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

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 15:15 — 2026-11-21 15:15(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 18 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2611.22362

HealthCLBench:Evaluating Context Learning in Health Conversations through Controlled Case Clusters

Ting Yang, Zijing Hong, Chengjie Wang, Peng Wei, Chunxiao Guo, Yun Yue, Xurui Li, Jinqun Guan 等 10 位作者

原文摘要

Complex health conversations require answers grounded in individual information and currently valid evidence. We evaluate health context learning: acquiring, integrating, and applying relevant context during inference with fixed model parameters to answer health questions and respond appropriately to changes in facts, evidence, or task goals. To our knowledge, Chinese-language medical benchmarks have yet to systematically combine explicit contextual difficulties, controlled case variations, and member-specific medical criteria for open-ended answers. We introduce HealthCLBench, comprising 328 controlled clusters, 1,103 cases, and 4,931 rubric criteria across medical consultation and everyday health management. Members share backgrounds while evidence, patient states, or task goals change; each has its own medical scoring requirements. A 70-person medical team annotates and reviews the simulated cases and their rubrics. Human review of 700 full-context responses from the original evaluation yields 90.5% pooled agreement with the original automated judgments at the rubric-item level. We report full-context and query-only results for seven general-purpose models and Ant Afu. Across the eight systems, scores with full context are 11.83 to 31.76 case points and 10.87 to 38.97 geometric cluster points higher than those with the current question alone. GPT-6 Astra leads both full-context metrics at 75.03 and 60.42, followed by Claude Opus 5.5 and Ant Afu. Cross-condition differences describe score changes under the reported evaluation settings. Response comparisons reveal failures in checking historical information, expressing uncertainty when warranted, and ensuring recommendations respect required conditions. The resource supports model comparison and targeted follow-up evaluation.

cs.AI

版本更新 · v3arXiv:2609.00993

AInfer-PD: Communication-Safe In-Place Prefill-Decode Multiplexing for Distributed MoE Rollouts

Guowei Wang, Chaokun Yang, Zhenxuan Pan, Yipeng Wei, Yuhong Guo, Minghua Zhu, Zechuan Zhang, Shuo Wan 等 9 位作者

原文摘要

In agentic reinforcement learning (RL), asynchronous multi-turn trajectories repeatedly introduce continuation prefills (P) while other trajectories remain in decode (D). Efficient rollout completion therefore requires D to advance during long P executions. In-place multiplexing shares devices, model weights, and KV state, but phase-specific communication in distributed MoE introduces two constraints: cross-rank collective ordering and ownership of mutable communication state. Whole-prefill coordination can ensure safe ordering but delays D. DeepEP's normal and low-latency paths suit large P and small D batches, respectively, but safely overlapping them requires separating their mutable communication state. We present AInfer-PD, which extends in-place P/D multiplexing to distributed MoE rollouts. AInfer-PD establishes rank-consistent collective ordering at safe communication boundaries, allowing successive D iterations to advance without waiting for an entire prefill execution to be enqueued or completed. It gives P and D separate communication buffers and protocol state within one DeepEP runtime, allowing P to use the normal path while D retains the low-latency path. Together, these mechanisms preserve useful P/D overlap while sharing model weights and KV storage on the same devices. Across repeated single-node prefill-intensive workloads, AInfer-PD reduces fixed-workload rollout completion time by 7.1-22.5% relative to the same AInfer engine with P/D multiplexing disabled and by 24.8-32.9% relative to SGLang. On two nodes, the reductions are 18.0-35.3% and 18.3-31.8%, respectively. In a same-engine ablation, fine-grained boundaries reduce completion time by a further 8.6-19.8% over whole-prefill asynchronous enqueue.

