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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 08:07 — 2026-11-16 08:07(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 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 5,257 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2609.35036

Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation

Jiashen Ren, Wenlin Zhang, Bohan Zhang, Xiaopeng Li, Zichuan Fu, Wanyu Wang, Junyi Li, Xiangyu Zhao

原文摘要

Persona prompting is widely used in LLM user simulation, yet it relies on an untested assumption: specifying a target user attribute should shift target behavior while leaving other fixed attributes unchanged. Across eight black-box and five open-weight models, however, changing a target attribute alone also shifts unspecified non-target choices, such as risk preference shifting color choice. We test whether explicitly specifying non-target attributes restores selective control across 477 held-out synthetic worlds and 200 independent items under unspecified, directional, and neutral states. Assigning a clear non-target direction nearly eliminates cross-attribute shifts. Explicitly declaring no preference, however, still leaves 37.7%-76.3% of held-out worlds and 51%-81% of independent non-target items shifting with the target attribute while preserving target efficacy. We call this disparity the neutrality gap. Because directional tests can be passed simply by following a stated preference, the neutral state reveals selective-control failures they miss: following a stated persona does not imply keeping unrelated choices invariant. In simulated investment decisions, incidental brochure color labels shift estimated target risk treatment effects by 25.5 percentage points, even when models accurately report having no color preference. Counterfactual attention interventions show that unwanted influence enters primarily at query time, when option evaluation reads the target persona directly. Blocking query-time attention cuts non-target drift by 72.1%-87.8%, whereas directional declarations suppress drift primarily by overwriting option values rather than rerouting attention. Because target and non-target choices share query-time access, blocking it weakens target efficacy while value overwrite imposes an artificial direction, leaving task-dependent selective access as a central challenge.

cs.AI

版本更新 · v2arXiv:2605.02209

Submodular Benchmark Selection

Alexander Smola

原文摘要

Evaluating a new language model means running it on a large, growing collection of benchmarks, at considerable cost. Much of this cost is redundant: arranged as a matrix of models by benchmarks, scores are strongly correlated and concentrate in a few dimensions, so a few well-chosen benchmarks largely determine the rest. This allows us to run a new model on a few benchmarks and predict the rest with a simple Gaussian model that copes with missing scores. The key question is \emph{which few to run}. An answer comes from sensor placement, which chooses the observations that carry the most information, measured by entropy or mutual information. We argue that the objective should instead reward a selection for how well it predicts every benchmark. This leads to two coverage objectives: explained variance, the predictions' accuracy if the estimated correlations were exact, and facility location, which credits each benchmark with its best proxy among the selected ones. On eleven score matrices built from public evaluation results, the coverage objectives predict the scores of held-out models best wherever the correlations can be estimated. The information objectives fall behind because they favor benchmarks that the selection predicts poorly (entropy) or that the others predict well (mutual information), not benchmarks that predict the others. By contrast, facility location predicts practically as well as explained variance, holds up on the addition of newer models and under real costs, has classical guarantees (even under a budget), and gives readable selections.

cs.AI · cs.LG

新论文 · v1arXiv:2611.16308

ORCHID-SAGE: Fully Reproducible CALPHAD Assessment from Evidence to Phase Diagram

Raymundo Arróyave

原文摘要

Knowledge of phase stability is the first requirement for materials design, and predicting the conditions under which new materials can be synthesized has become a key capability of self-driving laboratories (SDLs). For inorganic materials, notably alloys, these predictions come from thermodynamic databases built with the CALPHAD method. Building a database, however, requires expert judgment at many steps, and because these decisions are rarely recorded, others can use a database but cannot regenerate or update it. Machines can already collect the data, build a first model with machine-learned interatomic potentials and refine it against experiments. The assessment itself, the sequence of judgments that turns these parts into a reliable database, is still carried out by human experts. We argue that it can be automated reproducibly only if the expert knowledge behind an assessment is encoded in formal protocols, so that an assessment delivers a record of its construction and not only its parameters. We introduce ORCHID-SAGE, a standard that organizes this record into reproducible and automatable protocols. In this first attempt, applied to Cr-Ni, the database was regenerated from its record by a script on a second machine, by an AI agent working only through the Model Context Protocol (MCP) and by a refit from public sources only, with the same predictions. Recorded in this way, a database need no longer be fixed at publication but can be updated by AI agents as SDLs and other sources provide new evidence, while the judgment remains with people and on the record.

cond-mat.mtrl-sci · cs.AI

版本更新 · v2arXiv:2609.24969

Rare Event Estimation via Iterative Unalignment

Hanming Yang, Daksh Mittal, Jing Dong, Hongseok Namkoong

原文摘要

As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic. Safe deployment therefore does not depend on whether these events can occur, but on how often they might. We study the problem of estimating the probability of rare events that arise from stochastic variation in the agent's own actions. Estimating this type of risk requires searching over the combinatorially vast space of trajectories. Naive Monte Carlo is computationally prohibitive in this regime, and constructing effective importance sampling (IS) proposals requires coordinated changes to a context-dependent chain of conditional distributions. We develop a new IS method that perturbs the original model's weights to construct the proposal. The proposal is itself a differentiably parameterized language model, enabling gradient-based search over weight space. We formulate an objective that combines a differentiable surrogate for event amplification and an adaptive regularization scheme that dynamically balances amplification against estimator stability. We evaluate our approach on $\sim$120M and $\sim$2.6B models across three event families spanning 300+ rare events as rare as $10^{-9}$, all with independently estimated reference probabilities. In our most verifiable settings, we observe that our IS estimator achieves over $800\times$ compute-weighted efficiency gains on average over naive Monte Carlo for events with probabilities lower than $10^{-7}$. Our implementation is available at https://github.com/namkoong-lab/iterative-unalignment.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16300

