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

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 05:40 — 2026-11-17 05:40(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:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58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。

24,106 已收录论文20,158 AI 相关7,049 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 24,106 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v2arXiv:2609.37151

FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network

Haitao Wang, Chenjing Liang, Haipeng Zhang, Jiawei Hu, Sicheng Wang, Songzhu Mei, Chenglu Wen, Siqi Shen 等 9 位作者

原文摘要

Automated multi-agent systems offer clear advantages over manually designed ones in scalability and adaptability, but existing workflow topology methods still face important limitations. Search-based methods are often computationally expensive, textual-gradient-based methods rely on coarse-grained feedback, and existing generation-based methods are not well suited to discrete workflow topologies with complex dependencies. To address these limitations, we propose FlowMAS, a multi-agent workflow topology method based on Generative Flow Networks (GFlowNets). FlowMAS models workflow generation as reward-guided flow over the topology space and introduces three components: a GFlowNet-based topology generation backbone, a curiosity-driven module for structure-aware exploration, and an information-guided optimization module for evaluating intermediate topologies. Concretely, the curiosity-driven module encourages exploration of structurally novel workflows, while the information-guided module measures both the information contribution and the communication efficiency of different operators to favor more informative and effective collaboration patterns. Experiments on six benchmark datasets with three LLM backbones show that FlowMAS consistently outperforms multiple baselines.

cs.MA

版本更新 · v3arXiv:2605.14084

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

Mingzhi Zhu, Michele Merler, Raju Pavuluri, Stacy Patterson

原文摘要

Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary but misaligned. The Instruct model is concise and tool-disciplined, whereas the Thinking model offers stronger planning and recovery behavior but often over-deliberates and degrades agent performance. We present CRANE (Constrained Reasoning Injection for Code Agents via Nullspace Editing), a training-free parameter-editing method that treats the Thinking-Instruct delta as a directional pool of candidate reasoning edits for the Instruct backbone. CRANE combines magnitude thresholding to denoise the delta, a Conservative Taylor Gate to retain edits that are jointly beneficial for reasoning transfer and tool-use preservation, and Graduated Sigmoidal Projection to suppress format-critical update directions. By merging paired Instruct and Thinking checkpoints, CRANE delivers strong gains over either individual model while preserving Instruct-level efficiency: on Roo-Eval it achieves pass1 of 66.2% (+19.5%) for Qwen3-30B-A3B and 81.5% (+8.7%) for Qwen3-Next-80B-A3B; on SWE-bench-Verified it resolves up to 14 additional instances at both scales (122/500 and 180/500); and on Terminal-Bench v2 it improves pass1/pass5 by up to 2.3%/7.8%, reaching 7.6%/17.9% and 14.8%/30.3%, respectively, consistently outperforming alternative merging strategies across all three benchmarks.

cs.SE · cs.AI · cs.CL

新论文 · v1arXiv:2611.10445

DiSARM: Diverse and Surprising Association Rule Mining with Large Language Models

Lijia Liu, Hisashi Kashima

原文摘要

Exploratory Data Analysis (EDA) aims to discover informative patterns in large datasets. For transactional data, Association Rule Mining (ARM) is an established approach that facilitates EDA by efficiently generating candidate patterns. Beyond efficient mining, identifying informative rules has also been extensively studied through both objective and subjective interestingness measures. Recent advances in Large Language Models (LLMs) offer new opportunities for assessing subjective interestingness using world knowledge. Nevertheless, relying solely on LLMs raises concerns about scalability and statistical reliability. Building on prior ARM research, we propose a hybrid framework, DiSARM, that leverages the world knowledge of LLMs to assess the subjective interestingness of rules, while maintaining statistical reliability and promoting diversity among the selected rules. Across three transactional datasets, experiments demonstrate that DiSARM effectively combines statistical reliability with surprise and diversity, offering a promising approach to ADE from transactional data.

cs.AI · cs.LG

版本更新 · v7arXiv:2603.13334

Lipschitz-Based Robustness Certification Under Floating-Point Execution

Toby Murray

原文摘要

Lipschitz-based certification checks a neural network's robustness with a small numerical computation: milliseconds per input, and small enough to be formally verified. Its soundness is proved for execution in real arithmetic, whereas deployed networks execute in floating point, so rounding must be accounted for in the network and in the certifier itself. We show that the conservatism of Lipschitz-based certification does not absorb the rounding in the network's execution: we exhibit counterexamples to a formally verified real-arithmetic certifier that computes in exact arithmetic, and show that an adversary who controls the weights can make it issue false certificates for ordinary test images at standard perturbation bounds. We present the first Lipschitz-based certification method that is both efficient and sound with respect to floating-point execution. It keeps the real-arithmetic network's Lipschitz constant and bounds separately how far the floating-point outputs can depart from the real-arithmetic ones, through a compositional theory of the deviation that also rules out overflow; pre-deployment measurements of a high-precision execution tighten the bound. Its spectral norms come from a float64 Gram iteration proved never to under-estimate the true norm. We mechanise the theory in Rocq and implement it in a certifier, evaluated on dense image, tabular and many-class classifiers. It rejects every certificate a counterexample refutes and certifies entire test sets at milliseconds per instance on a CPU, losing relatively few real-arithmetic certificates, many of which the measurement reclaims. At float32, ERAN's GPUPoly, to our knowledge the only other public floating-point-sound verifier for networks of our size, loses most of its certificates on most of our models to its own rounding accounting; ours does not, and is more than an order of magnitude faster.

