跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 04:52 — 2026-11-19 04:52(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2604.17095

Computational Construction and Engineering Evaluation of a Verified Mono-Monostatic Body

Vincent Wesley Couey

原文摘要

Many engineering failures in orientation-dependent systems are geometric failure modes: changing the material delays the failure; changing the geometry can eliminate it. The mono-monostatic property (exactly one stable equilibrium under gravity) is mathematically proven to exist in convex homogeneous bodies, but, to our knowledge, no verified smooth geometry had been openly published when v1 appeared (April 2026). We introduce an Equilibrium Count Score (ECS) oracle that measures stable equilibria via drainage basin analysis on the center-of-mass height landscape. v2 correction: v1 reported that Sloan's (2023) analytical Gomboc parameterization shows 4-11 local minima "at all published parameter values." That claim is withdrawn. The beta values swept were this work's own grid points, not Sloan's (he states convexity bounds beta <= 0.15 and beta <= 0.17); they lie inside the strictly convex sub-regime beta < ~0.036, where a body at beta = 0.023 was later certified mono-monostatic by interval arithmetic; and the oracle's two stages are biased in opposite directions, so its count can be wrong either way. We construct one strictly convex mono-monostatic body by extending the Sloan phase function with a Fourier term and optimizing via differential evolution, with ECS=1 confirmed across merge thresholds from 0.5% to 10%; two more reach ECS=1 under the oracle but are not strictly convex. Conventional geometries cannot achieve ECS=1 through ballast alone: cylinders and cubes retain multiple stable equilibria even at 30% bottom-weighted mass. Applications: an IMU calibration housing (349x orientation precision improvement), aerial reforestation seed pods (20-67% germination loss from incorrect landing orientation), and marine buoy self-righting. Cross-layer scoring shows the Gomboc is 11.8x worse than the cylinder on contact distribution while optimal on equilibrium stability.

cs.CE

版本更新 · v3arXiv:2610.41675

Radial Kernel Attention for Global Feature Exchange in Polymer Machine Learning Force Fields

Wenbo Fu, Chenghui Mao, Haifeng Lv, Chengwen Hu, Zhou Lu

原文摘要

We introduce Radial Kernel Attention (RKA) for long-range modeling in polymer machine learning force fields. Existing approaches often rely on local neighbor graphs, which limit communication across polymer chains and their surrounding environments, whereas explicit all-pair attention incurs quadratic computational cost. RKA maps interatomic distances from the cluster centroid to learned radial features and combines their kernelized overlap with content-dependent queries and keys. Factorized aggregation and readout enable global feature exchange at linear complexity in the number of atoms for fixed feature dimensions. To ensure physically consistent predictions, we insert the invariant scalar update between EquiformerV3 local blocks and obtain conservative forces by differentiating the total energy, including its dependence on radial coordinate . Our models are trained on official OPoly26 training set for 12 epochs and evaluated directly after training on the complete official validation set. A matched 5M comparison shows that RKA reduces per-atom energy and force MAEs by 67.4% and 36.3%, respectively. The 20M RKA model attains a total-energy MAE of 15.81 meV (per-atom MAE of 0.1182 meV/atom) and a force MAE of 2.619 meV/Angstrom,improving all three metrics over UMA-S-1.2 and UMA-S-1.2.1 on the same validation structures. RKA provides a compact pathway for information exchange beyond local graph connectivity in polymer machine learning force fields.

cs.AI

版本更新 · v2arXiv:2607.03194

TATG: Tracking-Aware Testing Objective for LLM-based Test Generation

Guancheng Wang, Qinghua Xu, Lionel Briand

原文摘要

Complex Java methods challenge automated unit test generation, as achieving high coverage and fault detection requires satisfying intricate testing requirements involving program states, execution paths, and assertions. Existing LLM-based approaches leverage program context, static analysis, and dynamic feedback but lack explicit tracking of individual testing requirements across iterations, potentially leading to redundant generation and unresolved testing objectives. We present TATG, a tracking-aware LLM-based unit test generation framework that unifies structural coverage and mutation-based fault detection. TATG introduces a structured objective representation capturing testing requirements derived from static analysis and dynamic feedback, enabling fine-grained tracking of their satisfaction status. It employs a two-stage workflow that first improves structural coverage and subsequently strengthens assertions through mutation-guided hardening. We evaluate TATG on 141 complex Java methods against state-of-the-art baselines, including KTester and PANTA. Results show average improvements of 22.15, 20.14, and 37.66 percentage points in line coverage, branch coverage, and mutation score, respectively. TATG also outperforms general-purpose coding assistants, including Codex and Claude Code, under the same open-weight model configurations, achieving higher average coverage and mutation scores while generating fewer tests and consuming fewer tokens. These findings highlight the value of explicitly tracking testing objectives for effective LLM-based test generation.