SAGE-QA: Semantic-Aware, Grounded Evaluation for Closed-Context Question Answering on SQuAD 2.0

Chandra N Sekharan, Vishakan Umapathy, Abhishek Phadke

原文摘要

Closed-context question answering (QA) requires a system to generate an answer strictly supported by a supplied passage, or to abstain when the passage lacks adequate evidence. SQuAD 2.0 is a widely used benchmark for this setting, scored by Exact Match (EM) i.e., character-level agreement with human reference spans after lexical normalization. For generative large language models (LLMs), however, an EM failure may reflect a valid paraphrase or an alternative passage-supported answer rather than a hallucination. The best prior leaderboard EM is approximately 91%, but evaluating generative models requires separating lexical divergence from factual error. We introduce SAGE-QA (Semantic-Aware, Grounded Evaluation for Question Answering), a multi-tiered framework combining reference-based Semantic Equivalence Scoring (SES) and passage-based Re-Validation Scoring (RVS). On a fixed set of 10,000 SQuAD 2.0 validation examples, we compute EM and decision-matrix F1 from TP, TN, FP, and FN counts for zero-shot closed-weight frontier models and for open-weight models, untuned and fine-tuned. Zero-shot, Claude Opus 4.6 and Gemini 3.1 Pro reach 85.21 and 86.66 EM, outperforming untuned Llama 3 8B (56.88), gpt-oss-20b (66.28), and Llama 3.3 70B (71.39). Parameter-efficient fine-tuning adds 21.19 to 34.06 EM points, raising these models to 90.94, 87.47, and 94.24 EM, respectively. Auditing the frontier models with SAGE-QA and an external LLM judge yields dataset-wide SES scores of 92.81 for Claude Opus 4.6 and 91.67 for Gemini 3.1 Pro, and hybrid RVS scores, which combine benchmark credit with passage-based judge assessments, of 97.96 and 98.02. Fine-tuned open-weight models perform best, with fine-tuned Llama 3.3 70B surpassing the previous best known EM.

cs.AI · cs.LG

新论文 · v1arXiv:2611.16289

Eliciting and Mitigating Specification Satisficing in Coding Agents

Ruixin Wang, Tianyi Zhang

原文摘要

Coding agents often fail to meet all requirements in the task description. In some of these failures, the agent considers an implementation choice that meets a requirement, but later decides to commit to another one that does not meet the requirement for a reason it finds acceptable. We call this specification satisficing. It is challenging to identify and mitigate specification satisficing because the agent accepts such choices for its own reasons, and existing self-correction methods are biased toward them. We propose SatisFix, which guides a coding agent to report these choices and their reasons, and then check each choice against the task description. We evaluate SatisFix on DeepSWE and SWE-bench Pro with five LLMs as backbones and two different agent frameworks, and compare it with three self-correction methods. SatisFix improves the pass@1 of the base agent by an average of 5.09% on DeepSWE and 7.06% on the hard subset of SWE-bench Pro. On DeepSWE, it outperforms the best baseline by 3.98%. Our ablation study shows that both steps of SatisFix contribute to the improvement.

cs.SE · cs.AI · cs.CL

版本更新 · v2arXiv:2611.12125

CARE-PO: Controllable Tool-Call Efficiency for LLM Agents

Xiaoyang Ye, Xiao Yao, Hairui Zhu, Yiying Yang, Bei Gan, Jinliang Lu, Tengjin Weng, Yuan Yao 等 9 位作者

原文摘要

External tool calls are a major running cost of an LLM agent, while its training objectives align almost exclusively with task completion. In a step-level diagnosis of Qwen3.5 trajectories at two model sizes on GAIA, a long-horizon tool-use benchmark, we find that most contain removable calls, at a similar rate at both sizes. Some methods add an efficiency reward to the objective to reduce the call count, but introduce problems of their own: the anchor they price calls against is computed from the policy's own rollouts (e.g., the group's shortest correct rollout) and so moves with the policy; training can drift toward a collapsed policy that issues no tool call at all, a degeneracy seen in published reports and in our 27B baseline; and a training run delivers a single operating point, so the user cannot trade efficiency against capability. We present CARE-PO (Controllable Anchored Relative Efficiency Policy Optimization) to mitigate these problems. The efficiency reward prices calls against a reference budget anchored to the task's own difficulty and fixed before training. Injecting a successful trajectory from the training data into each online GRPO rollout group and charging for evidence a trajectory never gathers ease the drift toward a collapsed call count. Shaping the cost curve by an effort tag in the prompt yields an efficiency and a capability operating point from a single training run. On GAIA, five of the six operating points across three model sizes improve on their base model in success rate and call count at once. On four held-out multi-hop benchmarks the result is size-dependent: at 27B and 4B success rate is held or raised at a lower call count, while at 9B both operating points trade success rate for fewer calls. The call count remains well above zero throughout training at all three sizes.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16270

