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 10:10 — 2026-11-16 10:10(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 89 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)
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:2611.15735

Where Is Uncertainty Observed? A Mechanistic Understanding of Uncertainty Quantification in LLMs

Xiaoyu Liang, Virginia Ceccatelli, Aliai Eusebi, Tobias Braun, Nils Loose, Carlo Malagnino, Lorenzo Cavallaro

原文摘要

Knowing when a large language model's (LLM's) response can be trusted is critical for its safe use. Uncertainty quantification (UQ) can help LLMs recognize if their responses may be unreliable. Existing taxonomies organize UQ methods by uncertainty source or estimation mechanism. They leave unresolved the question of where uncertainty is observed in the model's computation. The answer matters because the observation point determines whether an estimator has access to enough information to recover a given target, and how well it can recover it. Drawing on mechanistic interpretability, we define four mechanistic observation lenses: the structural lens observes component updates, the representational lens observes hidden states, the distributional lens observes token probabilities, and the semantical lens observes distributions over meanings. We relate these lenses through the residual stream and order them by the information they carry, which gives a principle for selecting UQ methods for different targets. We survey existing methods through the four lenses. Furthermore, we distinguish evaluation targets, criteria, and metrics to clarify different UQ evaluation protocols. Finally, we identify open problems and research directions to connect uncertainty estimation to the internal computation and downstream use of LLMs.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.14700

Probe What-If Worlds Before You Ship: Persona Simulation for Real-World Decision Making

Julie Zhu, Jianheng Hou, Zhixu Silvia Tao, Shi Bo, Yilan Fan, Yixuan He, Zhiyuan Hu, Shirley Huang 等 24 位作者

原文摘要

User research and system testing reveal whether products and services meet user needs, yet recruiting specialized participants, designing controlled what-if comparisons, and repeating studies as designs evolve often bottleneck design iteration and data-driven decision-making. We present a framework and execution infrastructure that translates real-world industry inquiries into controlled experiments with simulated users. Our methodology formally defines the target cohort, experimental stimuli, and decision-relevant metrics, while the pipeline supports large-scale concurrent runs over cohort-stimulus-environment combinations (survey, web, chatbot, and OS app), auditable trial-level logging, cohort-level outcome aggregation, and cross-cohort and cross-variant statistical reports. Across twelve industry partner cases spanning five domains, we show how constructing hard-to-reach or what-if persona cohorts supports exploratory studies and distills simulated responses into testable design hypotheses. Cross-model comparisons on selected cases largely preserve primary conclusions, whereas perturbing or ablating persona attributes alters service outcomes, effect sizes, and inter-group differences, indicating that grounding target cohorts in detailed personas materially shapes simulation results. Together, these studies show that persona-enabled agents can test specified cohorts at design speed, diagnose systems under test, and deliver directional evidence that focuses problem definition, steers design and strategic decisions, and guides further study.

cs.CL

版本更新 · v4arXiv:2605.25379

StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation

Miaohe Niu, Xinyu Liu, Runsong Zhao, Pengxiang Li, Jingbo Zhu, Tong Xiao

原文摘要

Multi-step retrieval-augmented generation requires tracking evolving information needs, selected evidence, and unresolved gaps. However, free-form trajectories conflate this history, forcing each step to implicitly reconstruct the current state, while existing explicit-state methods remain vulnerable to inconsistent state overwrites. To address these limitations, we introduce StateRAG, a framework that coordinates a Planner, Navigator, Retriever, and Verifier through an explicit retrieval state with checked updates. These roles propose updates across four state fields: the plan, retrieval trace, evidence, and sufficiency assessment. A dedicated controller validates each proposal against the accepted state, rejecting inconsistent updates and guiding revisions within the query budget. A final Reader then answers strictly from the validated evidence. Ablation experiments on a shared graph backend show that StateRAG outperforms free-form trajectory and unverified explicit-state baselines on LongBench by 7.7 and 4.1 Macro F1 points, respectively. These gains consistently extend to document QA and flat passage retrieval. Furthermore, StateRAG surpasses the strongest external baselines by 5.3, 5.0, and 4.3 points on LongBench, QASPER, and DocVQA.

cs.CL

版本更新 · v4arXiv:2610.31303

The Value of Memory in Language Agents

Zehao Lin, Erenkai Zhu, Helan Hu, Xixuan Hao, Chunyu Li, Linyun Liu, Kai Chen, Chenxu Du 等 9 位作者