cs.LG · cs.CV · cs.PL

新论文 · v1arXiv:2611.10443

Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models

Jungin Park, Chaoran Zhu, Changjae Oh, Kwanghoon Sohn

原文摘要

Understanding three-dimensional physical structure has become essential for vision-language-action models (VLAs). However, existing approaches either rely on explicit geometric inputs at inference time or adopt a single visual pathway, potentially compromising the visual-semantic knowledge inherited from pre-trained models. We present SPARK-VLA, Spatial Representation distillation and Knowledge routing for VLAs, a preserve-specialize-route framework for spatially adapting VLAs without requiring external 3D inputs or experts at inference. SPARK-VLA consists of two key components: (1) spatial representation distillation, which transfers 3D understanding from a frozen 3D expert to a LoRA-adapted visual branch by aligning attention responses while preserving the original visual pathway, and (2) a lightweight knowledge router, which selectively forwards action-relevant visual tokens to the language model using routing supervision derived from action-loss gradients. Across LIBERO, LIBERO-Plus, CALVIN, and real-world manipulation, SPARK-VLA achieves strong performance with only a 0.5B language backbone and approximately 53M trainable parameters, providing an effective and parameter-efficient approach to 3D-aware VLA learning. Code is available at https://github.com/park-jungin/spark-vla.

cs.RO

版本更新 · v2arXiv:2605.17997

MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization

Le Su, Xing Luo, Zhi Jin

原文摘要

Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit Post-Training Quantization (PTQ) by introducing cross-module residuals to reduce error accumulated from previous modules. However, these residuals may also introduce additional bias arising from the Hessian-Approximation (HA) assumption, resulting their two-sided effect and potentially leading to suboptimal quantization performance. Therefore, in this work, we propose a residual regulation strategy to mitigate the HA bias associated with residual strength, while preserving accumulated-error correction. Furthermore, we observe that this two-sided effect is module-dependent, we futher propose a Module-Adaptive Residual Reconstruction (MARR), which assigns a module-specific scaling coefficient to adaptively balance accumulated-error correction and residual-related HA bias for each module. To avoid exhaustive per-module coefficient search and obtain a stable coefficient estimate, we design an Proportional-Integral-Derivative (PID)-based update strategy that employs reconstruction error as feedback to progressively refine this coefficient. Experiments on several typical Large Language Models (LLMs) and Vision Transformers (ViTs) demonstrate the effectiveness of MARR under low-bit quantization ($\leq$4-bit), achieving up to 20.2\% perplexity reduction on LLMs and up to 4.6\% accuracy gains on ViTs over the residual reconstruction baselines. Code will be made publicly available upon acceptance.

cs.LG · cs.AI · cs.CV

新论文 · v1arXiv:2611.10440

Lower Bounds Above $\sqrt{3}$ for Online Makespan Minimization on Four Identical Machines

Maximilian Janke

原文摘要

For deterministic online makespan minimization, $m = 4$ identical machines is the smallest case whose optimal competitive ratio is open: it is known only to lie between $\sqrt{3} \approx 1.73205$ and $26/15 \approx 1.73333$. We prove a lower bound of $14383/8304 \approx 1.73206$ using a single branching layer, and refine the construction with a second, mirrored branching layer to obtain $14350/8283 \approx 1.73246$, closing about a third of the gap. Our constructions are the first branching adversaries for $m = 4$ machines, and the first explicit lower bounds for online makespan minimization in which the adversary presents jobs in non-monotone order of size.

cs.DS · math.OC

新论文 · v1arXiv:2611.10439

Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction

Yunzhe Wang, Mesut Erhan Unal, Sheng Zhang, Shabnam Ghadar, Peng Tang

原文摘要

Self-evolving agents improve their own skills, memory, and harness code from experience without retraining the base LLM, and group-evolving agents go further by sharing these lessons across agents. Yet most such systems overlook that sharing across users and heterogeneous agents requires deciding who can benefit from each lesson and what information must remain private. We present MixUA, a memory system that distills independent user-agent trajectories into lessons and assigns each lesson to a user-agent pair, user, agent, or global scope according to whom it benefits and what it may disclose. For evaluation, we introduce CrossLearnBench, a mixed-user-agent benchmark that pairs established agent tasks with user preferences and privacy probes that test whether private facts leak into memory other users can read. With five users and seven agents, MixUA raises pass rates by up to 16 points over no memory and 5 over a single global memory, even on tasks previously tried only by other users on other agents. It retains up to 90% of previously stated preferences, and at most 0.02% of privacy probes find a planted private fact in a forbidden scope. We hope MixUA offers a scalable path toward a global system where users and agents co-evolve.