cs.SE

版本更新 · v4arXiv:2606.09289

Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning

Yuesen Li, Daniel Link

原文摘要

Recognising intentions from continuous movement trajectories is an important problem in spatiotemporal data mining. This becomes difficult when behaviours change over time and their boundaries cannot be directly observed. Football provides a useful setting for studying this problem because tactical intentions emerge from the coordinated movements of multiple players during possession. Existing methods for match phase recognition often classify individual frames, use predefined spatial rules, or identify only selected tactical patterns. They therefore cannot fully describe continuous possession sequences in which tactical intentions change over time. We address this gap by treating the identification of the in-possession match phase as a hierarchical sequence segmentation task. The framework includes three tactical intentions (Invade Opponent Space, Keep Possession, and Scoring) and six phases (Build Up, Progression, Counter Attack, Maintenance, Sustained Threat, and Finishing). We propose a Temporal Graph Attention Network (T-GAN) that combines player interaction graphs, contextual features, and Transformer based temporal modelling. The framework was evaluated on seven Bundesliga matches using leave-one-match-out validation and compared with rule-based, Random Forest, GNN, and Transformer baselines at both frame and sequence levels. The results show that temporal modelling is important for coherent phase segmentation, while graph modelling provides additional value for transition phases such as Counter Attack. The framework provides an interpretable method for discovering intention based behavioural segments from continuous player tracking data and supports automated tactical analysis in football.

cs.LG

版本更新 · v4arXiv:2603.09722

A Novel Two-Parameter Penalty: Relaxation Degree Analysis and Sparse Signal Recovery

Ziwei Li, Wengu Chen, Huanmin Ge, Dachun Yang

原文摘要

In this article, we introduce a nonconvex two-parameter penalty function $P_{a,p}$, parameterized by $a\in(0,\infty)$ and $p\in(0,1]$, and the relaxation degree RD$_P$ for a separable nonconvex penalty function $P$. Based on $P_{a,p}$, we further propose the $P_{a,p}$ minimization framework for sparse signal recovery. This framework generalizes the TL1 minimization model established by S. Zhang and J. Xin (corresponding to the special case $p=1$) and provides a unified family of nonconvex penalty functions for sparse signal recovery. Using the sparse convex-combination technique, we establish both exact and stable sparse signal recovery under the restricted isometry property (RIP). To efficiently solve the resulting nonconvex optimization problem, we apply a modified iteratively re-weighted least squares method and the difference of convex functions algorithm (DCA) to develop the IRLSTLp algorithm for unconstrained $P_{a,p}$ minimization and prove some convergence results. Finally, numerical experiments compare recovery and runtime against single- and double-loop baselines, examine sensitivity to $(a,p)$, and assess the empirical correlation between RD$_{P_{a,p}}$ and recovery within the proposed family.

math.FA · cs.IT · math.CA

版本更新 · v2arXiv:2609.31940

Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization

Haris Moazam Sheikh

原文摘要

Multi-objective Bayesian optimization (MOBO) is commonly approached through specialized acquisition functions or scalarization schemes designed to explicitly account for trade-offs among non-preferential objectives. In this work, we show that such complexity might be unnecessary. We propose a framework that extends standard single-objective acquisition functions directly to the multi-objective setting through a hypervolume-based methodology. We further extend hedge strategies for acquisition functions, which are typically used only in single-objective optimization, to the multi-objective regime. Our approach requires minimal modification to existing Bayesian optimization pipelines and avoids the need for bespoke multi-objective formulations. We demonstrate how a broad class of commonly used single-objective acquisition functions and hedge strategies can be adapted in a principled manner to handle multiple objectives, while preserving their intuitive interpretation and computational efficiency. Empirically, we evaluate the proposed methods across a range of synthetic and real-world multi-objective benchmarks. Despite their simplicity, our extensions consistently match or outperform more complex state-of-the-art MOBO methods in terms of optimization performance and sample efficiency. These results suggest that effective multi-objective Bayesian optimization can be achieved by reusing and carefully extending well-established single-objective acquisition strategies, offering a simpler and more flexible alternative to existing approaches.

cs.LG · math.OC · stat.ML

版本更新 · v2arXiv:2509.17228

Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness

Zihan Liang, Ziwen Pan, Ruoxuan Xiong

原文摘要

Clinical notes contain rich patient information, such as diagnoses or medications, making them valuable for patient representation learning. Recent advances in large language models have further improved the ability to extract meaningful representations from clinical texts. However, clinical notes are often missing. For example, in our MIMIC-IV cohort, 35.15% of patients have no eligible discharge summaries. In such cases, representations can be learned from other modalities such as structured data, chest X-rays, or radiology reports. Yet the availability of these modalities is influenced by clinical decision-making and varies across patients, potentially producing modality missing-not-at-random (MMNAR) patterns. We propose a causal representation learning framework that leverages observed data and informative missingness in multimodal clinical records. It consists of: (1) an MMNAR-aware modality fusion component that integrates structured data, imaging, and text while conditioning on missingness patterns to capture patient health and clinician-driven assignment; (2) a modality reconstruction component with latent alignment to preserve modality information in the learned representation; and (3) a multitask outcome prediction model with a rectifier that corrects for residual bias from specific modality observation patterns. Comprehensive evaluations across MIMIC-IV and eICU show consistent gains over the strongest baselines, achieving relative AUC improvements of up to 4.3% for hospital readmission and 2.7% for ICU admission.