原文摘要

Language agents carry information from past experience into future tasks whose demands may be unknown or change over time. We develop a decision-theoretic account of the capability available in history, retained in storage and realized through use, together with the costs of recovery and revision. Drawing on comparison of statistical experiments, information acquisition and the value of computation, we express these values in units of avoided task loss. Recovery and revision define attainable risk-cost profiles and preservation across uses. A cost-aware simulation condition and five minimal counterexamples establish how information timing, access, computation, feedback and demand shape these comparisons; a pointer with zero answer mutual information can reduce the cost of exact recovery. Allocation and recovery criteria identify when gains pay for estimation, selection and evidence access. Complete-split studies on LoCoMo, LongMemEval-S and PersonaMem cover 3,075 questions and two readers. They show complementary value from saved state and recovered evidence, task-dependent performance orderings, and the role of reuse in amortizing construction costs. Multi-project workflows connect correction to preservation and validation costs. Together, the theory and studies support decisions about what to retain, which recovery options to preserve, and how to adapt memory as evidence and objectives evolve.

cs.AI · cs.CL

新论文 · v1arXiv:2611.12041

SMO: Compiling Natural Language Skills into Graphs of Reusable State-Move-Outcome Bricks

Chao Chen, Jiashuo Zhang, Yunhang Shen, Liangyu Lian, Rongrong Ji

原文摘要

Large language model agents increasingly rely on reusable natural-language skills, yet growing skill collections remain accumulations of isolated text artifacts that are difficult to compare, deduplicate, and compose. We argue that the reusable content of a skill lies not in its surface wording but in its procedural transitions: which operation to execute under a given state and which observable outcome to produce. Based on this observation, we propose State-Move-Outcome (SMO), a compilation-like framework that decomposes raw skills into reusable procedural bricks and organizes admitted bricks as an externalized symbolic structure. When compiling a skill, SMO first retrieves and composes existing bricks, dynamically connects them through Outcome-to-State conditions, and creates a candidate brick only for an uncovered procedure; the candidate becomes reusable only after validation and admission. Experiments on SkillsBench v1.1 demonstrate that SMO represents 232 rawSkills from 87 underlying tasks with 95 shared bricks, reducing the corresponding skill representations from 366,472 to 149,154 tokens--a $\mathbf{59.3}\times$ reduction and $\mathbf{2.46}\times$ compression. Across 232 skill-conditioned evaluation instances, SMO raises the average task score from $\mathbf{0.6379}$ to $\mathbf{0.7478}$ and increases 5/5 Pass instances from $\mathbf{138}$ to $\mathbf{164}$, while matching or outperforming rawSkill on $\mathbf{208}$ of $\mathbf{232}$ instances. It also reduces average runtime token consumption by $\mathbf{38.38\%}$. These results show that compiling natural-language skills into shared procedural units can jointly improve skill reuse, representation efficiency, and downstream execution.

cs.CL

版本更新 · v2arXiv:2611.05877

When Does Better Confidence Improve a Knowledge-Graph Audit?

Zehao Lin, Kai Chen, Xixuan Hao, Erenkai Zhu, Chunyu Li, Helan Hu, Feiyu Xiong

原文摘要

Confidence estimates guide human review in LLM-built knowledge graphs, but an erroneous shared entity need not be the only reason an incident fact is wrong. We study how this distinction affects budgeted audits, alongside selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $Δ^{\mathrm{cl}}$. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. An error-rate $\times$ fan-out baseline leaves 3.98-4.74 percentage points more errors than joint planning with the same actions. Independent-block planning also avoids this disadvantage: its held-out point estimates improve on a fact-only scalar baseline by 1.22-1.79 points and are slightly better than the joint model, although the frozen equivalence criterion remains inconclusive. On 300 DWIE training documents, independent and joint plans also outperform fan-out in point estimates, with extractor-dependent gains over fact-only review. For verification, a generic support check improves three of four model-budget configurations on each held-out set. These comparisons motivate evaluating complete-repair probabilities and retaining both fact-only and factorised baselines when choosing an audit model.

cs.CL

版本更新 · v3arXiv:2610.13277

Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence

Han Luo, Zhan Zhuang, Xu He, Jujia Zhao, Yu Li, Suqin Yuan, Dong Li, Lei Feng

原文摘要

Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare single-vector representations of queries and memories, even when relevance depends on a small part of the content. Such local evidence can be matched to queries using the contextual token representations already computed by the same embedding models. Our method uses sparse token matching to improve retrieval without additional training. Each query token retrieves a small set of matching tokens across candidate memories. The matching scores are aggregated for each memory and combined with whole-memory similarity to rank memories. An optional low-rank query adapter can be trained with supervision while keeping the encoder and stored memory representations fixed. Our method improves retrieval across eight benchmarks and multiple model families without additional training. Query adaptation further increases the gains to 13.3 and 14.3 percentage points in average Recall@10 and NDCG@10 on Qwen3-Embedding-4B. These retrieval gains translate into higher question-answering accuracy on long-term memory benchmarks.