SMIC: Shared Multiscale Input-Reference Conditioning across Transformer Layers for Natural Language Inference

Xin Zhang, Victor S. Sheng

原文摘要

Natural Language Inference models can be sensitive to localized lexical changes. We introduce Shared Multiscale Input-Reference Conditioning (SMIC), which constructs a single input-dependent multiscale reference and reuses it across Transformer layers. Each layer applies its own multiscale transformation to the shared reference and injects the resulting conditioning feature before the attention update. We instantiate SMIC in a token--context Transformer (TCT) and conduct from-scratch comparisons against decoder-based and Multi-Layer Perceptron (MLP) baselines across all three ANLI rounds. TCT-SMIC attains the highest observed ten-seed mean accuracy on all three ANLI rounds. The ablations further support the contribution of SMIC. We evaluate a real-valued Llama-style plug-in and extend deletion/insertion diagnostics to pretrained ModernBERT encoder and Llama decoder models with and without SMIC. Across the evaluated perturbation protocols, TCT-SMIC exhibits comparatively low pooled-attention redistribution and smaller signed accuracy changes. We further establish a finite-sample bound on average subset-mass redistribution in terms of the mean Jensen--Shannon divergence between the restricted and renormalized attention distributions.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.16267

Causals: An Open Knowledge Graph for Research on Causal Reasoning

Miaozhe Lin, Qiongzheng Lin, Zhongwei Liang, Zijun Liu

原文摘要

Applying causal knowledge to a new event requires connecting the event to relevant entities and the relationships through which its consequences may unfold. We present Causals, an open knowledge graph for research on this form of reasoning. Its initial release, constructed from news reports, contains 369,184 nodes and 1,272,418 edges linking reported events, organizations, commodities, financial instruments, and other entities. Structural relationships, observations, and attributed causal claims retain distinct semantics and links to source records. We describe the construction and representation of the resource and characterize its connectivity and multi-hop retrieval properties. Causals provides shared relational knowledge for studying how language models retrieve relevant context and apply mechanisms to particular events. The dataset is available under CC BY 4.0 at https://causals.org/, and we invite contributions to its ontology, records, and evidence.

cs.AI

版本更新 · v2arXiv:2610.10498

EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

Python Song, Zhixuan Liang, Kelsey Fu, Mengdi Wang, Junfeng Yang, Shilong Liu

原文摘要

Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt around the model, but current self-evolving harnesses use robot trials inefficiently when deciding which code and skill changes to pursue. We introduce EmbodiedRSI, a self-evolving agentic harness that autonomously decides where to explore next and turns the resulting physical interaction into improved code and skills. EmbodiedRSI realizes this through a Fast-Slow Dual-System Architecture, in which competing code and skill hypotheses are maintained in a Hypothesis Graph. Value-of-Information Experiment Selection chooses physical experiments that can distinguish these hypotheses. Their outcomes guide Code-Skill Co-Evolution. The Slow System builds Hierarchical Memory, and Reward-Grounded Memory Learning selects effective memory according to their value for later Fast-System improvement. On RoboCasa365, EmbodiedRSI reaches 77.0% overall success and 71.3% on Composite-Unseen, compared with 40.1% for the best baseline. EmbodiedRSI also reaches 86.8% overall success on LIBERO-Pro. Beyond benchmark performance, EmbodiedRSI transfers zero-shot to real-world robot, achieving 71.3% overall success across multiple challenging tasks.

cs.AI

新论文 · v1arXiv:2611.16265

Rectified Looped Transformer

Musheng Li, Jiawei Zhang, Ziyuan Liu, Yuantao Gu

原文摘要

Looped Transformers increase effective depth by repeatedly applying a shared block, offering a parameter-efficient approach to language modeling. However, most existing works directly reuse each loop's output as the next's input, which can lead to hidden-state scale growth and perturbation amplification as recurrence deepens. We propose Rectified Looped Transformer (RLT), which redesigns feedback between loops using an interpolation schedule inspired by flow-based modeling. At each loop, RLT forms the next input by linearly interpolating between the current state and its prediction. Such interpolation distributes state changes across loops, encouraging a smoother trajectory from the initial input to the final output. Theoretical analysis proves that, under appropriate assumptions, RLT keeps state magnitudes uniformly bounded across loops and reduces the worst-case perturbation amplification. We evaluate RLT on language modeling corpora and downstream benchmarks. At matched training and inference depths, RLT consistently achieves lower perplexity than a standard looped Transformer, while exhibiting greater robustness to input perturbations and variance in inference depth. Consistent with the theoretical results, latent trajectory analysis shows that RLT maintains more stable hidden-state norms across loops, which also facilitates extrapolation-based decoding strategies. Notably, RLT achieves these gains without requiring additional trainable parameters or extra recurrent block evaluations, thus providing a simple yet more stable feedback mechanism for looped Transformers.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16264

Label-Efficient Document-Grounded Factuality Detection via Cross-Paraphrastic Invariance Learning

Chao Chen, Shanshan Lin, Dongsheng Hong, Sibo Ju, Wenjie Yang, Sihong Xie, Xiangwen Liao

