propose a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space. To enforce explicit semantic alignment, we introduce a non-overlap (orthogonality) regularizer that suppresses cross-factor interference and reduces information leakage between factors. Extensive experiments across multiple datasets demonstrate consistent improvements over representative baselines, yielding higher disentanglement scores as well as improved controllability and sample fidelity.

cs.LG

版本更新 · v2arXiv:2610.34045

Minimax Regret for Sobolev Kernel-Based Reinforcement Learning

Haichen Hu, David Simchi-Levi

原文摘要

We study the minimax regret rate for episodic kernel-based reinforcement learning, where the expected reward and transition density belong to a Sobolev reproducing kernel Hilbert space (RKHS), with continuous state and action spaces, and adversarial initial states. For Sobolev smoothness parameter $ν>0$, state dimension $d_S$, and action dimension $d_A$, we prove that the minimax expected regret over $T$ episodes is $\widetildeΘ(T^{\max\{e_A,e_B\}})$, where $e_A=\frac{ν+d_A}{2ν+d_A}$, $e_B=\frac{ν+d_A+3d_S/2}{2ν+d_A+2d_S}$ with the other model parameters fixed. The two exponents reflect the distinct difficulties of action selection and learning across states. We introduce Sobolev Optimal Value Iteration (\texttt{SOVI}), which attains this rate from observed rewards and transitions. For fixed smoothness and reference-kernel lengthscale, its regret bound has a prefactor polynomial in the state-action dimension $d=d_S+d_A$, horizon $H$, reward and transition RKHS norm bounds $B_r,B_p$, and the norm-comparison factor $Λ$, up to logarithmic factors; $Λ=1$ for normalized Matérn kernels. The algorithm separates initial action selection from continuation-value estimation and combines local polynomial approximation with the shared RKHS structure of the approximation errors. Our matching upper and lower bounds determine the optimal dependence on the number of episodes for Sobolev kernel-based reinforcement learning regret minimization. Thus, we partially address the open problem in Vakili(2024) under Sobolev kernel RL.

cs.LG · math.ST · stat.ML

新论文 · v1arXiv:2611.10390

A Computational Map of the Disaster Mental Health Research Landscape

Soheil Shapouri, Saber Soleymani

原文摘要

When disasters strike, they not only damage infrastructure, buildings, and the economy, but also affect the mental health of affected populations. Research on the mental health effects of disasters has expanded rapidly and has become an important, well-funded area of psychology, public health, and related social sciences. However, the overall structure of this research landscape has not been systematically characterized. Using large language models, we conducted a review of all articles related to terms 'disaster' and 'mental health' indexed in PubMed. 7,859 articles' metadata were retrieved using the NCBI API, and then Claude Sonnet was used to extract structured variables from the abstracts. The results indicated that earthquakes and epidemics were the most commonly studied disasters while many other disasters such as heat and cold waves have received less attention. PTSD, depression, and anxiety were well investigated but many other mental health issues (e.g., aggression, suicide) are relatively ignored. Despite enjoying relatively large sample sizes (median = 452, IQR = 142 - 1,568), the field rarely utilizes machine learning algorithms. Hypothesis significance testing, reviews, qualitative methods, and structural equation modeling are respectively most common methods while agent-based modeling, machine learning, casual inference, and NLP each appear in less than 1% of articles. Studies are limited to a small number of countries, particularly the United States, Japan, and China, while many disaster-prone regions remain substantially underrepresented. This LLM-assisted computational map provides a broad overview of the disaster mental health literature while highlighting important methodological gaps, with particular emphasis on the underutilization of computational methods that could help advance the field.

cs.AI · cs.CY · cs.DL

版本更新 · v2arXiv:2610.22100

When the next byte's type is fixed: why entropy patching skips computed values under tight budgets