cs.DC

新论文 · v1arXiv:2611.22458

Sample-Aligned Decoders for Latent Generative Models

Yu Lei, Yi Li, Hongcheng Gao, Yipeng Wei, Liang Li, Li Su, Qingming Huang

原文摘要

Latent generative models synthesize images by decoding generated latents, yet their decoder is trained only to reconstruct encoder latents and never sees the latents it decodes at test time, so the residual errors of the generator are rendered directly into the final image. Existing remedies retrain the generator, add cost at every sampling step, or make the decoder robust to perturbed real latents, assuming that generator errors resemble such perturbations. We find that they do not. Generated latents lie on the encoder latent manifold as closely as real ones, yet follow a different distribution. The decoder should therefore be adapted to the distribution of generated latents, which raises two challenges: (1) unpaired supervision, since a generated latent has no ground-truth image, and (2) latent-space drift, since a decoder freed from paired targets forgets the latent space it must decode. We propose Sample-Aligned Decoders (SAD), a post-training framework that fine-tunes only the decoder of a frozen generator at no inference cost. Generated-Sample Distribution Alignment matches decoded generated latents to unpaired real images in a frozen foundation-model feature space, and Encoder Anchor Preservation keeps the decoder close to the original one on encoder latents. Our analysis shows that the alignment is effective only on generated latents, where it corrects each sample in proportion to how much more often the generator produces such latents than the encoder; on encoder latents it can only work against the anchor. SAD improves four state-of-the-art ImageNet generators across three tokenizers, e.g., FID-50K from 1.15 to 0.98 for REPA-E, complements discriminator guidance, and extends to text-to-image generation. Our code and models are available at https://torpedo2003.github.io/SAD/.

cs.CV · cs.LG

版本更新 · v2arXiv:2611.16591

Singularity-Bench: Can Agents Build Agents?

Yang Zhou, Krish Agarwal, Zhuoming Chen, Zerui Wang, Zhenyu Zhang, Wenshuang Li, Xinpeng Wei, Zhichen Zeng 等 19 位作者

原文摘要

Frontier AI agents increasingly succeed on realistic, long-horizon tasks and are beginning to improve the systems through which they operate. Yet existing benchmarks often restrict agents to narrow action spaces, use simplified environments, or rely on verification methods that are unreliable for evaluating arbitrary agent-generated systems. We introduce Singularity-Bench, an open-ended benchmark for autonomous AI development with six end-to-end tasks spanning pre-training, mid-training, post-training, inference, the agent harness, and cluster orchestration. Each task requires agents to implement core systems from a minimal starting point and evaluates them against mature human-engineered baselines on identical hardware. Additionally, through extensive red-teaming covering 9 of the 10 categories in the OWASP Top 10 for Agentic Applications, we expose reward-hacking vulnerabilities in the conventional Harbor framework and develop Breakwater, an extension of Harbor that blocks all attacks tested in our study. Across 11 agents built from 7 frontier models and 2 harnesses, Opus 5.5 with Claude Code matches or outperforms the human baseline on all six tasks with a Singularity-Index of 1.25, suggesting it may have the skills needed to reach the singularity. The remaining agents average only 0.60. Our vision is for Singularity-Bench to track how much of AI development agents can already automate and when they may transition from assisting to taking end-to-end responsibility for building stronger successors.

cs.AI

新论文 · v1arXiv:2611.20648

Competent Autonomous Driving Through Fine Tuning Vision Language Action Models with Symbolic Traffic Rules

Barkin Dagda, Vinal Asodia, Iman Sharifi, Peng Wei, Saber Fallah

原文摘要

Vision-language-action (VLA) models offer a unified approach to perception, reasoning, and control for autonomous driving, but accurate action prediction alone does not establish compliance with traffic regulations. This paper presents a rule-guided VLA framework that incorporates symbolic traffic-rule feedback into policy optimisation. The framework combines supervised fine-tuning on expert demonstrations with reinforcement learning (RL) refinement using a reward that encourages encoded-rule compliance while penalising deviations from expert actions. Selected provisions of the United Kingdom Highway Code are formalised as executable first-order logic rules using PyReason, covering speed adaptation, following distance, and road-user priority. A frozen vision-language model extracts scene predicates, which are combined with vehicle-state information to assess the projected consequences of candidate control actions. Offline evaluation on held-out data collected in the CARLA simulator compares three group-based RL methods. The results show improvements in both action prediction accuracy and encoded-rule compliance over the supervised baseline. The best-performing variant increases the overall rule pass rate from 92.9% to 97.6%, with zero observed violations of the encoded road-user-priority check in the evaluated samples. These findings support symbolic rule feedback as a means of improving VLA policy alignment with explicit traffic-rule criteria.

cs.CV

版本更新 · v3arXiv:2602.08874

Do Reasoning LLMs Refuse What They Infer in Long Contexts?