原文摘要

Large language models (LLMs) can generate fluent claims that are unsupported by a given source document, motivating accurate and efficient document-grounded factuality detection. Existing LLM-based evaluators often require repeated inference and incur high computational cost, whereas compact factuality detectors are efficient at inference time but commonly rely on large labeled or synthetically generated corpora. We propose CPIL (Cross-Paraphrastic Invariance Learning), a two-stage Siamese framework that converts a small labeled set into relational supervision without acquiring additional factuality labels. CPIL constructs positive pairs from distinct label-preserving paraphrastic views of the same document-claim instance and negative pairs from opposite-label examples associated with the same source document. It further introduces quantile-aware semi-hard negative mining, which derives a boundary from the positive-pair similarity distribution and balances informative negatives with broader coverage. In the two-stage training procedure, Stage 1 learns an encoder from these task-aware pairs, and Stage 2 jointly fine-tunes the encoder and a linear classification head for binary factuality prediction. At inference time, CPIL requires no paraphrase generation, pair construction, or Siamese comparison and uses only one encoder-classifier forward pass. On the 11-task LLM-AggreFact benchmark, CPIL-2% and CPIL-3% achieve macro-F1 scores of 81.04 and 81.60 while using only 2-3% of the FactCG-released labeled pool. Both settings outperform all compared compact detectors and two vanilla LLM references. Ablations and sensitivity analyses support the contributions of task-aware pair construction, dynamic negative mining, and multi-pivot paraphrasing.

cs.CL · cs.AI

版本更新 · v3arXiv:2603.18859

RewardFlow: Can Action-Level Reward Be Estimated from State-Graph Topology in Agentic RL?

Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Kwok-Po Ng

原文摘要

In agentic tasks such as household assistance and web shopping, large language model (LLM) agents take multiple actions before receiving a final outcome indicating success or failure. For reinforcement learning (RL), this outcome obscures individual actions' contributions: a shopping trajectory may find the right product but fail to complete the purchase. To address this credit-assignment problem, we introduce RewardFlow, which connects multiple trajectories for the same task through shared states (states grouped by task-relevant equivalence or semantic similarity). The resulting directed state graph links observed trajectory segments. Therefore, an action in a failed trajectory may reach a state from which another trajectory succeeds. It propagates reward signals backward from states where the task succeeds, assigning state potentials that decrease with shortest-path distance to success in the graph. Potential differences then reward actions that reduce this distance, bringing the agent closer to success in the graph. These estimated rewards yield action-level advantages that complement trajectory-level advantages from outcome rewards during policy optimization, without a learned process reward model or manual action-level annotations. Experiments on ALFWorld, WebShop, Sokoban, and search tasks show gains over RL baselines across model scales. With 3B policies, graph construction and reward estimation take $1.47$-$2.39$ seconds per training step on ALFWorld, WebShop, and Sokoban (Fig. 1). Code is available at https://github.com/tmlr-group/RewardFlow.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2605.07979

The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty

Santiago Cortes-Gomez, Mateo Dulce Rubio, Carlos Patino, Bryan Wilder

原文摘要

The rise of machine learning has shifted targeted resource allocation in policy and humanitarian settings toward algorithmic targeting based on predicted risk scores. This approach is typically cheaper and faster than traditional screening procedures that directly observe the latent vulnerability status through physical verification. Yet, even access to the true conditional vulnerability probability cannot eliminate misallocation: aleatoric uncertainty over individual vulnerability status is irreducible, and probabilistic targeting inevitably misallocates some resources. In this work, we study how screening and algorithmic targeting should be optimally combined in a two-stage allocation framework, in which a screening stage observes true outcomes for a subset of units before a final allocation stage assigns the resource under a fixed coverage budget. We show that the optimal strategy screens units at the margin of algorithmic allocation, while directly targeting the highest-risk units. We empirically characterize when screening and algorithmic targeting act as complements or substitutes: efficiency gains from screening grow as the aleatoric uncertainty in the population increases. Finally, we characterize the relative value of screening and direct allocation, which yields a simple rule for splitting a program budget between the two: the optimal cutoff depends only on their cost ratio. We illustrate our framework with applications in income-based social protection programs and humanitarian demining in Colombia, where the tension between screening costs and allocation efficiency is operationally consequential

cs.AI

新论文 · v1arXiv:2611.16228

Indic-Task Gains and Regressions after Reinforcement Learning

Sutanshu Saksena Raj, Daksh Maan, Avinash Benki, Parijat Chatterjee, Pasunuti Prasanjith, Purusharth Malik

原文摘要

We run reinforcement learning (RL) with GRPO across four environments, starting from a supervised fine-tuned 30B-A3B mixture-of-experts model covering English and eight Indic languages. We compare the model before and after RL across 34 benchmarks in one evaluation campaign. MATH improves by 36.07 points, and most Indic benchmarks also improve. Yet XQuAD-Indic F1 falls 19.32 points as English answers rise from 8.7% to 91.7%; IndicQA falls 8.64, while English XQuAD gains 11.71 F1. A second RL run from the same supervised initialization adds an Indic environment together with language and repetition rewards. Compared with the released model, it improves both passage-answering and instruction-following benchmarks, along with preserving MATH performance. But it loses ground on reasoning and coding benchmarks. Several training choices changed together, so we cannot isolate the effect of any one of the reward terms. Script compliance remains unresolved. Adding a language reward did not ensure use of the requested script. Passage answering and script compliance therefore need direct evaluation, even when other benchmark scores improve.