cs.LG · cs.CL · stat.ME

版本更新 · v2arXiv:2603.16843

Counterfactual Distillation: Internalizing Reflective Experience into LLM Agent

Rui Ge, Yichao Fu, Yu-Yang Qian, Junda Su, Yiming Zhao, Hao Zhang

原文摘要

Large language models increasingly act as autonomous agents in long-horizon interactions, learning from final outcomes and environmental feedback. However, optimizing from such interaction experience remains challenging, as feedback is heterogeneous and rarely carries explicit reward information. Existing post-training approaches rely on outcome-driven methods, such as reinforcement learning with verifiable rewards (RLVR), which primarily exploit final success signals while leaving interaction experience and feedback underutilized. In sparse-reward, long-horizon tasks, this often results in distribution sharpening: the policy reinforces a narrow set of already-successful behaviors, without substantially improving the feedback-grounded agency needed for broader problem-solving capacity (e.g., Pass@k). We propose Counterfactual Distillation, a framework that converts exploration-derived experience into trainable policy supervision. Specifically, we organize exploration as a tree-structured search process, where the agent reflects on past decision points and makes new experience-guided decisions to form alternative branches. These corrections are then distilled as counterfactual targets: we train the model to predict the revised action from the original history without explicitly providing the experience, thereby introducing out-of-distribution behavior patterns and expanding exploration capacity. Across diverse interactive coding and agentic tasks, our method outperforms outcome-driven baselines such as GRPO and experience-based methods such as Early Experience, with gains of up to 14 percentage points over the base model on Pass@128. When interleaved with reinforcement learning updates, it further raises the performance ceiling, improving Pass@1 on Sokoban by 8 percentage points over extended GRPO. Our code is available at https://github.com/motigrez/Counterfactual-Distillation.

cs.AI

版本更新 · v3arXiv:2605.14477

Test-Time Learning with an Evolving Library

Weijia Xu, Alessandro Sordoni, Chandan Singh, Zelalem Gero, Michel Galley, Xingdi Yuan, Jianfeng Gao

原文摘要

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model parameters, our approach maintains a shared library of knowledge abstractions, including modular skills and reflective insights, automatically extracted from the model's own inference trajectories. To support continual improvement, we introduce a principled weighting and consolidation mechanism that jointly optimizes for immediate utility and long-term value. This allows simple, instance-specific abstractions to evolve into more general and reusable ones over time. Across challenging benchmarks in mathematical reasoning, code generation, and multi-turn agentic environments, EvoLib improves substantially over the top test-time scaling and learning methods without ground-truth feedback.

cs.LG

版本更新 · v2arXiv:2605.08360

Embeddings for Preferences, Not Semantics

Carter Blair, Ariel D. Procaccia, Milind Tambe

原文摘要

Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed set of candidates. A natural idea is to embed these opinions in a vector space so that the substantial literature on facility location problems and fair clustering can be brought to bear. But standard text embeddings measure semantic similarity, whereas distances in facility location problems and fair clustering require what we call preferential similarity: a participant's agreement with a piece of text should be inversely related to their distance from it. Off-the-shelf embeddings inherit a coarse preference signal through a correlation between semantic and preferential similarity, but fail to capture preferences when the correlation breaks. We formalize this as an invariance problem: text embedding models encode both a preference-relevant signal (stance and values) and semantic nuisance (style and wording), and the two are observationally correlated, so a geometry that relies on nuisance can appear preference-correct even when it is not. We show that synthetic training data designed to break this correlation provably shifts the optimal scorer away from nuisance-dominated cosine and significantly improves preference prediction across 11 online deliberation datasets.

cs.AI

版本更新 · v5arXiv:2410.22729

Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots

Vincent Guan, Joseph Janssen, Hossein Rahmani, Andrew Warren, Stephen Zhang, Elina Robeva, Geoffrey Schiebinger

原文摘要

Stochastic differential equations (SDEs) are a fundamental tool for modelling dynamic processes, including gene regulatory networks (GRNs), contaminant transport, financial markets, and image generation. However, learning the underlying SDE from data is a challenging task, especially if individual trajectories are not observable. Motivated by burgeoning research in single-cell datasets, we present the first comprehensive approach for jointly identifying the drift and diffusion of an SDE from its temporal marginals. Assuming linear drift and additive diffusion, we show that non-identifiability can only arise if the initial distribution possesses generalized rotational symmetries. We further prove that even if this condition holds, the drift and diffusion can almost always be recovered from the marginals. Additionally, we show that the causal graph of any SDE with additive diffusion can be recovered from the identified SDE parameters. To complement this theory, we adapt entropy-regularized optimal transport to handle anisotropic diffusion and introduce APPEX (Alternating Projection Parameter Estimation from $X_0$), an iterative algorithm designed to estimate the drift, diffusion, and causal graph of an additive noise SDE, solely from temporal marginals, and demonstrate its effectiveness on simulated data from linear additive noise SDEs.