Yu Fu, Haz Sameen Shahgir, Huanli Gong, Zhipeng Wei, N. Benjamin Erichson, Yue Dong

原文摘要

Long-context LLMs can infer objectives that are not explicitly stated. This capability is useful for reasoning over documents, code, and tool traces, but it also introduces a safety risk. Harmful intent can be distributed across a context and become apparent only after the model combines the relevant information. Existing safety evaluations largely focus on explicitly stated harmful requests and therefore do not fully capture this failure mode. We introduce compositional reasoning attacks, a long-context attack setting in which harmful requests are decomposed into semantically incomplete fragments and embedded in long contexts. The final query is neutral, and the model must retrieve and combine the fragments to infer the implied harmful objective. Empirically, we show that models generally refuse harmful requests when they are explicitly stated. However, refusal rates drop when the same objectives must be reconstructed from fragments, and these failures often become more pronounced in longer contexts. Our analyses suggest that this gap cannot be explained by retrieval difficulties alone. Models can often reconstruct the harmful objective but do not reliably refuse it. Increasing inference-time reasoning effort improves refusal, but at a higher computational cost, with unsafe responses still occurring. Our results reveal a long-context safety gap: Models are better at refusing harmful requests they see than harmful objectives they infer.

cs.CL · cs.CR

版本更新 · v6arXiv:2507.21183

MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge

Guangchen Lan, Sipeng Zhang, Tianle Wang, Yuwei Zhang, Daoan Zhang, Xinpeng Wei, Xiaoman Pan, Hongming Zhang 等 10 位作者

原文摘要

As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving performance. We propose Maximum a Posteriori Preference Optimization (MaPPO), a methodology for learning from preferences that explicitly incorporates prior reward knowledge into the optimization objective. Building on the paradigm employed by Direct Preference Optimization (DPO) and its variants of treating preference learning as a Maximum Likelihood Estimation (MLE) problem, MaPPO integrates prior reward estimates into a principled Maximum a Posteriori (MaP) objective. This not only generalizes DPO and its variants, but also enhances alignment by mitigating the oversimplified binary classification of responses. Additionally, MaPPO introduces no additional hyperparameters, and supports preference optimization in both offline and online settings. In addition, MaPPO can be used as a plugin for DPO variants, including widely used SimPO, IPO, and CPO, and produce consistent improvements. Extensive empirical evaluations of different model sizes and model series on three standard benchmarks (MT-Bench, AlpacaEval 2.0, and Arena-Hard) demonstrate consistent improvements in alignment performance without sacrificing computational efficiency.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.10432

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

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

原文摘要

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

cs.AI

新论文 · v1arXiv:2611.05168

DSL-Bench: Evaluating and Explaining LLM Code Generation Across Domain-Specific Languages

Zihan Zhou, Mingxi Ye, Yan Gao, Guipeng Wei, Zibin Zheng

原文摘要

Large language models (LLMs) are increasingly used in software-engineering workflows, but code-generation benchmarks largely focus on general-purpose languages. Domain-specific languages (DSLs) have distinct syntax, semantics, and validation requirements, making results from individual DSL benchmarks difficult to compare. We present DSL-Bench, an executable benchmark and analysis framework for cross-DSL code generation. Starting from 13,045 DSL-related papers, LLM-assisted open card sorting identifies 18 representative application domains. For each domain, we select an evaluable DSL and provide a syntax checker and task-level semantic oracle. Evaluating 7 LLMs on 18 DSLs, we observe mean syntax and semantic pass rates of 31.37% and 11.64%, respectively, revealing a substantial gap between syntax acceptance and semantic correctness. A variance decomposition attributes 76.99% of semantic pass-rate variation to differences among DSLs and 7.86% to differences among models. Among four DSL-level factors, Knowledge Demand has the strongest negative association with semantic correctness (r = -0.508). We evaluate prompt engineering across all 18 DSLs and study five improvement methods on five targeted DSLs. Prompt engineering yields uneven gains; RAG-Refinement, the strongest targeted method, improves semantic correctness by 16.29 percentage points on average over matched baselines. We further derive capability profiles and DSL-Profiler summaries for interpreting data-scarce DSLs. These results highlight toolchain-specific semantic bottlenecks and the need to evaluate DSL code generation beyond syntax acceptance.

cs.SE

版本更新 · v5arXiv:2607.22877

Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle

Yang Wang, Hongxuan Liu, Xinghui Xu, Arjun Menon, Xiaoran Cai, Yunyu He, Alex Tarvo, Jingzong Zhou 等 43 位作者