cs.CL · cs.AI

版本更新 · v8arXiv:2606.03163

OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery

Jinliang Xu

原文摘要

This yellow paper specifies the technical architecture and verification semantics of OpenAgenet (OAN), a protocol-neutral trust layer for heterogeneous Agent resources. The design combines did:oan decentralized identifiers (DIDs), verifiable credentials (VCs), on-chain infrastructure governance, and Root-verified resource packages. It defines the objects and lifecycle transitions that connect subject-control verification, Registrar admission, Root acceptance, authorized Discovery, and signed invocation. Infrastructure authorization requires both active governance state and a valid Root-issued credential; resource discovery additionally requires package integrity, current-version state, and authorized-domain coverage. Local OAN Identity signing material remains separate from public protocol objects. Integration profiles carry resource identity into the Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocol through Skill, Runtime, Sidecar, and Gateway interfaces without redefining native task semantics. The paper distinguishes protocol requirements from implementation choices and sets out security properties, persistence and recovery expectations, and conformance criteria. Together, these rules provide a technical basis for independently implemented registration, discovery, and identity-protected interaction within an OAN trust domain.

cs.MA · cs.AI · cs.DC

新论文 · v1arXiv:2611.16215

Guided Generation of Linux Kernel Semantic Patches with Small Local Language Models

Mohanned Ahmed

原文摘要

When a Linux kernel API changes, hundreds of drivers are converted by hand over months, and the earlier conversions are reviewed examples for the later ones. We ask whether small open language models running on a laptop can turn such examples into Coccinelle semantic patches, the rules kernel maintainers already use for tree-wide changes. We adapt guided code generation to this task: the training examples are decomposed by script into a tree of change variants, the model writes one small rule per variant under feedback from applying it to the examples, deterministic components repair SmPL syntax and generalise driver-specific names, rules are composed greedily, and a compile critic repairs or rejects a rule whose output does not build. We evaluate on a pre-registered test set of 7 migrations whose new APIs appeared after the training cutoffs of all three models (Qwen2.5-Coder 7B, Llama 3.1 8B, Gemma 3 4B), with 122 held-out driver conversions, counting a conversion as solved only if the rule's output matches the human fix and compiles. With the framework, Qwen2.5-Coder solves 35.3 conversions on average over three seeds (range 32-41), against 1.0 when prompted directly; Spinfer solves 41 and a frontier LLM agent 66. The local model solves fewer conversions than Spinfer but its rules are the most precise on the test set (0.74 of the files they change are solved, against 0.55 for Spinfer and 0.70 for the frontier agent), and the compile critic removes every output that matches the human fix but does not build. The two general-purpose models stay weak even with guidance (at most 12 solved). All code, prompts, model responses and results are released.

cs.SE · cs.AI

新论文 · v1arXiv:2611.16211

One Fuzzer, Many Reasoners: Adaptive Neuro-Symbolic Fuzzing with Reliability-Calibrated and Context-Gated Guidance

Jinghao Wen, Xianglong Yu, Shaohuang Wang, Xun Jiao

原文摘要

Neural-symbolic AI (NSAI) combines learned perception with programs, constraints, and compositional reasoning, but remains difficult to test because small semantics-preserving changes can alter grounded symbols and trigger discontinuous reasoning failures. Existing neural fuzzers mainly rely on neural coverage or representation-space feedback and do not provide a common testing interface for heterogeneous NSAI systems. We introduce NSAI-Fuzz, a unified semantics-aware fuzzing framework that separates task-specific valid mutation from architecture-neutral guided search and represents each candidate using five availability-aware, rank-normalized risk signals: boundary pressure, grounding uncertainty, representation drift, constraint violation, and archive novelty. We further propose Reliability-Calibrated Weighting (RCW), which learns dataset-model-level signal allocations from calibrated reliability, and Contextual Signal Gating (CSG), which adapts signal weights to the current candidate pool. We evaluate four NSAI systems across four reasoning tasks, nine compatible dataset-model cells, 20 policies, and 1,800 on-policy runs. Fixed five-signal guidance outperforms Random and Uniform in every cell, while RCW and CSG further improve over Fixed in all nine cells. Under matched mutation and query budgets, RCW and CSG achieve 16.17% and 16.06% aggregate failure discovery, compared with 6.06% for the strongest neural-fuzzing baseline. Wall-clock evaluation further shows that TensorFuzz requires 1.11x the runtime of RCW while achieving only 0.45x its failure throughput. These results show that effective and efficient fuzzing of heterogeneous NSAI systems benefits from a common neural-symbolic risk interface with adaptive signal allocation.

cs.AI · cs.LG

新论文 · v1arXiv:2611.16206

Turning Multi-Agent Communication into Token-Level Credit with On Policy Self Distillation

Zixu Wang, Yu Zhao, Xing Zheng, Bingbing Xu, Tian Xueyun, JiaTang Luo, Weiqiang Wang, Bowen Song 等 10 位作者

原文摘要

Reinforcement learning improves problem solving in large language model multi-agent systems. Existing approaches overlook communication knowledge or compress it into scalar rewards, leaving coarse credit with little guidance on which decisions each agent should reinforce or revise. OPSD4MAS converts future communication into fine-grained token-level credit through On Policy Self Distillation (OPSD). An external model extracts facts and assesses their trajectory relations for coarse-grained filtering, followed by fine-grained leave-one-out filtering of target-token influence against agent-wise outcome advantages. The fact-conditioned policy supplies token-level credit, combined with GRPO through a linearly annealed joint objective. Our method improves mathematical pass@4 over GRPO by up to 20.00 percentage points. Ablations support complete filtering, while frozen-history injection diagnostics support fact utility. Together, these results support combining agent-level outcome guidance with communication-derived token-level credit. Code is available at https://github.com/Camel-Prince/OPSD4MAS.