stat.ML · cs.LG · math.ST

版本更新 · v3arXiv:2609.19150

Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations

Ajit Mallavarapu, Ziwei Gu

原文摘要

Large language models (LLMs) encode rich stylistic structure in their hidden activations, but discovering which stylistic dimensions are salient for a given prompt typically requires supervised contrastive data. We present a training-free, prompt-conditional alternative: we repeatedly sample completions of a single prompt at elevated temperature, apply Principal Component Analysis (PCA) to the pooled hidden activations, and label the resulting axes automatically from the pole generations. We validate the discovered axes against 245 human-elicited stylistic annotations in a two-phase study. On our strongest model (Qwen-3.5-4B-Instruct), the top two axes match spontaneously requested human dimensions with 72.8% precision and 43.6% macro-recall, and 75.6% of validity ratings judge the axes' polar generations accurate to their labels, with 90.9% adjacent inter-annotator agreement. Discoverability is strongly model-dependent: both Qwen models and Llama-3.2-3B expose human-salient axes, while DeepSeek-7B-Chat drops to 35.3% precision, its leading components dominated by structural rather than stylistic variance. Simple PCA over a model's own decoding variance is thus an effective, low-cost probe of stylistic structure in LLM representations, one that also exposes sharp cross-model differences in how that structure is organized.

cs.CL · cs.LG

版本更新 · v2arXiv:2609.20797

The Strong Secretary Conjecture is True for Linear Matroids

Kristóf Bérczi, Shaddin Dughmi, Vasilis Livanos, José A. Soto, Victor Verdugo

原文摘要

We prove a $1/e$ guarantee for Matroid Secretary on linear matroids: each element of a fixed optimal basis is selected with probability at least $1/e$. This settles the strong secretary conjecture for this class of matroids. Our result holds both when the matroid is known in advance and when a linear representation is given online. In the known-matroid model, the result extends to fully modular extendable matroids. We also obtain $1/e$ guarantees for a more general model on linear matroids, both when the matroid is known and when its representation is revealed online. In XOS Matroid Secretary, agents with XOS valuations over the elements arrive in uniformly random order, and the algorithm must assign each arriving agent a bundle of elements. The bundles must be pairwise disjoint, and their union must be an independent set of the matroid. We obtain an expected total value of at least $1/e$ times the offline optimum. This model contains Group Matroid Secretary, in which the elements are adversarially partitioned into groups that arrive in uniformly random order, and the algorithm selects a subset of each arriving group. For this special case, we select each element of a fixed optimal basis with probability at least $1/e$

cs.DS

版本更新 · v2arXiv:2610.34855

DecoyCount: Evaluating Visual-Reasoning Misalignment in Counting

Qiuyi, Zhang, Zhen Xu, Jing Gu, Seojin Bang, Arnav Mohanty Das, Yaning Hu, Gautam Kumar 等 17 位作者

原文摘要

Visual counting benchmarks report whether vision-language models produce the correct number, but not whether errors arise from perception or reasoning. We introduce DecoyCount, a benchmark built from 1,586 real-world images with designed decoys across seven mechanisms, along with paired prompts: a neutral question, a matched alignment cue, and a novel multi-hop, multi-image question that situates the same counting problem in a realistic scenario. Using this design, we find that counting failures are induced partly by visual misalignment: models can execute the intended counting process when cue-guided but fail to select it unaided, and we term this difference in accuracy the reasoning-alignment gap. Despite being highly capable on general reasoning, frontier models remain below 50% accuracy on our benchmark, while alignment gaps range from 12.1-22.1 percentage points; strikingly, we observe that more capable models, greater thinking budgets, and agentic processes often induce larger gaps. Because humans may bring context that models lack, we test whether textual underspecification contributes to misalignment using a scenario-based multi-hop condition without explicit hinting, but this added context does not improve aggregate performance. Our analysis concludes that stronger general reasoning does not by itself generalize to aligned visual reasoning, leaving misalignment with human visual expectations as a substantial component of the remaining deficit. DecoyCount and the evaluation code are released at https://github.com/elorian-ai/decoycount.

cs.AI · cs.CV

版本更新 · v3arXiv:2512.02458

Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration

Zhongyi Cai, Yi Du, Chen Wang, Yu Kong

原文摘要

Embodied agents are expected to assist humans by actively exploring unknown environments and reasoning about spatial contexts. When deployed in real life, agents often face sequential tasks where each new task follows the completion of the previous one and may include infeasible objectives, such as searching for non-existent objects. However, most existing research focuses on isolated goals, overlooking the core challenge of sequential tasks: the ability to reuse spatial knowledge accumulated from previous explorations to guide subsequent reasoning and exploration. In this work, we investigate this underexplored yet practically significant embodied AI challenge. Specifically, we propose 3DSPMR, a 3D SPatial Memory Reasoning framework that utilizes Field-of-View (FoV) coverage as an explicit geometric prior. By integrating FoV-based constraints, 3DSPMR significantly enhances an agent's memory, reasoning, and exploration capabilities across sequential tasks. To facilitate research in this area, we further introduce SEER-Bench, a novel Sequential Embodied Exploration and Reasoning Benchmark that spans two foundational tasks: Embodied Question Answering (EQA) and Embodied Multi-modal Navigation (EMN). SEER-Bench uniquely incorporates both feasible and infeasible tasks to provide a rigorous and comprehensive evaluation of agent performance. Extensive experiments verify that 3DSPMR achieves substantial performance gains on both sequential EQA and EMN tasks.