原文摘要

Physical intelligence refers to intelligence systems that understand, reason about and act in accordance with the physical world and its underlying laws, dynamics, and constraints. Unlike conventional AI systems, physical intelligence interacts continuously with uncertain physical environments, and its actions produce consequences that are physically irreversible. As existing trustworthy AI frameworks have been developed primarily for digital AI systems, they do not fully capture the distinctive challenges of Physical Intelligence, such as physical safety, cyber-physical security, and physical manufacturing process. To address this gap, our paper develop a foundation for understanding, operationalizing, and governing trustworthy physical intelligence. First, we characterize the fundamental capabilities of physical intelligence. Second, we investigate the role of physical laws and principles in AI and analyze the associated challenges of physical intelligence. Third, we provide a unified structure of the end-to-end physical intelligence life cycle across five core stages and introduce the Trustworthy Physical Intelligence Operationalization (T-PAIO) framework. Fourth, we formulate the Trustworthy Physical Intelligence (T-PAI) Principles as a theoretical framework that synthesizes key trustworthiness dimensions and establishes a conceptual foundation for the governance of physical intelligence systems.

cs.AI · cs.HC · cs.RO

版本更新 · v2arXiv:2610.03335

Randomization Beyond Deterministic Adaptivity in Parallel Sampling

Da Li, Bo Jin, Xiaopeng Wei

原文摘要

Parallel samplers, including masked diffusion models, generate several coordinates per round from conditional marginals, and their accuracy depends on which coordinates are revealed together. A schedule can be improved in two natural ways: adaptively, by choosing later batches from the values already generated, or by randomization, by drawing the schedule at random. We show that randomization is strictly more powerful. For every $r \geq 1$ we construct a full-support distribution on $9r$ binary coordinates such that every deterministic three-round sampler, even with value-dependent batches and arbitrary product kernels, has forward Kullback-Leibler divergence at least $γr - \log 4$ with $γ\approx 0.0966$, whereas drawing one of four fixed schedules with two fair bits drives the divergence below $18 r β^r$ with $β\approx 0.966$. Both samplers query conditionals of the same target. The separation holds for every fixed number of rounds $T \geq 2$, a strict advantage survives perturbations of the target and errors in the conditional predictor, and exact rational arithmetic certifies the gap at nine coordinates, where trained neural predictors preserve it. The mechanism is a hidden mixture: each schedule preserves the dependence pattern of one component, while no deterministic first batch can serve them all.

cs.IT

新论文 · v1arXiv:2610.39470

RoFiGR: Coarse Routing, Fine Refinement via Level-Adaptive Distillation in Multimodal Generative Recommendation

Ji Dai, Zhipeng Wei, Zhuang Zhuang, Rongfeng Guo, Jie Chen, Quan Fang, Fei Pan

原文摘要

Generative recommenders predict an item's semantic identifier (SID) one code at a time. Early codes select broad branches, so a routing error can exclude relevant items before fine-grained prediction begins. In multimodal recommendation, these coarse decisions must reflect collaborative preferences as well as item semantics. We introduce RoFiGR, a two-tree recommender that uses collaborative information in both SID construction and generation. It aligns cumulative L1-L2 code vectors with frozen collaborative item embeddings and explicitly encodes item distance and source level in the serialized history. During generation, a sequential teacher supervises legal branches. Fixed coarse-level weights maintain routing supervision, while a bounded adaptive residual allocates additional weight according to teacher-student demand. On Instruments, Arts, and Games, RoFiGR improves all five ranking metrics over the evaluated external baselines. Five-seed paired tests with Holm correction support the main NDCG@10 improvements. Comparisons with alternative collaborative supervision objectives and tokenizers support the proposed design. Matched task and decoding analyses distinguish the effects of training exposure, stream fusion, and candidate budgets.

cs.IR

版本更新 · v2arXiv:2610.16959

DiTSG: Context-Aware Air Traffic Scene Generation with Multi-Agent Diffusion Transformers

Seokbin Yoon, Kyungmin Kim, Taejung Kwon, Keumjin Lee, Peng Wei

原文摘要

Understanding how many aircraft, and which traffic configurations, can be safely and efficiently managed by air traffic controllers within a given airspace is fundamental to air traffic management. Air traffic controllers continuously modify aircraft trajectories through interventions such as speed advisories and radar vectoring, and the patterns of these interventions are difficult to capture effectively using existing air traffic simulators. To address this limitation, we propose Diffusion Transformers for Traffic Scene Generation (DiTSG), which learns to generate air traffic scenes from recorded multi-aircraft trajectories. DiTSG employs stacked multi-agent inverted Transformer layers as the denoising backbone of a diffusion transformer, jointly generates the trajectories of multiple aircraft within a traffic scene, and conditions the generation on agent-specific required times of arrival. The resulting trajectories generated by DiTSG preserve realistic inter-aircraft interactions observed in actual air traffic operations. Experiments show that the DiTSG generates diverse traffic scenes that reproduce the statistical properties of recorded traffic while preserving realistic inter-aircraft interactions.