cs.IR · cs.CL

版本更新 · v2arXiv:2603.05432

Ensembling Language Models with Sequential Monte Carlo

Robin Shing Moon Chan, Tianyu Liu, Samuel Kiegeland, Clemente Pasti, Jacob Hoover Vigly, Timothy J. O'Donnell, Ryan Cotterell, Tim Vieira

原文摘要

Combining the predictions of multiple models is one of the most effective strategies in machine learning. Thus, it is only natural to investigate the ensembling of language models (LMs). However, because LMs define distributions over strings, a proper ensemble requires aggregating predictions at the string level, which requires a computation that is generally intractable. In this work, we cast LM ensembling as an inference problem and propose the deployment of sequential Monte Carlo (SMC), an appropriate approximate inference scheme. Concretely, we introduce a unified framework for composing multiple LMs into ensemble distributions parameterized by a broad family of aggregation functions. To sample from these distributions, we introduce an SMC algorithm that operates in a shared byte space, enabling ensembles of models with mismatching vocabularies and consistent sampling in the limit. We evaluate a range of ensembles across prompt and model combinations for various text generation tasks, finding that consensus-seeking strategies such as the product consistently outperform probability averaging, and that better posterior approximations can yield better ensemble performance.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.09868

CodeQuant2:面向低精度大型推理模型的增强型离群值缓解与自适应聚类

CodeQuant2: Enhanced Outlier Mitigation and Adaptive Clustering for Low-Precision LRMs

Xingyu Liu, Xiangyang Yin, Tianhua Xia, Haiyu Wang, Sai Qian Zhang

AI 速读 基于摘要

CodeQuant2 是一种基于聚类的查找表(LUT)量化框架,通过旋转与缩放缓解激活离群值、自适应码本大小并改进校准样本选择,以提升低精度大型推理模型的推理精度与速度。

cs.CL

查看原文摘要

Large reasoning models (LRMs) improve task performance by generating longer intermediate reasoning traces, but this substantially increases inference costs and makes low-precision quantization increasingly important. However, aggressively quantized models often perform poorly on reasoning tasks. We observe larger activation fluctuations during the first decoding steps of reasoning. Calibration that omits these early states may miss their activation fluctuations. To address these reasoning-specific quantization challenges, we propose \textbf{CodeQuant2}, a clustering-based LUT quantization framework for low-precision large reasoning models. CodeQuant2 mitigates activation outliers with rotation and scaling, uses clustering to represent non-uniform weight distributions, and adapts codebook sizes to the quantization difficulty of each layer. Guided by our observation of reasoning-time activation behavior, CodeQuant2 further improves calibration sample selection to better match actual decoding statistics. Combined with our customized LUT CUDA kernel, CodeQuant2 delivers substantial accuracy improvements on reasoning benchmarks while achieving up to $2.85\times$ speedup over BF16.

版本更新 · v2arXiv:2611.08162

RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection

Jihao Zhao, Ding Chen, Yanfang Chen, Bo Tang, Feiyu Xiong, Junchi Yan, Zhiyu Li

原文摘要

LLM service selection requires performance evidence that reflects the demands of the current task. Aggregate scores obscure differences in capability and difficulty, while semantically related examples can involve different combinations of skills. We present RouteAlign, which uses task requirements to structure both the measurement of model performance and the selection of services. Task requirements describe capability demand and difficulty, enabling alignment with corresponding model performance measurements. Historical requirements determine how outcomes contribute to global profiles and local capability estimates; incoming requirements determine how those measurements inform the current decision. A shared scorer integrates the evidence, and a generation-cost preference controls selection among eligible services. Evaluation across diverse tasks and heterogeneous LLM services shows that RouteAlign extends the empirical quality-cost frontier toward higher task quality. Comparisons with open Jev-style decision backends show consistent quality gains, with lower generation cost than their strongest tested configuration. Ablations support the contribution of local performance evidence, while catalog-update experiments demonstrate effective reuse of the fitted scorer with refreshed model measurements.

cs.SE · cs.CL

版本更新 · v3arXiv:2605.10832

Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

Shijue Huang, Hangyu Guo, Guanting Dong, Chenxin Li, Junting Lu, Xinyu Geng, Zhaochen Su, Zhenyu Li 等 11 位作者