cs.CV

版本更新 · v3arXiv:2604.23853

ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation

Boqin Yuan, Yue Su, Renchu Song, Sen Yang, Jing Qin

原文摘要

Skill-distillation pipelines learn reusable rules from LLM agent trajectories, but they lack a key signal: how much each step costs. Without per-step cost, a pipeline cannot distinguish adding a missing step to fix a bug from removing an expensive step that never affected the outcome. We use the cost-attribution gap to ask whether the rule types inside a distilled skill transfer the same way to new tasks. ClawTrace records cost-attributed agent traces and compiles each session into a TraceCard; CostCraft reads TraceCards and writes three kinds of skill patches: preserve, prune, and repair. We find a pattern aggregate metrics hide. On 30 held-out SpreadsheetBench tasks across two seeds, removing prune patches roughly tripled the quality-regression count without lowering median cost. Across the full 84-task SkillsBench transfer, CostCraft saves no aggregate cost. All three quality regressions trace to the preserve lane, and both quality wins trace to the prune lane: prune patches act as quality guardrails while preserve patches drive regressions. We argue that reusable agent skills should be evaluated at the rule-type level, not as monolithic instruction packages. To support this, we release ClawTrace, the TraceCard schema, and the full set of typed skills.

cs.AI

版本更新 · v3arXiv:2608.26515

Sharp Minimax Regret for Infinite-Memory Logistic Prediction

Vaneet Aggarwal

原文摘要

We study sequential prediction of binary marks whose log-odds are a linear function of all past inputs. The inputs are independent uniform signs. The coefficient of the input observed $j$ steps earlier is unknown, but its absolute value is at most a known number $r_j$, and $\sum_j r_j\le B$. A learner is judged by its expected cumulative log loss in excess of the loss of the true conditional probabilities. We show that for every such sequence $r$ and every horizon $T$, the minimax value of this regret lies between $c\,Γ_T(r)/\max\{1,B^2\}$ and $\frac12Γ_T(r)$, where $Γ_T(r)=\sum_{j\le T}\log(1+(T-j+1)r_j^2)$ and $c$ is an absolute constant. The term for lag $j$ combines the size bound $r_j$ with the number $T-j+1$ of rounds in which that lag influences a prediction, and no monotonicity or other regularity of $r$ is needed. The upper bound is attained by a Bayesian mixture with independent Gaussian priors. For the lower bound, we apply the van Trees inequality at each prediction step and then bound the expected log-determinant of the random matrix whose rows are the lagged input vectors. We also characterize when $\frac12$ is the exact leading constant: for envelopes with a common bound $B$, possibly changing with $T$, the regret is asymptotic to $\frac12Γ_T(r)$ if and only if $\sum_{j\le T}\min\{1,(T-j+1)r_j^2\}=o(Γ_T(r))$. This gives, for example, $\log^2(A^2T)/(8α)$ for $r_j=Ae^{-αj}$, whereas for $r_j=Aj^{-s}$ with $s>1$ the regret is of order $T^{1/(2s)}$ and its ratio to $Γ_T(r)$ stays below $\frac12$. Finally, for a known horizon, an online Newton predictor with features scaled by $r_j$ attains regret of order $Γ_T(r)$ with polynomial computation per round.

cs.IT · cs.LG

版本更新 · v4arXiv:2509.22738

Enabling Approximate Joint Sampling in Diffusion LMs

Parikshit Bansal, Sujay Sanghavi

原文摘要

In autoregressive language models, each token is sampled by conditioning on all the past tokens; the overall string has thus been sampled from the correct underlying joint distribution represented by the model. In contrast, masked diffusion language models generate text by unmasking tokens out of order and potentially in parallel. Generating an overall string sampled from the correct underlying joint distribution would (again) require exactly one token unmasking in every full-model forward pass. The more tokens unmasked in parallel, the further away the string is from the true joint; this can be seen in the resulting drop in accuracy (but, increase in speed). In this paper we devise a way to {\em approximately} sample multiple tokens from the joint distribution in a single full-model forward pass; we do so by developing a new lightweight single-layer ``sampler" on top of an existing large diffusion LM. One forward pass of the full model can now be followed by multiple forward passes of only this sampler layer, to yield multiple unmasked tokens. Our sampler is trained to mimic exact joint sampling from the (frozen) full model. We show the effectiveness of our approximate joint sampling for both pretrained-only (Dream-7B-Base, Llada-7B-Base) and instruction-tuned (Dream-7B-Instruct, Dream-7B-Coder) models on language modeling and math \& coding tasks. When four tokens are unmasked for each full-model denoising step, our sampling algorithm achieves a MAUVE score of 0.87 (vs marginal baseline of 0.31) with respect to the true joint distribution.