cs.CL · cs.AI · cs.LG · cs.MA

版本更新 · v3arXiv:2601.10560

LAMaS: A Modular Platform for Learning Low-Latency Multi-Agent Orchestration

Xi Shi, Mengxin Zheng, Qian Lou

原文摘要

In a multi-agent system (MAS), removing an expensive agent call can save tokens without making the answer arrive sooner: latency depends on the longest chain of dependent calls. We present Latency-Aware Multi-agent System (LAMaS), a modular platform for learning low-latency orchestration. A framework can send a query to LAMaS and receive an answer and execution trace, or keep its own graph builder and use the platform's latency-optimized orchestration layer. During training, the layer gives operators on the critical path the greatest latency penalty while targeting a floor on expected accuracy. During inference, a lightweight controller uses partial results to decide whether to skip work that has yet to start. Across four benchmarks, LAMaS reduces end-to-end latency by over 50% relative to the evaluated learning-based MAS baselines while maintaining competitive or better accuracy. GDesigner and AgentDropout retain their graph builders and train the controller on their own traces; both achieve lower latency across the same benchmarks.

cs.MA · cs.AI · cs.CL

版本更新 · v2arXiv:2511.22688

Test-time scaling of diffusions with flow maps

Amirmojtaba Sabour, Michael S. Albergo, Carles Domingo-Enrich, Nicholas M. Boffi, Sanja Fidler, Karsten Kreis, Eric Vanden-Eijnden

原文摘要

A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics of the diffusion itself. This procedure is often ill posed, as user-specified rewards are usually only well defined on the data distribution at the end of generation. While common workarounds to this problem are to use a denoiser to estimate what a sample would have been at the end of generation, we propose a simple solution to this problem by working directly with a flow map. By exploiting a relationship between the flow map and velocity field governing the instantaneous transport, we construct an algorithm, Flow Map Trajectory Tilting (FMTT), which provably performs better ascent on the reward than standard test-time methods involving the gradient of the reward. The approach can be used to either perform exact sampling via importance weighting or principled search that identifies local maximizers of the reward-tilted distribution. We demonstrate the efficacy of our approach against other look-ahead techniques, and show how the flow map enables engagement with complicated reward functions that make possible new forms of image editing, e.g. by interfacing with vision language models.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10435

Multi-Objective Adaptation After Deployment: A Position on World Models for Remote Robot Teams

Jamie Santos, Kagan Tumer

原文摘要

Autonomous robot teams deployed in remote, unstructured environments may face changes in the environment, hardware, and team composition that degrade previously effective policies. Shifting mission objectives can be handled by selecting a different solution from an existing Pareto set, but shifting deployment conditions can reorder the set itself, making previously dominated policies competitive or new policies necessary. However, evaluating these policies in new contexts while minimizing risk to the hardware remains an open problem. We argue that, although largely untested in this domain, world models merit investigation for post-deployment multi-objective adaptation. By predicting policy outcomes under updated estimates of current conditions, world models could enable teams to re-evaluate existing policies without physically executing each candidate, provided predicted performance changes reflect those realized on deployed systems. We identify research priorities for model-based policy re-evaluation, validation of predicted against realized performance, and incorporating shared information into world models to support coordinated team adaptation.

cs.RO

版本更新 · v4arXiv:2511.14718

Natural Language Interfaces for Databases: What Changes for SQL-Literate Users?

Panos Ipeirotis, Haotian Zheng

原文摘要

Natural Language Interfaces for Databases (NLIDBs) let users query data in everyday language instead of SQL, and modern systems translate most questions accurately. Does an NLIDB remove the work of querying, or move it? We compared SQL-LLM, a GPT-4o-backed NLIDB, with Snowflake, a manual-SQL platform. Twenty SQL-literate professionals and graduate students, ten per interface, each completed 12 BIRD benchmark tasks with hints naming target columns and operators. SQL-LLM cut completion time per query by 31%. It did not improve accuracy: SQL-LLM users answered 46% of queries correctly versus 64% for Snowflake, a gap this sample cannot confirm ($p = 0.08$) that narrows to 14 points without one session where the system timed out. Think-aloud audio from 11 participants (4 SQL-LLM, 7 Snowflake) showed how the work shifted: SQL-LLM users left initial schema navigation to the model, mainly on easier tasks, and focused on checking the generated SQL, while Snowflake users explored the schema and wrote queries by hand. Coded behavior rates did not differ detectably between arms, and positive remarks during a task did not reliably predict a correct answer. The evidence fits a reallocation of querying work, not its removal: users still had to check the generated SQL.