原文摘要

Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visual context. Two bottlenecks limit current systems. First, existing tool-use harnesses treat images returned by search, browsing, or transformation as transient outputs, so intermediate visual evidence cannot be re-consumed by later tools. Second, training data is usually built by fixed curation recipes that cannot track the target agent's evolving capability. To address these challenges, we first introduce a visual-native agent harness centered on an image bank reference protocol, which registers every tool-returned image as an addressable <image:N> reference and makes intermediate visual evidence reusable by later tools. On top of this harness, On-policy Data Evolution (ODE) runs a closed-loop data generator that refines itself across rounds from rollouts of the policy being trained. This per-round refinement makes each round's data target what the current policy still needs to learn. The same framework supports both diverse supervised fine-tuning data and policy-aware reinforcement learning data curation, covering the full training lifecycle of the target agent. Across 8 multimodal deep search benchmarks, ODE improves the Qwen3-VL-8B agent from 24.9% to 39.0% on average. At 30B, ODE raises the average score from 30.6% to 41.5%. Further analyses validate the effectiveness of image bank reuse, especially on complex tasks requiring iterative visual refinement, while rollout-feedback evolution yields more grounded SFT traces and better policy-matched RL tasks than static synthesis.

cs.CL

版本更新 · v3arXiv:2507.16271

Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction

Tianyun Zhong, Guozhao Mo, Yanjiang Liu, Yihan Chen, Lingdi Kong, Xuanang Chen, Yaojie Lu, Hongyu Lin 等 12 位作者

原文摘要

Large language models (LLMs) are increasingly expected to extract and synthesize structured information from complex real-world documents, yet they typically produce unstructured, hard-to-verify paragraph-style outputs. We introduce AOE (Arranged and Organized Extraction), a bilingual benchmark that evaluates LLMs' ability to distill long-form, multi-document inputs (64k to 1.8M tokens) into structured tables. AOE comprises 12 tasks across four domains (academic, financial, legal, and medical), each grounded in genuine analytical needs, with schema guidance provided to isolate extraction quality from formatting variance. We evaluate 12 frontier LLMs (both open-weight and proprietary) under four generation settings of increasing autonomy: direct full-document input, RAG-based retrieval, offline document-browsing agent, and online web-search agent. Even the best-performing model achieves only 42.7% Cell F1, and retrieval-augmented approaches often degrade rather than improve performance, revealing that structured extraction from long contexts remains a fundamental challenge - an "Area of Effect" (AOE) that impacts all tested systems.

cs.CL

新论文 · v1arXiv:2611.04480

ReListen: Training-Free Evidence Localization in Hour-Long Audio with Frozen Audio Language Models

Ming-Hao Hsu, Shujie Liu, Yuxuan Hu, Yuxiang Wang, Yingda Shen, Jinyu Li, Zhizheng Wu

原文摘要

Audio language models are meant to answer questions from the audio itself, but an hour-long recording rarely fits in their context, and the answer often depends on a few seconds of it. Transcribing the recording first makes it fit but discards sounds and voices, while systems that return to the audio must be trained for this behavior. We propose ReListen, a training-free method in which a frozen audio language model finds its own evidence before answering. In a Jev-style scan, the model scores each 20-second window by the probability that it helps answer the question, and it then answers from the highest-scoring minute. This minute overlaps the annotated evidence far more often than transcript retrieval, for 88.5% of VoiceGiraffe questions. Without any change, the same scan also grounds events on LAT-Bench as well as a model trained for temporal grounding. Answering from it matches or exceeds hearing the whole recording with a small fraction of the audio, and on VoiceGiraffe it exceeds a transcript of the whole recording by 9.2 points. The selected evidence is also worth hearing rather than reading. Given the same excerpts, reading their transcript matches listening on speech content, but listening is clearly more accurate on questions about sounds and voices. Moreover, ReListen answers faster than every transcript-based system, and its memory stays constant even for recordings too long to hear whole on one GPU. Therefore, a frozen audio language model can search hour-long recordings by itself, without a transcript or additional training.