Nicolás Vera Zúñiga

原文摘要

The Byte Latent Transformer (BLT) runs a large model once per patch and starts patches where a small model's next-byte entropy is high. Under tight budgets this rule skips computed values, such as the number after "= " in math. On BLT-1B at inference we trace the miss to the cue before a value: when the preceding bytes fix the next byte's type, the patcher's entropy is capped near log2 10 bits, close to a 10% budget's threshold. Entropy then starts a patch at 0% of values after a dollar sign and 19% after "= "; writing "is " instead of "= " raises the 19% to 66%. Version 1's two-byte lookup table, motivated by LZ novelty, acts as a learned detector of cues that tend to precede new values in its fitting text: on the solutions rewritten as prose it covers every value after a dollar sign and none after a plain space, and its margin over entropy falls from +42.1 to -8.9 points, partly because prose gives entropy more starts per value. In BLT-style models trained from scratch (1M-50M parameters, 128-byte context, 3 seeds per rule) and scored by teacher-forced exact match on answer spans, the table beats entropy at 50M by 36.8 points on computed results and 29.6 on final answers, which mostly copy the last computed result. A hand-written marker rule is not distinguishable from the table at 1M and 12M; its 50M control was not run. At 1M and 12M the table ran on a T4 GPU in fp16 and the baselines on an A40 in bf16; at 50M all ran on the A40. End to end, no 1M-50M model solves more than 2 of 100 GSM8K problems. A label-free probe of BLT-1B's patcher finds prose values, mostly after a dollar sign, but costs final answers. In six domains, no rule we tested beat entropy on exact match of whole words and numbers in more than one domain. The positive findings concern tight budgets on cue-formatted text. This version corrects version 1; the work is closed, with no venue intended.

cs.CL · cs.LG

新论文 · v1arXiv:2611.10389

From Task Affinities to Optimal Allocations: Probabilistic Graphical Modelling for Supervised Finetuning

Prateek Chanda, Saral Sureka, Krishnateja Killamsetty, Ganesh Ramakrishnan

原文摘要

Supervised fine-tuning over a large pool of heterogeneous tasks is often computationally expensive, leading practitioners to train language models on a fixed training budget of carefully chosen SFT tasks. Thus, achieving strong downstream performance hinges on selecting an effective subset of tasks, or equivalently, identifying an optimal task mixture under a fixed budget constraint. In practice, supervised finetuning mixtures are often determined using simple heuristics (e.g., uniform or size-proportional sampling) that ignore task interactions, which can hurt transfer and waste budget on redundant task sources. We introduce TASKMIXPGM, a framework for learning continuous task mixtures through energy-based modelling over SFT tasks. Each task forms a node in a Markov random field, with unary potentials capturing task utility and pairwise potentials modelling inter-task relationships via behavioral divergences between predictive distributions of single-task fine-tuned models. Optimizing this objective yields task mixtures that balance utility, coverage, and redundancy. We further show that the induced set function defined over the set of such tasks is weakly submodular under budget constraints, enabling approximation guarantees for discrete task selection. Empirically, we provide a fixed, benchmark-independent mixture that improves over heuristic mixing across multiple model families and different training budgets. TASKMIXPGM also uncovers interpretable structure in task interactions, revealing complementarities and redundancies that inform effective SFT mixtures.

cs.LG

版本更新 · v2arXiv:2606.08914

Vibe Visualizing: How Visualization Novices Try (and Fail) to Generate and Interpret Visualizations with Conversational AI

Sam Yu-Te Lee, Yun-Hsin Kuo, Chifang Chou, Matthew Ward, Xiwei Xuan, Kwan-Liu Ma

原文摘要

Conversational AI lowers technical barriers to generating and interpreting visualizations. People without visualization training or practical experience can therefore perform these tasks, but may lack the expertise needed to evaluate the resulting charts and interpretations. Through a study with 20 visualization novices, we examine conversation logs from 60 sessions with ChatGPT and develop a codebook that characterizes participant and AI behaviors in AI-assisted visualization. Paired with interview transcripts and survey responses, we derive three themes under outcome quality, AI non-compliance, and trust, verification, and repair. An exploratory role analysis identifies two session-level roles distinguished by user initiative and associated with different failure patterns. A comparative analysis with Gemini and Claude further reveals distinct system-specific behaviors. Based on these findings, we derive five design recommendations for AI-assisted visualization design and discuss implications for visualization literacy, human-AI roles, accountability, and agentic visualization.

cs.HC

版本更新 · v4arXiv:2208.03784

CoVault: Secure, Scalable Analytics of Personal Data

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg 等 9 位作者

原文摘要

There is growing awareness that the analysis of personal data, such as individuals' mobility, financial, and health data, can provide significant benefits to society. However, liberal societies have so far refrained from such analytics, arguably due to the lack of secure analytics platforms that scale to billions of records while operating in a very strong threat model. We contend that one fundamental gap here is the lack of an architecture that can scale (actively-)secure multi-party computation (MPC) horizontally without weakening security. To bridge this gap, we present CoVault, an analytics platform that leverages server-aided MPC and trusted execution environments (TEEs) to colocate the MPC parties in a single datacenter without reducing security, and scales MPC horizontally to the datacenter's available resources. CoVault scales well empirically. For example, CoVault can scale the DualEx 2PC protocol to perform epidemic analytics for a country of 80M people (about 11.85B data records/day) on a continuous basis using one core pair for every 30,000 people.