cs.DB · cs.HC

版本更新 · v2arXiv:2609.18128

Symbolic Temporal Supervision of LLM Agents Using Contracts

Yifeng Xiao, Johnna Liu, Pierluigi Nuzzo

原文摘要

Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orchestration, by acting on external systems through tool calls. However, hallucinations, distributional instability, and adversarial manipulations in LLMs, and the irreversible consequences of certain tool calls can lead to harmful outcomes. These risks call for safeguards that can check requirements across a trajectory, both before actions execute and when recorded behavior is evaluated. We present ContrAgent, a contract-based framework for symbolic temporal supervision of LLM agents. ContrAgent captures an agent's behavior as a sequence of tool calls and formalizes it as a trace over a fixed set of checkable predicates. It then specifies required behaviors using assume-guarantee contracts in linear temporal logic over finite traces (LTL$_f$). Each contract is compiled to a deterministic finite automaton (DFA) that serves two roles: gating agent actions online and evaluating recorded traces offline. A contract library, acting as a reusable knowledge base, is maintained independently of the agent's model and can be applied across different agents within the same task domain. We show the effectiveness of our approach on four benchmarks spanning both roles, where ContrAgent is competitive with LLM-judge, classifier, and guardrail baselines while producing deterministic, reproducible verdicts and, in the online mode, orders of magnitude lower per-call latency.

cs.AI · cs.LO

版本更新 · v2arXiv:2605.13450

Do Semantic Distance Tests Actually Predict Creativity in LLMs? Evidence for Jagged Creativity

Samuel Schapiro, Alexi Gladstone, Jonah Black, Heng Ji

原文摘要

Measuring the creativity of large language models (LLMs) is essential for designing methods that can improve creativity and for enhancing our scientific understanding of this ability. To accomplish this, it has become common in recent years to administer semantic distance tests of human creativity to LLMs. Although these tests provide a convenient and fully automated way to score aspects of "creativity," their validity as measures of machine creativity has not been established. To address this problem, we conduct the first large-scale, systematic study assessing the effectiveness of semantic distance tests for predicting the creative achievement of LLMs across four target constructs: (a) creative writing, (b) output diversity on open-ended prompts, (c) combinatorial creativity, and (d) scientific ideation. We score each test on two criteria (validity and specificity), and derive a theoretical limit for the maximum attainable specificity and validity a test can achieve. We find that: (1) No test is a significant predictor of output diversity, suggesting that point creativity, the ability to produce a single response connecting semantically distant concepts, and distributional creativity, the ability to produce distinct responses across repeated samples, may dissociate in current LLMs--a pattern we call jagged creativity. (2) The Remote Associates Test is effectively a proxy for general capabilities rather than a specific predictor of creativity in LLMs. (3) Lastly, the Divergent Association Task is the best predictor of creative writing, but no single test predicts all constructs well. In summary, our results prescribe caution when applying psychometric tests and tasks of creativity validated among human populations to LLMs.

cs.AI · cs.CL · cs.HC

版本更新 · v2arXiv:2607.13298

FOLIO: Focused Semantic Memory for Streaming Video Understanding

Haoyang Fan, Dhruv Parikh, Anvitha Ramachandran, Sameh Gobriel, Nilesh Jain, Rajgopal Kannan, Viktor Prasanna

原文摘要

In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time. Because streaming frames grow without bound, the system must continuously compress and retain information from the observed video prefix while future frames and future queries remain unknown. The core challenge is deciding what information to retain and how to organize the maintained history: as this history grows with the stream, memory cost increases and many redundant visual details are retained, whereas later queries often depend on specific entities, actions, and their temporal changes. To address this challenge, we introduce FOLIO, a training-free focused semantic memory system that records important parts of the stream in higher detail while keeping surrounding context compact. As the stream arrives, FOLIO updates memory at the segment level, guided by a dynamic focus state, combining a short-term visual buffer with a long-term semantic memory organized around observed entities and linked to a visual-evidence cache. At query time, lightweight hybrid retrieval combines direct matching over the structured memory with semantic query expansion. FOLIO achieves state-of-the-art performance, reaching 82.0/69.1 Perception/Backward accuracy on OVO-Bench with Qwen3-VL-8B and 74.5 overall accuracy on StreamingBench, while substantially reducing the cost of maintaining streaming memory by reserving detailed records for focused entities and storing surrounding context compactly.

cs.CV

新论文 · v1arXiv:2611.10433

HexIt: Learning Hexahedral Block Decomposition with Expert Iteration on Combinatorial Maps

Arjun Narayanan, Per-Olof Persson

原文摘要

Decomposing a polyhedral solid into a few well-shaped hexahedral blocks is a long-standing open problem in mesh generation. We cast it as a sequential decision problem on a 3-dimensional generalised map: an agent splits edges, faces and volumes with three insert operations until every cell is a hexahedron and the mesh passes a quality threshold, and a policy that convolves over the map's involutions chooses each insert. A successful decomposition takes over a hundred decisions, and a uniformly random policy never finds one. We clone a policy from constructed decompositions and improve it by expert iteration. On held-out chamfered solids that share no boundary topology with the cloning data, the final policy solves an expected $94.4\%$ in $20$ samples, and expert iteration raises the best-of-20 solve rate on large chamfered solids from $0.203$ to $0.355$. At matched compute, PPO, GRPO and VinePPO updates all make the cloned policy worse.

cs.LG · cs.AI · cs.CG

新论文 · v1arXiv:2611.10432

D-REAL: Acceptance-Length Optimization with Unbiased Gradients for Speculative Decoding