cs.CL · cs.SD · eess.AS

新论文 · v1arXiv:2611.04449

Near-Zero Token Embeddings Silently Stall Training in Gated Sequence Models

Xin Liu, Boyuan Sun, Yuxin Wang, Haoran Song, Mingjian Zhao, Mengyu Liu

原文摘要

Among 291 surveyed open-weight language model repositories (280 distinct embedding tables), 52.6% of untied gated and hybrid checkpoints (20/38) contain reachable input embeddings with norms below $10^{-6}$, compared with 0% of weight-tied models. Such near-zero rows can arise during pretraining when unseen rare or template tokens receive zero input gradients while AdamW weight decay shrinks untied embeddings. In tested Transformer configurations, non-initial positions or a BOS token prevent this failure mode. In gated sequence models (Mamba, Gated DeltaNet, xLSTM), a near-zero token can amplify input-embedding gradients by more than 30 orders of magnitude (up to 35). At zero input, current-token readout factors (SiLU gates or linear queries) vanish, suppressing historical-state readout. Residual RMS values can then fall below the square root of the RMSNorm floor across consecutive layers, causing Pre-RMSNorm to amplify backward gradients by up to $10^3$ per layer. When a gradient entry exceeds $1.84 \times 10^{19}$, FP32 global-norm clipping in PyTorch, Hugging Face Trainer, and FSDP2 can overflow to infinity and zero the current batch's gradients. In Telugu continual pretraining of Nemotron-3-Nano-4B, this discards updates on approximately 20% of steps and leaves triggered rows frozen. We propose two remedies. For released checkpoints, GroupClip decouples input-embedding clipping using a 64-bit or rescaled norm; its rescaled implementation eliminates update loss and heals triggered rows in one step with negligible measured end-to-end overhead. For pretraining, GateFloor ($\mathrm{SiLU}(z) + δ$, $δ\in [0.01, 0.1]$) keeps the gate positive at zero input, reducing near-zero gradients by 28 orders of magnitude in experiments up to 370M parameters, with perplexity comparable to the baseline.

cs.LG · cs.CL

版本更新 · v2arXiv:2611.02791

PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models

Junyu Lin, Mengjie Wu, Yonghao Dong, Yuchuan Fu, Jinfeng Li, Xiaodan Li, Xiaohan Yuan, Yicheng Liu 等 14 位作者

原文摘要

As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the generation process has become a critical challenge. We introduce PGuard, a native, streaming, and plug-in guardrail that transforms safety monitoring from an external serving dependency into an integrated capability of the backbone model. PGuard directly leverages the backbone's intermediate representations for token-level safety detection, without altering its original inference pathway or generation behavior. Specifically, dynamic layer gating selectively aggregates residual-stream representations across layers to extract safety-relevant signals during both prefill and autoregressive decoding. To balance detection accuracy and computational efficiency, PGuard supports multiple representation-modeling architectures, including a lightweight stateless variant and sequence-aware variants built on multi-scale causal EMA-attention and GRU-based recurrent modules. Its design also accounts for the execution characteristics of LLM serving frameworks, such as SGLang, optimizing computation and data access to minimize additional runtime and synchronization overhead. As a result, PGuard incurs only 0.82-2.26% end-to-end overhead on the hundred-billion-parameter backbone Qwen3.5-122B-A10B served by SGLang. Extensive evaluations across more than 30 benchmarks spanning text and multimodal safety, jailbreaks, cyber and CBRN risks, multilingual scenarios, and real-world traffic demonstrate state-of-the-art performance among native guardrails. On text queries with Qwen3.5-9B, PGuard achieves an average F1 score of 0.836, approaching dedicated external guardrails, while supporting deployment-time configuration of category-specific thresholds and enforcement actions.

cs.CL

版本更新 · v7arXiv:2606.03371

See, Foresee, Act: Intent-Aware World Modeling for Proactive Retail Assistance

Honghui Zhang, Anna Min, Chenmeinian Guo, Yujia Zhang, Zezhou Zhang, Yichen Yu, Guanyu Liu, Yongming Qin 等 12 位作者

原文摘要

World models allow agents to anticipate action consequences, but proactive assistance also requires interpreting incomplete observations and deciding whether to intervene before a user asks for help. We propose See-Foresee-Act and instantiate it as the Proactive Intent World Model (PIWM) for retail assistance. See preserves role-relevant observable evidence alongside AIDA-BDI customer states; Foresee predicts one-step consequences for candidate actions; Act explicitly compares those consequences, including non-intervention. GuidanceSalesBench supplies predominantly synthetic supervision linking observations, states, candidate outcomes, and decisions. On 509 Full test examples, consequence-based selection achieves 63.65% decision accuracy, compared with 45.38% for direct decision output, an improvement of 18.27 percentage points. These results support candidate-consequence comparison for decision reasoning in this retail task. Code and data will be released after consent verification and upon publication.

cs.CL

版本更新 · v2arXiv:2609.22231

EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems

Zeyu Liu, Jian Zhong, Rongduo Han, Ziyang Wu, Shunye Tang, Chenghao He, Yaxuan Yang, Yihang Qiu 等 15 位作者