cs.CR · cs.DC

新论文 · v1arXiv:2611.10386

Pruning DNA Sequence

Faias Satter, Shaker Islam, Aminul Islam

原文摘要

Data pruning can substantially reduce training cost by removing examples that contribute little additional learning signal, but it has not been studied for DNA language-model pretraining. We introduce Sequence Pruning (SP), a dynamic pruning framework that removes genomic sequences as they become easy for the model to predict. SP uses per-sequence pretraining accuracy computed directly from the model's forward pass, requiring no separate scoring model or additional pass over the corpus. We evaluate SP across five pretraining settings spanning two corpora, three model families, and both MLM and CLM objectives, with downstream evaluation on five genomic benchmarks. SP reduces pretraining data processing by up to 96% while largely preserving downstream performance. At moderate savings, pruning improves performance by up to 1.2 MCC points over full-data pretraining; at the highest savings, pretraining uses only 4% of the baseline GPU hours with little performance loss. SP also outperforms the dynamic pruning methods InfoBatch and BPAS across most comparisons. Beyond accuracy, our framework supports alternative criteria such as perplexity and EL2N, although accuracy yields the strongest downstream performance at matched savings. These results show that genomic pretraining does not require repeatedly processing all available sequences and that dynamic sequence-level pruning can substantially improve its data and computational efficiency. Code is available at https://github.com/FaiasPromit/pruning-dna-sequence.

cs.LG · q-bio.GN

版本更新 · v2arXiv:2601.16906

The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning

Calarina Muslimani, Yunshu Du, Kenta Kawamoto, Kaushik Subramanian, Peter Stone, Peter Wurman

原文摘要

The success of RL is fundamentally tied to having a reward function that accurately reflects the task objective. Yet, designing reward functions is time-consuming and prone to misspecification. To address this, our first goal is to understand how to support RL practitioners in specifying reward functions. We leverage the Trajectory Alignment Coefficient (TAC), a metric that evaluates how closely a reward function's induced preferences match those of a domain expert. To test whether TAC provides meaningful support, we evaluated its impact in a user study where practitioners designed reward functions for Lunar Lander. We found that iterative TAC feedback allowed participants to design more performant reward functions while reporting lower cognitive workload than unguided reward design. However, the study also underscored that manual reward design, even with TAC, remains labor-intensive. This motivated our second goal: to learn a reward model that maximizes TAC directly. Specifically, we propose Soft-TAC, a differentiable approximation of TAC that can be used as a loss function to train reward models from human preferences. Our theoretical analysis guarantees that under Soft-TAC optimization: (1) the optimal reward function belongs exclusively to the set of human-aligned reward functions, and (2) this optimal reward remains invariant whether trained on clean or noisy preference data. Empirically, we first evaluate reward models trained with Soft-TAC across three robotic tasks, demonstrating that they consistently match or outperform those trained with the Cross-Entropy loss. Next, we evaluate Soft-TAC in the GT7 driving simulator, and find that Soft-TAC-trained reward models more successfully capture preference-specific driving styles. Ultimately, this work demonstrates that TAC can serve as both a practical tool for guiding reward design and a reward learning objective in complex domains.

cs.LG · cs.HC

版本更新 · v2arXiv:2610.24184

Multi-author style detection with stylistic embeddings

Man-Ling Sung, Chak Fai Li, Damianos Karakos, Fred Bernardin, Brian Ulicny

原文摘要

We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection.

cs.CL

新论文 · v1arXiv:2611.10385

A Topological Encoder Decoder Framework for Temporal Graph Learning

Ronan Buck, Kiarash Shamsi, Tran Gia Bao Ngo, Astrit Tola, Baris Coskunuzer, Cuneyt Gurcan Akcora