cs.CL · cs.LG

版本更新 · v2arXiv:2609.16222

How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning

Max W. Shen, Mark Goldstein, Zichu Wang, Aahlad Puli, Rajesh Ranganath

原文摘要

Stopgrads are widely used in training machine learning models, but stopgrads can alter the gradient, stationary points and convergence guarantees of the original objective, which can make stopgrad training theoretically ungrounded. We introduce a stopgrad regression principle, which identifies a general template for stopgrad objectives with a closed-form characterization of stationary points and their uniqueness, unifying stopgrad objectives for flow maps, reinforcement learning, and diffusion samplers. We provide theoretical grounding for optimizing stopgrad flow map objectives by showing their unique stationary point is the true flow map, and showing positive convergence results for Eulerian and Lagrangian objectives, including MeanFlow and improved MeanFlow. Remarkably, we show that under functional semi-gradient flow, the learned flow map has a closed-form expression composing the initial flow map and the true flow map. We additionally use our stopgrad regression principle to propose modified stopgrad placements for flow map objectives which reduce training memory by 2x.

cs.LG

版本更新 · v3arXiv:2605.30778

Closed-Loop Object-Informed Control for Non-Prehensile Robot Manipulation

Nikola Raicevic, Hyomuk Kim, Shahid Mulla, Hyungjun Doh, Bharath Raam Radhakrishnan, Chenbin Yu, Ki Myung Brian Lee, Nikolay Atanasov

原文摘要

Non-prehensile robot manipulation is challenging due to discontinuous, long-horizon interactions between the robot and the objects it manipulates. Sampling-based model predictive control methods are effective with discontinuous contact but face challenges with finding promising trajectories in long-horizon planning. We propose a closed-loop object-informed (CLOI) method that splits the problem into object-level planning to find long-horizon object poses that lead the object to its goal, and robot-level planning to select robot actions that follow those poses. We use model predictive path integral (MPPI) control to solve the subproblems and couple their solutions through consensus on the object poses using the alternating direction method of multipliers (ADMM). The object plan is revised toward robot-realizable object trajectories, while the robot plan is aligned with the object poses the task requires. In planar pushing tasks with obstacles using an xArm6 manipulator, CLOI increases the success rate by 35% in simulation and 43% on hardware, compared to standard MPPI given the same computational budget.

cs.RO

版本更新 · v2arXiv:2605.29059

SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers

Kaihua Qin, Dawn Song, Arthur Gervais

原文摘要

Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studies use narrow datasets, inconsistent metrics, and limited semantic consistency checks. This gap is increasingly important as large language models (LLMs) begin to generate source-like Solidity that may compile and appear plausible, even when its semantics diverge from the original contract. We introduce SCDBench, a dataset and benchmark methodology for LLM-based smart contract decompilation. The dataset contains 600 real-world Solidity contracts with paired bytecode inputs, ground-truth source code, and replayable semantic checkpoints. SCDBench evaluates decompiler outputs through four cumulative stages: format completeness, compilability, Application Binary Interface (ABI) recovery, and semantic consistency via differential replay. We evaluate Claude Opus 4.7, GPT-5.3-Codex, and GLM-5 in a zero-shot decompilation setting, including GLM-5 variants with and without extended reasoning and a zero-shot compilation-repair setting. The results show that frontier LLMs can often produce structured and compilable Solidity, but achieving semantic consistency remains far from solved: the best-performing frontier model perfectly decompiles only 42/600 contracts. We further show that introducing same-model compilation repair substantially improves performance at modest additional cost. SCDBench establishes a common ground for rigorous, reproducible evaluation and aims to accelerate the development of reliable smart contract decompilers for blockchain security and transparency.

cs.SE · cs.AI · cs.CR

版本更新 · v3arXiv:2609.04748

Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving

Aditi Patodiya

原文摘要

Major open-source serving stacks reuse the key-value tensors of a shared prefix by default. We measure what this prefix reuse costs in reproducibility. Holding model, decoding, seed and request order fixed at batch size one, we ran an eighty-episode multi-turn agentic tool-use workload with prefix reuse on and off across two engines and four weight formats. Without prefix reuse, repeated runs reproduced every token and log-probability in all ten configurations. With it, cache-hit and recompute paths diverged on both engines. On llama.cpp with GGUF weights this path divergence rises with quantization: for Qwen2.5-7B over ten independent server histories, it reached 37.4 percent of episodes at 16-bit and 82.5 percent at four-bit. Near-tie decisions became only about 1.2 times as common, while the cache-path change in top-two margins grew 4.9-fold from 16-bit to three-bit. Serving four-bit weights through 16-bit kernels left divergence not detectably different from 16-bit, placing the amplification mainly in the quantized execution path. At Q4_K_M, run-to-run divergence came mainly from llama.cpp's server-level prompt cache: under the canonical episode order it moved divergence by 37.5 points, and at its default, divergence spanned 20.0 to 28.7 percent under five random orders. With cache state restored, each path reproduced exactly while the two still differed. In the tested stacks, cached serving is irreproducible because the cache state is absent from the request and not reset by default. A single-turn bridge shows path divergence reaching task outcomes with no detectable net change in accuracy. We release the harness, logs, and analysis pipeline.