原文摘要

Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories. Existing evaluations report end-to-end QA accuracy and cannot determine whether errors arise from encoding, retrieval, or generation. We introduce EvalMem, an operation-level diagnostic framework with three parallel Examiners. For each query, the Encoding Examiner checks whether the target fact is stored, the Retrieval Examiner assesses whether the native retriever returns usable evidence, and the Generation Examiner tests whether the model can answer from oracle evidence. Their outputs form fine-grained multi-label defect codes. To improve store-level diagnosis, we adapt agentic RAG with a recall-first strategy that searches using both the query and source evidence, increasing recall of present evidence on LoCoMo from 70.2% to 95.6%. Evaluations of seven memory systems on LoCoMo, LongMemEval-S, and dynamic DynaMem-Bench identify retrieval as the most frequently attributed failure layer; in default LoCoMo, retrieval defects reach 22.1%, compared with 7.7% for encoding and 6.5% for generation. Guided by this diagnosis, MemWiki, a search-friendly auxiliary structure built from each system's memory export, improves mean accuracy by 2.5 and 2.3 percentage points on LoCoMo and LongMemEval-S, respectively.

cs.CL

版本更新 · v2arXiv:2606.25421

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making

Guangfeng Cai, Kaibing Yang, Shuo He, Yu Li, Shengtian Yang, Jiaqi Lv, Lei Feng

原文摘要

Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. However, this objective ties supervision to what a transition happens to reveal, which may omit the dynamics most relevant to the agent's current decision. To bridge this gap, we propose Agent-Authored World Modeling (AAWM), a training procedure that constructs supervision from the policy's own decision needs. Specifically, at each state, the agent identifies what it needs to understand about the environment before acting. These needs drive the retrieval of relevant transition evidence across trajectories, which is then synthesized into training targets that capture decision-oriented dynamics instead of reconstructing the next observation. This aligns the training objective with the dynamics the policy needs before acting, not with the contents of the next observation. Experimental results validate the effectiveness of AAWM across multiple environments and training settings. These results show that decision-aware world-model targets provide a more effective learning signal than next-observation prediction.

cs.CL

版本更新 · v5arXiv:2607.26998

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents

Ruoyu Wang, Heng Zhao, Renjie Wu, Tianhang Zheng, Mengnan Zhao, Wanyu Lin, Kui Ren

原文摘要

Large language model agents automate web penetration testing through observation-action loops, enabling defenders to influence decisions with deceptive decoy observations. Advanced agents can recognize and bypass static decoys, then refocus on real targets. We propose AgentSnare, a trajectory-adaptive deception system that expands a decoy environment alongside exploration. For online deployment, ShadowOS combines an LLM-driven decoy constructor with a virtual kernel. Conditioned on exploration, it generates decoy artifacts that the kernel materializes and handles consistently across interactions, sustaining long-horizon exploration. Because deploying a powerful LLM for decoy construction is costly and slow, we train a small LLM using an offline adversarial interaction-simulation framework. It synthesizes multi-round trajectories by generating candidates and retaining those that sustain simulated interactions. Across 15 CVE-Bench web applications and four attacker models, AgentSnare absorbs 49.9% of tool calls to delay attacks, retains 57.2% of post-entry actions in the decoy to divert trajectories, and grounds 89.5% of completion reports in decoy evidence to defuse threats; across 60 attacker-CVE pairs, no real target is exploited at pass@3.

cs.CR · cs.CL · cs.LG

新论文 · v1arXiv:2611.01834

LegoEnv: Self-Evolving Agentic Environments via Modular Recombination

Zhuosong Jiang, Chengxu Wu, Junqi Liu, Yujie Yi, Siqin Wang, Zhixuan Huang, Jinqian Jiang, Lijun Xiao 等 14 位作者

原文摘要

LLM agents learn by interacting with environments, yet existing environments are designed for specific tasks and fail to generalize to new ones. Recent methods automate environment construction with LLMs. However, they generate each environment from scratch, neither reusing parts shared across environments nor carrying a fix from one environment to the rest. To address this, we propose a new paradigm of evolving environment atoms, which composes environments from reusable atoms (intent, rule, data and server) and evolves the atoms when an environment fails to give reliable feedback (e.g., an application lacks a tool the task requires). To instantiate this paradigm, we introduce LegoEnv, which builds 5,465 verified environments over 223 applications, and one round of evolution raises the share of solvable environments from 71.6% to 88.3%. On AutomationBench, SFT on these environments lifts Qwen3.6-27B from 16.0% to 32.0%, and RL with their verifiers lifts Qwen3.8-27B from 37.6% to 40.3%. Further analyses show steady gains with corpus size, transfer to unseen applications, and failures concentrated in a few shared root causes.

cs.CL · cs.AI

版本更新 · v5arXiv:2607.06540

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

Zhenyu Liu, Xuanyu Zhang, Yunxin Li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Minjun Zhao, Fanbo Meng 等 13 位作者