cs.AI

版本更新 · v8arXiv:2606.03161

OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection

Jinliang Xu

原文摘要

OpenAgenet (OAN) is an open infrastructure project for trusted Agent interconnection across independently operated networks. It addresses the verification of resource identity, governance state, discovery authorization, and freshness before interaction. OAN combines decentralized identifiers (DIDs), verifiable credentials (VCs), and on-chain infrastructure governance with a routing-aware did:oan registration and discovery model. Registrars verify onboarding evidence; the Root service accepts resource identity versions and publishes verifiable packages; authorized Discovery nodes return signed results within their governed scope. Root also governs the semantic tag tree shared by registration and discovery. Public DID Documents and credentials remain separate from local OAN Identity signing material and from controller authorization. Skill, Runtime, Sidecar, and Gateway integration paths allow existing Agents to adopt this identity model progressively, including through the Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocol, while retaining their native task and workflow semantics. Prototype evaluation and a public pilot support examination of the trust lifecycle and its operational bottlenecks. This white paper presents the architecture, governance model, ecosystem adoption paths, and standardization opportunities for OAN as a shared identity and trust infrastructure for heterogeneous Agent resources.

cs.MA · cs.AI

版本更新 · v2arXiv:2602.00282

Constrained Bilevel Reinforcement Learning via Approximate Lower-Level Responses

Naman Saxena, Vaneet Aggarwal

原文摘要

We study constrained bilevel reinforcement learning in which the lower-level problem is a constrained Markov decision process with a generally parameterized policy. The lower-level solution map can be set-valued and need not be Lipschitz continuous in the upper-level variable, so standard hypergradient analyses do not apply. We therefore define the upper-level objective as the expected upper-level loss of the policy returned by a fixed stochastic lower-level algorithm, which we call the approximate response. This objective is well defined without uniqueness of the lower-level solution. To compute its gradient, we randomize the reward and constraint values used during lower-level training without changing their means, so that the upper-level variable affects training only through known probabilities. This yields an unbiased estimator of the upper-level objective's gradient that does not differentiate through the lower-level updates. We establish lower-level reward and feasibility guarantees, upper-level stationarity, and a total sample complexity of $\widetilde{\mathcal{O}}(δ_\ell^{-6}ε_o^{-2})$ over both levels, where $δ_\ell$ is the lower-level accuracy and $ε_o$ is the upper-level stationarity error. Setting $δ_\ell=ε_o=ε$ gives $\widetilde{\mathcal{O}}(ε^{-8})$.

cs.LG · cs.AI

版本更新 · v3arXiv:2610.15221

HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems

Zhaoyuan Qiu, Sachith Seneviratne, Yu Xia, Saman Halgamuge

原文摘要

AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation models frozen. Existing studies focus on single agents, leaving joint harness evolution in multi-agent systems (MAS) underexplored. A single global optimizer faces growing context and workload as the system scales, while access restrictions may prevent sharing agent internals or system-wide feedback. We propose HarnessNet, a framework for hierarchical harness evolution in MAS. Its basic unit, Agentron, comprises an evolvable forward harness, a foundation model, and a local optimizer that can observe and modify only that harness. Agentrons form a layered graph through which environment feedback propagates backward, with upstream optimizers receiving node-specific feedback from the downstream layer. This decomposes joint harness evolution into smaller, coordinated tasks with separate contexts, reducing individual optimizers' context and workload while keeping access local. Optimizers need not access all agent trajectories or raw environment feedback. Experiments on AgentBench with multiple foundation models demonstrate the feasibility of training HarnessNet. Compared with a single global optimizer, HarnessNet achieves comparable performance gains while respecting local privacy and requiring fewer tokens and less time per optimizer call. A migration study shows that the evolved harnesses remain jointly effective after replacing the foundation models, suggesting transferability across models.

cs.AI

版本更新 · v2arXiv:2610.19423

Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training

Anshu Raina, Peyman Razaghi, Yuankai Chen, Cheng Yao, Yao Fu, Vidushi Goyal, Devang Patel, Wen Xie 等 10 位作者

原文摘要

Configuring distributed LLM training across hundreds of GPUs requires jointly optimizing tensor, pipeline, expert, context, and data parallelism alongside micro-batch size, recomputation, sharding, and overlap, a combinatorial space where memory legality can hinge on a single byte of activation accounting. Today, teams navigate it through expensive multi-node trial and error, burning GPU-hours on crashes and suboptimal recipes. We present Primus Projection, which closes this loop with two coupled components. First, a hybrid projection engine that measures what it can and simulates what it cannot: GPU microbenchmarks on as few as a single device capture compute kernels and any in-scope communication; a sub-node downscale-measure-upscale workflow analytically restores out-of-scope collectives, FSDP overlap, and the full pipeline schedule at the multi-node target. A pure simulation mode runs entirely on CPU, enabling pre-silicon planning without any GPU. Second, the Primus Tuning Agent treats the projection engine as a fast scoring oracle (seconds per candidate instead of tens of minutes) and uses it to drive an intelligent search over the configuration space. A deterministic seed planner sweeps single axes; an LLM investigation loop proposes cross-axis combinations the planner cannot reach, with an analytic memory pre-filter that rejects infeasible candidates before any GPU time is spent. Validated on Llama 3.1 (dense) and Mixtral 8x22B (MoE) across two GPU generations, all projections stay within ~10% of measured multi-node throughput, and fidelity holds at production scale: 4.7% error on DeepSeek V3 671B at 1,024 GPUs and 1.9% on Qwen3-235B-A22B at 256 GPUs. In a Mixtral 8x22B case study, the Primus Tuning Agent discovers a configuration delivering +27% throughput over the published 4-node BF16 reference at the same scale, in under 30 minutes of single-node exploration.