cs.SE · cs.DC · cs.LG

版本更新 · v8arXiv:2509.24102

Pragmatic Inference for Improving Social Reasoning Generalization in Large Language Models

Guangliang Liu, Xi Chen, Bocheng Chen, Han Zi, Xitong Zhang, Yuda Chen, Kristen Johnson

原文摘要

Achieving social reasoning, including moral reasoning, cultural awareness, and politeness, is critical for the socially reliable deployment of large language models (LLMs). A key bottleneck is limited generalization: social situations that convey similar social implicatures can be expressed through highly diverse linguistic forms, creating an enormous space of possible situations and posing a substantial computational challenge even for LLMs. From a linguistic perspective, this challenge arises because social reasoning operates at the pragmatic level, requiring a pragmatic inference process to infer social implicatures from a given situation and its underlying social context. Although moral values such as moral foundations are generally considered as the representations of the social context, how to construct the corresponding pragmatic inference steps remains underexplored. Taking moral reasoning as an instance of social reasoning, this paper develops a pragmatic inference approach that enables LLMs to infer moral implicatures by (1) specifying the inferential steps through which LLMs derive moral implicatures from language, and (2) explicitly modeling the metapragmatic links among these inferential steps to bridge the pragmatic gaps between them and make such inferences learnable for LLMs. Experimental results demonstrate that our approach substantially improves LLMs' generalization in moral reasoning, highlighting the potential of pragmatic inference for future social reasoning research.

cs.CL

版本更新 · v7arXiv:2601.03079

Learning to Diagnose and Correct Moral Errors in Large Language Models

Bocheng Chen, Xi Chen, Han Zi, Haitao Mao, Zimo Qi, Xitong Zhang, Yuda Chen, Kristen Johnson 等 9 位作者

原文摘要

Enabling large language models (LLMs) to diagnose and correct moral errors is crucial not only for ensuring their reliable deployment but also for charting a pathway toward continuous improvement. Existing research has primarily followed two directions: fine-tuning LLMs on corpora of morally appropriate texts and developing carefully designed prompting strategies to promote moral behavior, including moral self-correction and self-improvement. However, both lines of work often remain brittle, relying heavily on shallow heuristics rather than enabling LLMs to reason about why and how a given moral discourse is morally (in)appropriate. In this paper, we address this challenge by developing pragmatic inference-driven approach that help LLMs learn to diagnose and correct moral errors. Pragmatic inference is the reasoning process through which implied meanings are derived, a central concept in linguistics. To improve the reasoning efficiency, our approach adapt the inference procedure according to the inferential load required by different moral discourses. Empirical results demonstrate that our method not only improves LLMs' ability to diagnose and correct moral errors, but also generalizes effectively across tasks without relying on shallow heuristics.

cs.CL

版本更新 · v2arXiv:2611.00422

A Spectral Renormalization-Group View of Learning

Charles H. Martin

原文摘要

We study how the layers in deep neural networks (NNs) converge, using Wilsonian Renormalization-Group (RG) ideas to organize the spectral picture. During training, these layers often develop heavy-tailed power-law (PL) spectra, and the strongest checkpoints often appear near the PL exponent $α\approx 2$. This pattern raises a simple question: why should this value mark a well-trained layer? The answer is both statistical and physical. Our statistical hypothesis is that $α=2$ marks the boundary between stable if not optimal learning and overfitting via non-self-averaging. The physical answer is that the same value makes the spectral energy gain scale evenly across logarithmic spectral scales, which is the proposed Wilsonian marginal condition. We then apply the ERG trace-log condition, the proposed SETOL theory, which we justify by taking volume-preserving, scale-invariant transformations to remove arbitrary layer scale along the proposed RG flow. The resulting spectral RG flow connects the HTSR and SETOL theories to optimizers such as Muon, and motivates a new optimizer extension, WW-PGD. Together, these results point toward a spectral Renormalization-Group view of learning, in which NNs may approach shared spectral structure in the settings studied here.

cs.LG · cond-mat.dis-nn · cs.AI

版本更新 · v5arXiv:2509.00761

L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit

Boqin Yuan, Ziqi Wang

原文摘要

Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy. This measure overlooks a common failure: whether the citation source attached to an answer exists and supports the rule the system attributes to it. We present L-MARS, an open multi-agent legal QA system with agentic search and judge-driven evidence checks, and audit it claim by claim against its cited source. Each atomic claim is labelled with a six-class taxonomy and scored with strict-ALCE under cross-provider judging, where the answerer and verifier come from different model families. On a stratified 100-question Bar Exam audit, retrieval barely moves accuracy, yet the multi-turn judge loop lifts strict citation F1 from 0.13 (naive RAG) to 0.25 and cuts the no-citation rate from 34% to 13%. We further introduce Faith-Search, a post-draft step that re-verifies and repairs unreachable citations; it drops the unreachable rate below 1% but does not improve F1 over the multi-turn loop, so we report it as a targeted reachability intervention rather than a faithfulness breakthrough. A 50-question LegalSearchQA case study confirms the picture: retrieve-then-draft pipelines saturate near 0.75 citation F1, while a single-agent web-search baseline collapses to 0.22 under external audit.