原文摘要

Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent. In this paper, through an exhaustive fine-grained analysis of model optimization dynamics, we uncover the root cause of such performance degradation, revealing that modality interference arises from inherent gradient conflicts between acoustic and semantic modeling when the two modalities are forced to share a deep parameter space. Guided by this key insight, we introduce Lychee-FD, a native end-to-end full-duplex framework designed to mitigate modality interference. Importantly, we propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel. Extensive experiments on multiple full-duplex benchmarks demonstrate that our method significantly advances the state of the art, yielding substantial improvements in both speech intelligence (+7.4% on Spoken QA) and full-duplex interaction fluidity (+28.5% on FullDuplexBench 1.5) without compromising inference efficiency. To the best of our knowledge, this work is the first to achieve two key advances: 1) uncovering and elucidating the root cause of modality interference in full-duplex SLMs, and 2) designing an elegant hierarchical model together with a practical solution for seamless, high-performance, native intelligent full-duplex SLMs.

cs.CL

版本更新 · v2arXiv:2608.09802

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Yuling Shi, Jinghan Xu, Kelin Fu, Wenhao Zeng, Shilin He, Lei Zhang, Yue Liu, Zelin Zhao 等 15 位作者

原文摘要

As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a substantially harder and more realistic test of agent capability, yet remains underserved by current benchmarks. We introduce SWE-Bench ProMax, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages (Python, Java, TypeScript, Go, C, C++, and Rust). Every instance undergoes rigorous, multi-stage curation that directly addresses the quality problems identified in prior benchmarks: issue descriptions are rewritten from scratch to provide precise, unambiguous specifications, and test suites are manually reviewed to remove overly narrow and overly broad tests. Tasks with insufficient complexity or limited cross-file scope are filtered out, yielding a benchmark of challenging, large-scale refactoring tasks that average 11.5 modified files and 261.6 lines of code per instance, substantially exceeding the scale of existing benchmarks. Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate, confirming that SWE-Bench ProMax presents a meaningful and unsaturated challenge for current AI coding agents. Our benchmark is available at https://huggingface.co/datasets/swe-bench-promax/SWE-Bench-ProMax.

cs.CL · cs.SE

新论文 · v1arXiv:2610.36877

GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents

Bingchao Wang, Yongcheng Jing, Shunyu Liu, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng Tao

原文摘要

Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large language model or VLM in the loop, making them slow and memory-hungry. To address these issues, we propose GUI-JEPA, to our knowledge the first decoder-free GUI agent policy built on a Joint-Embedding Predictive Architecture (JEPA), which selects actions in the latent space of a JEPA encoder pretrained on unlabelled GUI screenshots. Its action- and region-conditioned latent predictor turns the screen latent into one latent per candidate action, letting lightweight heads score all candidates against the instruction in a single batched pass, without decoding a token. We further show that the scorer relies on this latent pathway and that the predictor is trained for the decision itself: a randomly initialised predictor does just as well as one pretrained on screen dynamics. On AndroidControl, GUI-JEPA is 2.8-4.0x faster on the same GPU than a Qwen2.5-VL-7B agent we fine-tune with the same inputs, while reaching 86-92% of its in-distribution accuracy with 6% of its parameters. Code is available at https://github.com/bcwang-sjtu/GUI-JEPA

cs.AI · cs.CL · cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.16ACL Anthology · ACL 2026

Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks

Yihan Wang, Peiyu Liu University of International Business and Economics, Runyu Chen, Jiaxing Pu Zhejiang University of Technology, Wei Xu Renmin University of China

原文摘要

Text-to-SQL technology has evolved rapidly, with diverse academic methods achieving impressive results. However, deploying these techniques in real-world systems remains challenging due to limited integration tools. Despite these advances, we introduce Squrve, a unified, modular, and extensive Text-to-SQL framework designed to bring together research advances and real-world applications. Squrve first establishes a universal execution paradigm that standardizes invocation interfaces, then proposes a multi-actor collaboration mechanism based on seven abstracted effective atomic actor components. Experiments on widely adopted benchmarks demonstrate that the collaborative workflows consistently outperform the original individual methods, thereby opening up a new effective avenue for tackling complex real-world queries. The codes are available at https://github.com/LLM-Cube/Squrve.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.26ACL Anthology · ACL 2026

JointCoder: Exploring Automated ICD Coding on Real-World Chinese EHRs with a Multi-Agent Framework

Kangjun Liu, Zhenyu Li Qilu University of Science and Technology, Jianlei Wang Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Hongjiao Guan, Ying Lian The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Guoqiang Chen The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Tao Xin The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Wenpeng Lu