Meng Wei, Yefei Chen, Antong Li, Yanan Gao, Xingliang Shi, Xin Gao, Zhiling Ye, Yun Yue 等 10 位作者

原文摘要

Speculative decoding efficiency depends on the number of consecutively accepted draft tokens, yet token-level training objectives do not directly optimize this quantity. We introduce D-REAL (Drafter Reinforcement of Expected Acceptance Length), a post-training method that directly optimizes expected acceptance length for a fixed decoding context. D-REAL weights position-wise draft-target distributional overlap by prefix survival probabilities along a draft-sampled prefix, faithfully capturing the sequential dependence of verification on earlier proposals. By accounting for the parameter dependence of the proposal distribution, we derive an unbiased gradient estimator for this single-round objective under stochastic verification. We evaluate D-REAL on DSpark and DFlash2 with Qwen3-8B as the target model across ten benchmarks. Starting from baselines whose mean acceptance length has plateaued, one epoch of D-REAL post-training consistently improves the benchmark-averaged mean acceptance length by up to 0.23 tokens across both architectures under greedy (T = 0.0) and stochastic (T = 1.0) sampling, translating into up to a 9.4% end-to-end serving throughput improvement.

cs.AI

版本更新 · v2arXiv:2610.17020

CWE-bench: Refocusing Agentic Security from Exploitation to Defense

Gonzalo Gonzalez-Pumariega, Ajay Jagannath, Adit Jain, Guram Gogia, Soumyadeep Bakshi, Nazneen Rajani

原文摘要

Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An attacker needs to exploit only one vulnerability; a defender must find and fix all of them. We introduce CWE-bench, a benchmark of 250 repository audit-and-repair tasks spanning 185 CWE types and eight languages, grouped into ten weakness classes. We release 100 tasks publicly and keep 150 held out. Agents are given a repository to audit and a description of its threat model, but are not told the weakness, where it occurs, or how many vulnerable sites there are. Each patch must block the exploit while preserving original functionality, as checked by a deterministic programmatic verifier. Verifiers were curated with panels of agentic judges and reviewed by hand, so that they reject incomplete repairs without penalizing correct ones. The best agent reaches 67% pass@1 and 79% pass@4. We further conduct analyses showing that (i) agents with similar pass@1 differ widely in retry gains and cost, and (ii) no single agent is best across languages or weakness classes. As the offensive capabilities of agents improve, CWE-bench provides a broad and rigorous measure of whether their defensive capabilities keep pace.

cs.CR · cs.AI · cs.SE

新论文 · v1arXiv:2611.10430

Deploying Physically and Epistemically Compliant Agents by Distilling Belief-Space Task and Motion Planners

Phillip J. K. Christoffersen, Rachel Ma, Patrick Barragán, Dylan Hadfield-Menell

原文摘要

In this work, we train agents to act under uncertainty according to specified, belief-dependent rules. Deep reinforcement learning (RL) can in theory train agents to follow rules if encoded into well-designed rewards, but in practice, RL fails to perfectly optimize these rewards, leading to ineffective or noncompliant agent behavior. Belief-space planners by construction produce behavior in line with developer specification, but require hand-programming online planners and belief-state estimators, adding significant engineering complexity at scale. We combine the two: we plan offline to generate a dataset of sample trajectories and then distill the plans into a policy that acts on raw observations. We propose two changes to planner distillation that address problems specific to history-based policies: Dual Averaging, a loss that combines per-timestep predictive loss and average loss on task changes, and $ρ$-Optimal Reinforcement, a feedback mechanism that reinforces the policy's own successful rollouts when these are near-optimal. We provide a sufficient condition under which static search problems with noiseless observation models is complete, and show that maximum-likelihood-observation planning implies this condition in static search with continuous beliefs. We create a challenging new domain, Scavenger, where an agent needs to gain information in order to succeed. We evaluate our distilled policy in two versions of Scavenger, one where information is provided visually and one where it is provided as a command in natural language. In either case, the learned policy attains a success rate above 90% in Scavenger, compared with at most 5% for RL. We also find that distilled planners transfer with greater than 60% success to following unseen and intentionally vague commands and greater than 75% success to following floorplans larger than those seen in training.

cs.RO · cs.AI

版本更新 · v4arXiv:2608.14529

Polynomial-Factor Deterministic NP-Hardness for SVP in Every $\ell_p$ Norm with $p>2$

Isaac M Hair, Amit Sahai

原文摘要

We prove that for every constant $2<p<\infty$, the shortest vector problem in the $\ell_p$ norm is NP-hard to approximate within a polynomial factor under a deterministic reduction. More precisely, for lattices of rank $M$, we obtain a factor of $M^\varepsilon$ for every constant $0<\varepsilon<\min\{(p-2)/(4p),1/8\}$. For $p=\infty$, the same holds for every constant $0<\varepsilon<1/8$. Our reduction adapts OpenAI's encoding of a satisfying assignment for the closest vector problem ("Ten Advances in Mathematics and Theoretical Computer Science"). The encoding has one block of coordinates for each evaluation of a polynomial, with one position for each possible value. We allow the entries in a block to be arbitrary field elements, which can cancel when we take weighted sums of powers of these values. We show that on an unsatisfiable formula, a nonzero codeword with small support must have many nonzero entries in each block it uses. Applying a Hadamard matrix to each block, as in a work by Hair and Sahai (STOC 2026), gives the gap in vector length. The main results of this paper were discovered by Codex / ChatGPT 5.6 Sol Ultra using harness components from the UCLA Moonshot Harness Project, in response to a general strategy suggested by the authors. See the end of the introduction for a discussion.