原文摘要

Most temporal graph learning methods reduce future prediction to discriminative inference over past interactions, focusing on edges or node labels for a largely persistent set of nodes. This view breaks down when new nodes and edges appear, since the future graph becomes a new object with changing size, composition, and structure. We address this gap by framing temporal graph prediction as an inverse topology problem. Instead of predicting edges directly, we first predict a multiscale topological descriptor of the future graph and then reconstruct a plausible future snapshot that realizes this descriptor under inductive constraints. This approach makes global structure and node churn explicit prediction targets and produces forecasted graphs that downstream tasks can evaluate without retraining. Across 14 temporal graph datasets, we evaluate our method, TOPOGED, on node, link, and graph property prediction and compare it against state-of-the-art temporal graph models. TOPOGED significantly improves node-level forecasting accuracy over the strongest baseline, with a macro average of 0.49 versus 0.05. It also outperforms baselines in 60% of graph-structure metric evaluations and substantially increases macro-average edge prediction metrics, from near-zero to 0.12. Our results show that topology-guided graph forecasting can predict inductive future snapshots whose structure supports multiple downstream evaluations.

cs.AI · cs.LG

新论文 · v1arXiv:2611.10382

From Reflection to Co-Evolution: Self-Evolving Agents with Locally Verified Memory

Xinxiang Yin, Xinglang Zhang, Haodong Chen, Zhiqing Cui, Weidong Tang, Yuxuan Wang, Junrui Wang, Jingyi Zhang 等 10 位作者

原文摘要

LLM agents have made impressive progress in coding and mathematical reasoning, motivating growing interest in learning from long-horizon interaction. Memory supports this process, but plausible lessons can be redundant or reinforce inappropriate actions. Can a memory's source decision provide a practical test for whether to retain it? We localize consequential trajectory steps, extract candidate memories, and replay each source decision with and without its candidate under the same context. This reveals two properties: most candidates barely shift the probed distribution, and both successful and failed source actions can be reinforced or suppressed. These observations motivate Anchor, which tests shift magnitude and source-role alignment before retention. Admitted memories guide later trajectories, enabling experience-driven improvement under a frozen policy. On held-out ALFWorld and WebShop tasks, Anchor improves success rate and mean score by up to 19.9% and 17.2%, respectively, relative to the strongest baseline for each backbone. With Qwen3.5-27B, it retains 41% fewer ALFWorld cards than unfiltered retention and outperforms all four WebShop cost-comparison baselines while using fewer tokens.

cs.CV

版本更新 · v3arXiv:2605.13230

Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

Xinyu Liu, Kechen Jiao, Chunyang Xiao, Runsong Zhao, Junhao Ruan, Bei Li, Jiahao Liu, Qifan Wang 等 13 位作者

原文摘要

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods rely on reverse KL (RKL)-based teacher supervision over trajectories sampled from the student policy. However, we identify a critical limitation: under large teacher--student policy divergence, RL-driven exploration often produces trajectories outside the teacher distribution, resulting in uninformative negative feedback. To address this, we propose Teacher-Guided Policy Optimization (TGPO), an on-policy reasoning distillation method that remains effective under large policy divergence settings. Rather than relying solely on evaluative supervision, TGPO uses teacher to directly guide token level generation conditioning on student-generated contexts; together with RLVR-style trajectory level rewards, TGPO steers exploration toward improved continuations. Experiments on reasoning benchmarks show that TGPO consistently outperforms existing RKL-based OPD methods and remains robust across different teacher models.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10379

RefineSplat: Reconstruction-Guided Object-Centric Gaussian Splatting for Open-Vocabulary Querying

Yiren Lu, Disheng Liu, Sreya Srinidhi, Yunlai Zhou, Yiran Qiao, Chaoda Song, Tuo Liang, Jing Ma 等 10 位作者

原文摘要

Open-vocabulary 3D scene understanding aims to segment and retrieve arbitrary objects in 3D scenes using natural language queries. Most existing methods typically follow a splat-then-segment paradigm, where 3D Gaussian Splatting is first reconstructed and then augmented with labels or language features for subsequent segmentation. However, this pipeline often suffers from view inconsistency, ambiguous object boundaries, and weak object-level correspondence, especially in complex static and dynamic scenes. Building on our prior Segment-then-Splat framework, we present RefineSplat, a reconstruction-guided extension that retains its object-centric paradigm: it first tracks objects in 2D and then reconstructs each object with a dedicated set of 3D Gaussians, preserving explicit object-Gaussian correspondence for unified open-vocabulary segmentation and retrieval. To improve robustness, we further close the loop between 2D tracking and 3D reconstruction. Since off-the-shelf video trackers can produce unreliable masks that propagate errors into object reconstruction, we introduce a reconstruction-guided feedback mechanism that refines object tracking using rendered masks and multi-view consistency. Moreover, instead of assigning each object a single language embedding, we propose a viewpoint-aware embedding assignment strategy, where each object maintains multiple view-clustered embeddings to capture view-dependent semantic cues. We also introduce Blender-OVS, a synthetic benchmark of static and dynamic sequences with exact object meshes and point clouds, enabling direct evaluation of extracted geometry. Experiments on static and dynamic benchmarks show improved rendered-view segmentation and lower object-level Chamfer distances, with competitive scene reconstruction quality.