原文摘要

Automated ICD coding is a critical task for standardizing clinical information from electronic health records (EHRs) and supporting downstream healthcare administration.However, existing automated ICD coding systems face several fundamental challenges. First, the majority of existing research focuses on English ICD tasks, with limited attention to Chinese-language clinical contexts due to the scarcity of publicly available Chinese ICD datasets. Second, most approaches primarily target disease coding, overlooking procedure coding as well as the multi-stage workflows followed in real-world clinical practice. Moreover, many recent methods rely heavily on closed-source large language models or substantial computational resources, which limits their scalability and deployability in clinical environments.To address these gaps, this paper proposes JointCoder, which includes a real-world Chinese ICD coding dataset and a multi-agent framework that reformulates automated ICD coding as a joint disease-procedure coding task. JointCoder explicitly models real-world clinical coding workflows through stage-wise agent collaboration.All agents are instantiated using locally deployed 1.7B-parameter models, enabling scalable and privacy-preserving deployment.Extensive experiments on real-world Chinese ICD coding datasets demonstrate JointCoder’s superiority over state-of-the-art baselines across all evaluation metrics.

cs.CL · cs.MA

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.30ACL Anthology · ACL 2026

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Jiasheng Zheng Institute of Software, Chinese Academy of Sciences, Xin Zheng, Boxi Cao Institute of Software, Chinese Academy of Sciences, Pengbo Wang, Zhengzhao Ma, Qiming Zhu, Jiazhen Jiang, Yaojie Lu Institute of Software, Chinese Academy of Sciences 等 11 位作者

原文摘要

Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, a high-fidelity and scalable system designed to address these limitations in large-scale code training. ScaleBox introduces automated special-judge generation and management, fine-grained parallel execution across test cases with seamless multi-node coordination, and a configuration-driven evaluation suite for reproducible benchmarking. A series of experiments demonstrates that ScaleBox significantly enhances code verification accuracy and efficiency. Our further RLVR experiments show that ScaleBox substantially improves both performance on LiveCodeBench and training stability, significantly outperforming heuristic-matching baselines. By providing a reliable and high-throughput infrastructure, ScaleBox facilitates more effective research and development in large-scale code training.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.116ACL Anthology · ACL 2026

Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination

Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit, Jiaxin Zhang, Vaibhav Vats, Yu Li, Xiangyu Peng, Chien-Sheng Wu

原文摘要

Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.118ACL Anthology · ACL 2026

PAR^2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering

Xingyu Li, Rongguang Wang, Yuying Wang, Mengqing Guo, Chenyang Li, Tao Sheng, Sujith Ravi, Dan Roth

原文摘要

Multi-hop question answering (MHQA) is a practical bottleneck in industry applications such as enterprise assistants, customer-support copilots, and compliance analysis, where systems must combine evidence across multiple documents before answering. Large language models (LLMs) remain brittle in this setting: iterative retrieval can commit too early to low-recall trajectories, while planning-only approaches can produce static query sets that fail to adapt when intermediate evidence changes. We propose Planned Active Retrieval and Reasoning RAG (PAR^2-RAG), a training-free two-stage framework that separates coverage from commitment. PAR^2-RAG first performs breadth-first anchoring to build a high-recall evidence frontier, then applies depth-first refinement with evidence sufficiency control in an iterative loop. This design targets deployment constraints by avoiding retraining cycles, reducing maintenance overhead under changing corpora, and improving scalability across domains. Across four MHQA benchmarks, PAR^2-RAG consistently outperforms strong baselines: compared with IRCoT, it achieves up to 23.5% higher answer accuracy and up to 10.5% NDCG gains in retrieval quality.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.129ACL Anthology · ACL 2026

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment

Yingfeng Luo, Hongyu Liu, DingYang Lin, Kaiyan Chang, Chenglong Wang, Bei Li, Quan Du, Tong Xiao 等 9 位作者

原文摘要

Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensive. A widely adopted remedy is the hybrid system paradigm, which balances cost and quality by serving most requests with a small model and selectively routing a fraction to a large model. However, existing routing strategies often rely on heuristics, external predictors, or absolute quality estimation, which fail to capture whether the large model actually provides a worthwhile improvement over the small one. In this paper, we formulate routing as a budget allocation problem and identify marginal gain, i.e., the large model’s improvement over the small model, as the optimal signal for budgeted decisions. Building on this, we propose RouteLMT (routing for LLM-based MT), an efficient in-model router that predicts this expected gain by probing the small translator’s prompt-token representation, without requiring external models or hypothesis decoding. Extensive experiments demonstrate that our RouteLMT outperforms heuristics, quality/difficulty estimation baselines, achieving a superior quality–budget Pareto frontier. Furthermore, we analyze regression risks and show that a simple guarded variant can mitigate severe quality losses.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表