cs.CC

新论文 · v1arXiv:2611.10429

Applied bifidelity material response model construction and uncertainty quantification with a sampling hypernetwork

Reese E. Jones, Cosmin Safta, Dan Bolintineau, Craig M. Hamel, Gianluca Geraci, Sharlotte LB Kramer

原文摘要

Multifidelity modeling offers a practical route to accurate prediction and uncertainty quantification when high-fidelity data are scarce but lower-fidelity data are comparatively abundant. This work develops a bifidelity Langevin sampling hypernetwork framework that constructs probabilistic neu- ral response models by learning a posterior distribution over model parameters rather than a single deterministic fit. The method combines a flexible shared-latent data representation for low- and high-fidelity responses, enabling parameter sharing and transfer learning between the fidelities. We introduce several methodological enhancements to improve the robustness and efficiency of this ap- proach, including stability-promoting drift models, staged and conditional training strategies, adap- tive initialization of Langevin trajectories, and training procedures designed to better exploit corre- lations between fidelity levels. These additions improve convergence behavior, reduce the sampling effort required to obtain representative posterior ensembles, and provide more reliable predictive uncertainty in data-limited regimes. The resulting framework makes more effective use of available multifidelity data while preserving interpretability through the learned posterior structure, yielding improved predictive performance, better uncertainty characterization, and a more stable workflow for constructing uncertainty-aware surrogate models. The method is demonstrated on experimental, high-fidelity simulation and illustrative synthetic data.

cs.LG

新论文 · v1arXiv:2611.10425

Governed Self-Improvement for a Local-First Security Analyzer: Baseline Measurements and a Preregistered Evaluation Protocol for Tantular Cyber

Raditio Ghifiardi, Rifny Rachman

原文摘要

Local-first security tools let organizations analyze code without sending it to third-party services, but the small language models they can run locally are weaker than hosted ones and are hard to improve without breaching the privacy guarantee that motivates them. We present Tantular Cyber, an open-source, read-only repository security analyzer that keeps deterministic scanner findings authoritative and confines a locally served language model to advisory explanations in Bahasa Indonesia. We report its measured v0.3.0 baseline on a synthetic, ground-truth benchmark: combining Semgrep with an interprocedural call-graph scanner yields precision 0.843 and recall 0.915 (Semgrep alone: 0.818 and 0.766). The advisory layer is the weak point: 57% of explanations met an evidence-grounding check, against 95% for a different 8B model under identical prompts. A forensic re-scoring of retained outputs shows that every grounding failure cites a code identifier absent from the evidence shown, and that a prompt change which appeared to raise grounding from 0.56 to 0.72 did so partly by citing nothing. We document two evaluation-validity hazards we encountered: silent model-file migration during a run and non-reproducible published figures. Building on these lessons and on constraint-aware evaluation from security operations research, we propose a governed self-improvement loop (code-free feedback, curated data, a cheapest-first intervention ladder from prompts to LoRA and weight-space edits, hard gates, and human release approval) and preregister the protocol by which its first cycle will be judged. We report no results for the loop itself.

cs.CR

版本更新 · v2arXiv:2605.30101

List Recovery for Random Low-Rate Linear Codes

Isaac M Hair, Amit Sahai

原文摘要

We show that random linear codes of fixed dimension $d$ over sufficiently large prime fields have nearly optimal output list size for list recovery. Fix an error fraction $0<α<1$ and $0<\varepsilon<1$. For all sufficiently large block lengths $n$, with probability at least $1-\varepsilon$, the following holds simultaneously for every input list size $\ell\le 2^{δn/\log n}$, where $δ>0$ depends only on $α,\varepsilon$, and $d$. Given any list of $\ell$ symbols at each coordinate, at most $(1+\varepsilon)\ell/(1-α)$ codewords agree with the lists in at least $(1-α)n$ coordinates. Our proof adapts the colored-graph and determinant arguments of Matousek, Privetivy, and Skovron for reconstructing planar point sets from their projections. We also prove that the range of input list sizes is nearly optimal. There is a constant $c=c(α,\varepsilon)>0$ such that, for every linear code of dimension at least two over a sufficiently large prime field $\mathbb{F}_p$ and every $2^{cn}\le\ell\le p$, there are lists of size $\ell$ and a set of more than $(1+\varepsilon)\ell/(1-α)$ codewords, each of which agrees with those lists in every coordinate. The main results of this paper were discovered by ChatGPT 5.5 Sol using harness components from the UCLA Moonshot Harness Project, in response to a less optimal result found by the authors. See the end of the introduction for a discussion.