cs.AI · cs.CL

版本更新 · v3arXiv:2607.00642

Coachable Agents for Interactive Gameplay

Roberto Capobianco, Harm van Seijen, Nolan D. Bard, Neil Burch, Fatima Davelouis, Josh Davidson, Alisa Devlic, Yunshu Du 等 41 位作者

原文摘要

Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing (Silver et al., 2016; 2017; Wurman et al., 2022) to robotics (Levine et al., 2016; Andrychowicz et al., 2020; Luo et al., 2025; Dürr et al., 2026) to foundation models (Ouyang et al., 2022; Noukhovitch et al., 2024; Sun et al., 2024; Guo et al., 2025). Through trial and error, these AI systems typically learn a single, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, after training is completed, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning algorithms, and data augmentation to create a framework for coaching agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA video games Horizon Forbidden West and Gran Turismo, and in an open-source humanoid test domain. Despite the different nature of the domains--car racing, stylized game combat, and humanoid walking--each agent shows strong coherence to the style requests while still satisfying the main task in its domain. Importantly, the techniques outlined in this paper allow an end user to choose the final behavior at run time, giving them flexible control over the final executed performance.

cs.AI · cs.LG

版本更新 · v2arXiv:2611.02236

Iterative Gumbel Planning for Continuous Control

Shaohuai Liu, Weirui Ye, Yilun Du, Le Xie

原文摘要

Search-based planning remains a powerful policy improvement paradigm in reinforcement learning, driving milestone successes in discrete domains. However, extending this paradigm to continuous control exposes a structural mismatch: search evaluates a finite set of action candidates, whereas continuous RL typically relies on Gaussian policies. We show that winner-action distillation into a continuous Gaussian induces a \textit{projection error} and a stepwise variance-expanding gradient tendency when the selected action is sufficiently far from the current mean. Empirically, this tendency is associated with elevated terminal variance and a return gap on the evaluated tasks. To address this, we propose \textbf{Iterative Gumbel Planning (IGP)}. By adopting a per-dimension factorized categorical policy, IGP naturally aligns the policy support with the search candidates, eliminating the projection error and reducing the residual approximation to a bounded discretization error. To bypass the combinatorial explosion of high-dimensional discrete action spaces, IGP pairs Gumbel Top-$K$ candidate sampling with an MPPI-style multi-round iterative search to refine the policy at each state. Empirically, IGP achieves state-of-the-art aggregate performance and sample efficiency on DMControl and HumanoidBench. Furthermore, it produces more stable action sequences with lower temporal variance, demonstrating its practical potential for real-world robotic deployment.

cs.LG · cs.AI

版本更新 · v3arXiv:2606.23276

Exposing the Illusion of Erasure in Knowledge Editing for LLMs

Advik Raj Basani, Anshuman Chhabra

原文摘要

Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood. In this work, we examine KE from an adversarial elicitation perspective, revealing that edited knowledge is often not fully erased and continues to surface, with consistent failures observed across diverse model architectures. To explain this behavior, we conduct a mechanistic analysis of popular KE methods. We show that low-rank updates do not overwrite existing knowledge but instead redistribute it within the model's representation space. Furthermore, we find that these methods act as targeted suppression mechanisms that reduce the likelihood of expressing original facts, rather than removing them from the model. Analysis of the loss landscape reveals that edited knowledge lies in narrow, anisotropic regions that are highly sensitive to perturbations, making them highly vulnerable to indirect prompting and adversarial attacks. By exposing these profound architectural vulnerabilities, our work proves that KE algorithms are inherently bypassable and motivates a fundamental reevaluation of how we deploy post-hoc updates in several LLM applications.

cs.LG · cs.AI · cs.CR

版本更新 · v3arXiv:2507.09608

prNet: Data-Driven Phase Retrieval via Stochastic Refinement

Mehmet Onurcan Kaya, Figen S. Oktem

原文摘要

Phase retrieval is an ill-posed inverse problem in which existing methods often struggle to balance reconstruction fidelity and perceptual quality. We propose a novel Langevin-based framework for phase retrieval that bridges model-driven and data-driven approaches by combining stochastic posterior sampling, learned denoising, and model-based updates to better navigate the perception-distortion tradeoff. The framework consists of three progressively more advanced variants. The first, prNet-Small, provides a theoretically grounded and lightweight pipeline that integrates Langevin dynamics with learned noise and denoising processes and alternating projection-based updates. Building upon this foundation, prNet-Large exploits parallel sampling of diverse reconstructions and aggregates them to approximate the MMSE solution, significantly improving distortion metrics. Finally, prNet-Large-Adversarial enhances perceptual quality by replacing simple averaging with an adversarially trained aggregation network while preserving reconstruction fidelity. In addition, we incorporate test time augmentation to further improve the performance. Extensive experiments demonstrate that the proposed framework consistently outperforms classical, deep learning-based, and diffusion-based baselines across multiple benchmarks in both reconstruction fidelity and perceptual quality. The source code and trained models are available at https://github.com/METU-SPACE-Lab/prNet-for-Phase-Retrieval

eess.IV · cs.CV