cs.AI · cs.DC

版本更新 · v4arXiv:2610.16102

Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science

Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato, Kodo Yamauchi

原文摘要

Tacit knowing is an operating regime of one memory substrate, not a separate kind of content. In VaCoAl (CASRAM, PyVaCoAl), an algebro-deterministic hyperdimensional memory over GF(2), one DAG of bound records is read in two ways. With every collision repaired (Rescue), the trace is exactly auditable but no path outranks another; with collisions tolerated (Don't Care), a path-integrated confidence $CR_2$ ranks direct over circuitous routes without being stated. This audit-valuation complementarity formalizes Polanyi's claim that tacit and explicit knowledge are not sharply divided. (1) Polanyi's from-to structure reads as non-commutative binding. (2) Full explication destroys the valuation (Lemma 1), as with Polanyi's pianist; tacitness is contingent or regime-bound, placing Polanyi, Nonaka, Tsoukas and Collins on one substrate. (3) The same lemma answers the popular dual-process moral ("train slow System 2 to tame fast System 1"), which mirrors the two-store reading of knowledge Polanyi rejected; Mercier and Sperber's reply, that reasoning is intuitive inference about reasons, matches his. (4) To know a large DAG is to cull it. Simon answered Polanyi's Meno argument: a test and a generator suffice. The AlphaGo-to-AlphaProof lineage builds that answer, yet a checker audits an endpoint and values no path: the tacit is relocated, not removed, and results are verified yet rootless. (5) Collins's three tacit knowledges map to bound structure, substrate valuation and value binding. (6) Our mentor-student DAG charts tacit transmission. (7) AI-solved problems with few follow-ups (Tao) are rootless explicit knowledge, re-rooted when LLMs generate, VaCoAl keeps the trace and the community values. (8) On Mercier and Sperber's theory an LLM is a sophist; truth-seeking lies in collective tacit knowing, Polanyi's conviviality, which we conjecture extends beyond humans. Testable predictions follow.

cs.NE · cs.AI

版本更新 · v2arXiv:2611.12048

Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study

Nova-Silicon Team

原文摘要

Floorplanning is an early step in turning a logical circuit into a physical chip: it positions large circuit modules and constrains the space available for subsequent logic placement and wiring. These decisions affect congestion and timing, but their physical consequences emerge through downstream implementation. For AI agents, the task requires translating engineering constraints into spatial decisions whose quality cannot be judged by successful tool execution alone. We present an evaluation framework that connects submitted layouts to a prescribed downstream implementation flow, checks geometric validity, measures physical quality, and reports resource use. On one industrial design whose 99 macros occupy approximately 71\% of a fixed L-shaped layout region, we compare our specialized system Nova-SI with general-purpose engineering agents and agents restricted to file access, obtaining complete physical measurements for 39 layout outputs. Under our 0--100 composite quality score, Nova-SI achieves a mean of 57.97 without online feedback from the prescribed power-grid and placement evaluation, compared with 31.17 for the strongest measured general-purpose configuration, GPT-6 Astra. The difference is supported by raw congestion and timing measurements and persists across scoring-sensitivity checks. Layout-level analysis further shows that similar global utilization can conceal substantially different local congestion. Together, the protocol and case study assess agents through the physical consequences of their delivered layouts and provide evidence about system performance on this industrial instance.

cs.AI

版本更新 · v2arXiv:2611.03093

An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification

Lakshmi Narayanan P, Narenkarthik K, Naren Kumar C

原文摘要

Claim verification is the task of deciding whether a source text supports a claim, contradicts it, or lacks sufficient evidence. Natural Language Inference (NLI) models can judge whether a single sentence supports or contradicts a claim, but they struggle when the evidence is spread across several sentences. Conversely, Large Language Models (LLMs) can reason across sentences, but may draw conclusions the text does not support. In this experimental study, we test whether a conservative fusion rule, labeling a claim Support or Contradict only when both models agree and defaulting to Not Enough Evidence otherwise, combines their strengths. We construct a benchmark of 2,035 claims from SciFact and CliniFact (858 Support, 152 Contradict, 1,025 Not Enough Evidence). We retrieve the top five most relevant sentences per claim using a hybrid of semantic and lexical (BM25) retrieval, which slightly outperforms either method alone. These retrieved sentences are then provided to every verification model. We then compare a DeBERTa-v3-base-mnli-fever-anli NLI baseline against Llama 3.1 8B, Qwen3 8B, and Mistral 7B. Qwen3 achieves the highest Macro-F1 (0.7937), followed by Llama 3.1 (0.7204) and Mistral (0.6388), while the NLI baseline reaches only 0.3157. Contrary to our hypothesis, fusion degrades performance, dropping Macro-F1 to 0.7392, 0.6730, and 0.5991, respectively. To understand this decline, we analyze agreements, disagreements, and common error patterns between the NLI and LLM verifiers. Our error analysis shows that NLI and LLM disagreements often result in correct LLM predictions being overturned.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.16190