cs.IT

版本更新 · v3arXiv:2605.12938

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

Seonghyun Jin, Youngmin Kim, Sunwoo Park, Jong Chul Ye

原文摘要

Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only camera signals or rely on pinhole camera geometry, limiting their applicability to general camera control under the Unified Camera Model, including wide-angle and fisheye lenses. To address this limitation, we propose Curved Ray Expectation Positional Encoding (CRePE). CRePE represents each image token as a depth-aware positional distribution along its source ray, providing a Unified Camera Model-compatible positional encoding that naturally captures the curved-ray geometry of wide-angle and fisheye cameras. CRePE is implemented through a Geometric Attention Adapter added to frozen video DiTs, injecting token-wise scene-distance information into selected attention layers and stabilizing it with pseudo supervision from a monocular geometry foundation model. This design leads to more stable camera control with competitive video quality in camera-conditioned video generation under the Unified Camera Model, and the resulting model transfers zero-shot to real fisheye and diverse pinhole videos. Controlled positional-encoding ablations show improvements over a RayRoPE-style endpoint approximation, demonstrating the effectiveness of curved-ray-aware positional encoding, particularly for non-pinhole cameras. Furthermore, by extending the same positional-encoding pathway to external geometry control through Radial MixForcing, CRePE supports external radial-map control for scene-geometry-conditioned generation and source-video motion transfer beyond camera control. Project page: https://crepe-neurips2026.github.io/; code: https://github.com/jinotter3/CRePE.

cs.CV · cs.AI · cs.LG

版本更新 · v3arXiv:2602.08616

Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces

Heiko Hoppe, Fabian Akkerman, Wouter van Heeswijk, Maximilian Schiffer

原文摘要

Reinforcement Learning (RL) is increasingly applied to large-scale decision-making problems like logistics, scheduling, and recommender systems, but existing algorithms struggle with the curse of dimensionality in such large discrete action spaces. We propose Distance-Guided Reinforcement Learning (DGRL), combining Sampled Dynamic Neighborhoods and Distance-Based Updates to enable efficient RL in problems with up to $10^{36}$ actions. Unlike prior methods, DGRL performs stochastic volumetric exploration and transforms policy optimization into a stable regression task, decoupling gradient variance from action space cardinality. On structured tasks, DGRL provably guarantees local value improvement. DGRL naturally handles action spaces without regular semantic structure and hybrid continuous-discrete action spaces. We demonstrate performance improvements of up to 66% against state-of-the-art benchmarks across regularly and irregularly structured environments, while simultaneously improving convergence speed and computational complexity.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.21699

X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation

Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Mingyu Yang, Ali Taghibakhshi, Saurav Muralidharan, Ashwath Aithal, Pavlo Molchanov

原文摘要

Cross-tokenizer knowledge distillation allows a student to learn from teachers with incompatible vocabularies while preserving its tokenizer and inference architecture. Existing logit-based methods either supervise only the observed token or match full distributions through strict token partitions and heuristic ranking. We identify two limitations: an uncommon-token failure, where task-critical tokens outside the shared vocabulary are suppressed, and over-conservative matching, where exact string equality discards useful correspondences. We propose X-Token, which addresses both through a sparse projection initialized from tokenizer-level string rules and optionally refined during distillation. P-KL removes the partition and projects the student distribution into the teacher vocabulary; H-KL retains the hybrid loss while relaxing matching through the projection. A token-coverage audit guides the choice between them, and both extend naturally to heterogeneous teachers. Across Llama, OLMo, and Gemma students, X-Token achieves the highest average accuracy in all four teacher-student settings among all evaluated cross-tokenizer methods. Complementary teachers provide a further 1.30-point gain, and both variants are faster than the evaluated cross-tokenizer baselines in matched profiling.

cs.LG · cs.CL

版本更新 · v2arXiv:2604.10479

Expanding Codes with Polynomial Stretch

Isaac M Hair, Amit Sahai

原文摘要

We give a polynomial-stretch, constant-arity counterpart to the expanding-code construction of Blasiok, Lou, Rosen, and Sudan (FOCS 2026). For every constant $\varepsilon\in(0,1/2)$, we construct binary matrices with $n$ columns and polynomially many rows, each of weight $k=O(\varepsilon^{-6})$, such that the union of the supports of any set of at most $n^{1-\varepsilon}$ rows has size at least $(1-\varepsilon)k$ times the number of rows. Nevertheless, a polynomial-time test accepts every codeword (generated by the columns of this matrix) corrupted in at most a $1/2-\varepsilon$ fraction of its coordinates, while rejecting a uniformly random vector with high probability. We give two applications. First, we obtain a family of (nearly lossless) constant locality expanders on which Goldreich's pseudorandom generator with the XOR-MAJ predicate can be distinguished from uniform in polynomial time, well within the small-bias parameter regime and the hard regime for known algebraic-immunity/annihilator attacks and algebraic-degree linearization attacks described by Applebaum and Lovett (STOC 2016, SICOMP 2018). Second, we obtain public key encryption from either the constant-noise $k$XOR conjecture over random graphs or the Goldreich conjecture with XOR-MAJ over random graphs, together with a new planted-hypergraph conjecture. We prove low-degree lower bounds for the planting conjecture, providing evidence for subexponential hardness, and give lower bounds against dimension tests based on coordinatewise products (Schur products) of public-code vectors. The PKE schemes and lower bounds were discovered by the authors. The code construction was discovered by Codex / ChatGPT 6 Astra Ultra using harness components from the UCLA Moonshot Harness Project, in response to a general strategy suggested by the authors. See the end of the introduction for a discussion.