cs.CV

版本更新 · v2arXiv:2611.04072

Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies

Yizhou Zhang, Yashaswini Murthy, Laixi Shi, Adam Wierman

原文摘要

We study the problem of average reward Multi-Agent Reinforcement Learning (MARL) where agents interact within a network. Each agent in the network conducts local updates with information within its $k$-hop neighborhood and collaboratively maximizes the overall reward of the entire network. We first provide impossibility results in achieving convergence to the global optimal joint policies in our setting. These impossibility results highlight the challenges of decentralized learning with local information in multi-agent systems, namely the issues of multiagency, where each agent independently optimizes its policy, and partial observability, where agents have limited visibility into the global state. Given these challenges which indicate that decentralized policy optimization can generally be certified only up to stationarity, we provide finite-sample convergence guarantees for a decentralized actor-critic algorithm with linear function approximation that converges to an approximate stationary point with small gradient norm. To overcome such impossibility results, we further show that adding fixed-state entropy regularization reshapes the objective landscape which leads to even stronger global convergence guarantees for our proposed actor-critic algorithm.

cs.LG · cs.MA

新论文 · v1arXiv:2611.10377

Vision Language Models for Primary Structure Threat Identification in Wildland Urban Interface Fires

Zhangding Liu, Neda Mohammadi, John E. Taylor

原文摘要

Wildland urban interface (WUI) fires increasingly threaten communities and infrastructure, motivating the need for rapid visual assessment. Recent research has focused primarily on detecting fire and assessing post-event damage. However, structure-level fire threat identification during active WUI fire events remains underexplored. This study evaluates Qwen3-VL-8B-Instruct for this active-fire decision using two separately scored tracks: 1,824 synthetic images from 491 designed WUI scenarios and 45 frames from a controlled-burn experiment conducted in collaboration with Columbus Fire & EMS Department. Under zero-shot prompting, the model returned valid target fields for 1,808 synthetic images and 39 controlled-burn frames. Accuracy among valid outputs was 94.0% for the synthetic track and 69.2% for the controlled-burn track, compared with a 16.0% random-selection baseline for the latter. On the synthetic track, the model generally identified the intended target across varied designed WUI scenarios when the relevant fire-spread cues were visually distinct. Controlled-burn performance was well above random selection, but errors showed difficulty interpreting spatial relations in complex scenes. The dual-track protocol provides scalable stress testing in designed scenarios and a controlled-burn reference for assessing model behavior under physical fire conditions. Future work can use the synthetic data for VLM post-training and then evaluate the adapted models on larger and more diverse real WUI fire datasets.

cs.CV

新论文 · v1arXiv:2611.10376

PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image Dehazing

Rayen Dhahri, Lei Sun, Victor Javier Kartsch Morinigo, Alice Pagnoux, Luca Benini, Danda Pani Paudel, Luc Van Gool

原文摘要

Modern dehazing networks are often computationally expensive and overfit to synthetic haze, limiting real-time deployment. This underscores an urgent demand for efficient, high-fidelity restoration methods that can operate on resource-constrained edge devices in practical, dynamic environments. We introduce PhysDNet, a lightweight multimodal architecture that fuses NIR imagery with sparse LiDAR depth and is trained with a physics-constrained dual-head objective. Differentiating through a fixed Koschmieder inversion induces density-adaptive gradient amplification, acting as an implicit resource allocation mechanism that concentrates learning on heavily degraded regions without increasing inference cost. PhysDNet delivers superior restoration with minimal capacity and enhanced training efficiency, facilitating real-time deployment on edge devices without increasing inference overhead. On the Seeing Through Fog benchmark, PhysDNet outperforms competitors by 1.67 dB at 5.2 times lower compute while recovering 54.9% of fog-induced detection loss. Ablations and cross-domain evaluations show that physics-guided training improves generalization, including under non-homogeneous haze that violates the Koschmieder assumption. PhysDNet further demonstrates compatibility with fixed-function NPUs, running at 29/45/99 FPS at <4 W across L/M/S variants. Code, deployment scripts and pre-trained checkpoints are available at https://github.com/Heatdh/PhysDnet.

cs.CV · cs.LG