When can an interpretability claim be trusted? Stability and certification of feature dimensionality, ridge leverage and the feature recovery rate

Ali Tajfar, Behnam Tajfar

原文摘要

Interpretability tools increasingly support safety claims, such as that a sparse dictionary has recovered most of a model's features. Such claims rest on measurements with arbitrary thresholds, and small changes to the model weights, a different training seed or a different threshold can reverse them. We study two widely used measurements in toy models and synthetic dictionaries with known ground truth: the feature dimensionality of Elhage et al. and the feature recovery rate (FRR) with a cosine threshold. We characterize exactly where feature dimensionality is discontinuous and replace it with a regularized (ridge) version with sharp stability bounds: the ridge leverage score changes by at most $3\sqrt{3}/(8\sqrtλ)$ times the operator-norm change of the weights, and this constant cannot be improved; for the regularized dimensionality the stability constant grows like $ρ/4$ in the scale $ρ=R/\sqrtλ$, with explicit upper and lower bounds. We also prove certificates stating when a claim "feature $i$ is recovered" must survive a given change of the dictionary. The certificates held in every test and are informative for small perturbations, but certify no feature non-trivially across independently trained dictionaries; at the standard threshold, whether a feature counts as recovered changed with the training seed for 55 percent of features. Experiments use toy models only. The proofs, code and text were drafted by AI agents directed by the authors and checked by an independent blind AI reviewer and by numerical tests; the authors take full responsibility for the content.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16183

Data-Efficient LLM Safety Alignment Guided by Interpretable Features

Hongyu Li, Zhan Yu, Zhe Zhao, Kimmo Yan, Xiong Kuang, Renfen Hu

原文摘要

Existing large language models typically rely on massive fine-tuning datasets for safety alignment, which results in higher costs for safety alignment and often leads to the problem of over-refusal. We propose Less is Safer (LIS), a compact yet highly effective dataset for safety alignment, constructed through interpretable feature-guided selection and adversarial synthesis. Specifically, we leverage Sparse Autoencoder (SAE) activations to efficiently select prompts that cover diverse and interpretable safety features. Then, we employ a multi-agent adversarial synthesis framework to generate harmless prompts that nevertheless elicit unnecessary refusals. LIS contains only 2.4K samples, yet outperforms much larger datasets, e.g., TRIDENT-Core (26K), TRIDENT-Edge (19K) and WildJailbreak (262K), in overall performance on four safety and five over-refusal benchmarks. Through ablation experiments, we demonstrate that neither safety data nor over-refusal data alone can achieve optimal results. We also used safety features from SAE, annotated by an LLM, for data filtering, but the results were inferior to those obtained using the pipeline proposed in this paper.

cs.CL · cs.AI

新论文 · v1arXiv:2611.16182

Same-State Pairs Make One JEPA Proof of the Platonic Representation Hypothesis Vacuous

Xin Li

原文摘要

In a Joint-Embedding Predictive Architecture (JEPA), the JEPA proof of the Platonic Representation Hypothesis (PRH) assumes that every observation determines the world state and that a spectral gap makes minimizers unique up to rotation. Under the hard-whitening population objective, same-state positive pairs make the induced world kernel the identity: every centered whitened state function is a global minimizer, and, when $d_z-1\ge 2k$, two minimizers can have best-rotation squared residual $2k$. The uniqueness claim is conditional; for $k<d_z-1$, where $d_z$ is the number of world states, this limit makes its premise unsatisfiable, so the claim has no content there. The experiments that motivate it leave the assumption: a caption sees only part of an image, and the paper states no experiment meets its hypotheses exactly. The theorem does not reach those experiments, and for $k<d_z-1$ its idealized same-state limit is vacuous. One of the paper's four quantitative results survives: a gap-free lower bound. Its bound vanishes only at perfect scene-explained fraction; it bounds alignment error but cannot certify good-view alignment. A canonical frame is determined only up to a rotation and a latent permutation. Paired samples fix the relative frame at effective rank $k$; a global rotation remains. Component semantics fix the relative permutation only up to signs; value anchors fix it once the mixing frame is pinned. A resource--gauge ledger records which resource fixes which gauge.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16175

Stack more levels: how to get general and human-like Mario playing

Shinichi Arimura, Yuchen Li, Julian Togelius

原文摘要

Super Mario Bros. is widely used in game AI and procedural content generation (PCG), yet it remains unclear whether a model-free agent can reliably win unseen levels. To address this question, we train Proximal Policy Optimization (PPO) agents on increasingly large sets of PCG-generated Mario levels and evaluate their generalization on 1000 held-out test levels. We then shape competent PPO policies into three gameplay archetypes---runner, killer, and collector. Finally, we fine-tune these PPO policies using Diffusion-Reward Adversarial Imitation Learning (DRAIL) with human gameplay demonstrations. We find that increasing the number of distinct PCG-generated training levels generally improves unseen-level performance, and that fine-tuning PPO policies with DRAIL increases action-level human-likeness while preserving much of the persona induced by PPO pretraining.

cs.AI