cs.CR

版本更新 · v3arXiv:2603.00963

Stabilizing Policy Optimization via Logits Convexity

Hongzhan Chen, Tao Yang, Yuhua Zhu, Shiping Gao, Xiaojun Quan, Ting Yao

原文摘要

While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unstable, especially when compared to supervised fine-tuning (SFT). In this work, we investigate the stability gap between SFT and RL from a gradient-based perspective, and show that the convexity of the SFT loss with respect to model logits plays a key role in enabling stable training. Our theoretical analysis demonstrates that this property induces favorable gradient directionality during optimization. In contrast, Proximal Policy Optimization (PPO), a widely adopted policy gradient algorithm utilizing a clipped surrogate objective, lacks this stabilizing property. Motivated by this observation, we propose Logits Convex Optimization (LCO), a simple yet effective policy optimization framework that aligns the learned policy with an optimal target derived from the original RL objective, thereby emulating the stabilizing effects of logits-level convexity. Extensive experiments across multiple model families show that our LCO framework consistently improves training stability and outperforms conventional RL methods on a broad range of benchmarks.

cs.LG · cs.CL

新论文 · v1arXiv:2611.10423

Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning

Mi Luo, Rohan Dugad, Zihui Xue, Alex Dimakis, Kristen Grauman

原文摘要

Mental simulation, the ability to reason by constructing and updating internal visual states, is central to flexible human cognition, but remains elusive in current multimodal large language models. Latent multimodal reasoning offers a promising route toward this capability by interleaving text with continuous visual latent blocks, allowing models to maintain internal visual workspaces without decoding them into pixels. In this paper, we ask whether these latent visual states actually matter. Through a direct perturbation analysis across representative latent-reasoning MLLMs, we find that they often do not: dropping, replacing, or shuffling generated visual latents has only minor effects on the model's own final-answer probability, while equivalent perturbations to the linguistic reasoning trace are substantially more damaging. We call this failure mode Mental Simulation Collapse (MSC): the model appears to perform interleaved visual reasoning, but routes most answer-relevant computation through text. We further diagnose that MSC follows naturally from existing training objectives: visual alignment can make generated latents resemble helper-image embeddings, but it does not require the decoder to rely on them; subsequent text-only supervision further leaves the semantic role of the latent pathway unidentifiable. To address this, we introduce AnchorSim (Anchored Mental Simulation), a contrastive distillation framework that trains models to make their generated visual latents consequential. Across multiple visual reasoning benchmarks, AnchorSim improves performance, while diagnostic re-evaluation shows that visual perturbations now meaningfully affect predictions. Our results expose a fundamental failure mode of latent multimodal reasoning and demonstrate that mental simulation must be anchored to model behavior in order to matter.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.35165

How Tuning, Reference Preview, Actuator Modeling, and Fallback Policies Change Quadrotor Controller Comparisons: A Reproducible Simulation Study

Xuan-Quy Dao, Le-Minh Nguyen, Ngoc-Bich Le

原文摘要

Quadrotor controller comparisons commonly report a single tracking error, although the ranking also depends on tuning effort, reference information, actuator prediction, optimizer fallback, and command timing. We quantify these effects for cascade PID, hover LQR, boundary-layer sliding-mode control (BL-SMC), linear MPC with LQR fallback (LMPC-F), a preview-enabled LMPC-F, and a geometric $SO(3)$ controller on a common nonlinear plant with rotor gyroscopic coupling, motor lag, and saturation. A primary study (556 episodes at 50~Hz) combines matched twelve-candidate tuning, 400 paired evaluation episodes, and a 48-cell MPC factorial; a confirmation study (1462 episodes) repeats the evaluation on 50 fresh realizations with tuning budgets of 12, 24, and 48 candidates. A matched twelve-candidate tuning protocol changed the mean-RMSE ordering of the fixed baseline settings, mainly by moving BL-SMC from last to first. The ordering recurred on fresh realizations and did not change with 48 candidates, although BL-SMC's lead on the fresh set depends on a wider search range for its vertical switching gain. Reference preview reduced MPC tracking error and removed fallback activity on the figure-eight task. In single abrupt-step runs, completion depended jointly on fallback policy, predictor, and actuator authority. Command timing also changed the outcome: replaying measured command-call delays terminated three of four nominal MPC configurations on a desktop and all four on a Raspberry Pi~5, whereas capping the solver at 100 iterations removed every deadline miss in these profiles. We propose a reporting checklist that adds tuning effort, failure rates, fallback activity, applied-input variation, and command timing to tracking accuracy.

cs.RO