cs.MA · cs.LG · cs.RO

版本更新 · v2arXiv:2605.24218

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Jian Xie, Tianhe Lin, Zilu Wang, Yuting Ning, Yuekun Yao, Tianci Xue, Zhehao Zhang, Zhongyang Li 等 19 位作者

原文摘要

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.

cs.CL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.514ACL Anthology · ACL 2026

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs

Wenzhuo Xu Qihoo 360, Zhipeng Wei, Zonghao Ying, Deyue Zhang Qihoo 360, Dongdong Yang Qihoo 360, Xiangzheng Zhang, Quanchen Zou Beijing Qihoo Technology Co., Ltd.

原文摘要

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to less efforts on multi-image safety alignment. Previous MLLM jailbreak methods only uses a single image, which restricts the attack space: they cannot distribute harmful requests across multiple images, carry abundant information, or exploit additional visual reasoning tasks to distract MLLMs. To address these limitations, in this paper, we propose a compositional jailbreak framework, \textbf{DMN}, which leverages \textbf{D}istributed instruction, \textbf{M}ultimodal evidence and a \textbf{N}umber chain task to fully enhance the jailbreak performance. Extensive experiments show that DMN is highly effective for MLLM jailbreaking, e.g. achieving attack success rates of over 90% on GPT-4o, Gemini-2.5-pro and Claude Sonnet 4, surpassing other baselines by a large margin. This compositional, multi-image jailbreak strategy reveals fundamental weaknesses in their safety mechanisms.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.988ACL Anthology · ACL 2026

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning

Junjie Wang Ant Group, Zequn Xie, Dan Yang, Jie Feng, Yue Shen antgroup, Duolin Sun, Meixiu Long, Yihan Jiao 等 12 位作者

原文摘要

Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning. Concretely, we model the agent’s search process as a state graph and cast trajectory optimization as a minimum-necessary Directed Acyclic Graph (DAG) mining problem, yielding pruned trajectories that preserve essential reasoning while eliminating redundant steps. Continued training on these refined trajectories enables the agent to evolve toward more efficient search patterns and reduces tool-call rounds by about 20% while improving accuracy. Furthermore, we introduce a new metric called F-AE Score to measure the model’s overall performance in balancing accuracy and efficiency. Experiments demonstrate that WebClipper compresses tool-call rounds under excellent performance, providing practical insight into balancing effectiveness and efficiency in web agent design.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-short.14ACL Anthology · ACL 2026

Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization

Gongbo Zhang Columbia University, Yifan Peng Weill Cornell Medicine, Cornell University, Chunhua Weng Columbia University

原文摘要

Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge. Recent agentic RAG systems extend this paradigm by introducing critic agents that evaluate model responses and iteratively refine outputs. However, most prior work implicitly assumes reliable critic feedback and focuses on planning strategies, while paying limited attention to the robustness of the error correction process itself, which is often hindered by misaligned error categories and ineffective or incorrect corrections. We hypothesize that RAG performance can be improved without explicit error categorization. To this end, we propose RePAIR, a response–action learning paradigm that directly maps flawed RAG outputs to error-mitigating action plans without relying on fine-grained error taxonomies or explicit critic supervision. Across multiple benchmarks, RePAIR consistently improves agentic RAG performance.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-short.24ACL Anthology · ACL 2026

MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation

Yi Lin Weill Cornell Medicine, Cornell University, Yihao Ding University of Western Australia, Yonghui Wu University of Florida, Yifan Peng Weill Cornell Medicine, Cornell University

原文摘要

Automated 3D radiology report generation often suffers from clinical hallucinations and a lack of the iterative verification found in human practice. While recent Vision-Language Models (VLMs) have advanced the field, they typically operate as monolithic “black-box” systems without the collaborative oversight characteristic of clinical workflows. To address these challenges, we propose MARCH (Multi-Agent Radiology Clinical Hierarchy), a multi-agent framework that emulates the professional hierarchy of radiology departments and assigns specialized roles to distinct agents. MARCH utilizes a Resident Agent for initial drafting with multi-scale CT feature extraction, multiple Fellow Agents for retrieval-augmented revision, and an Attending Agent that orchestrates an iterative, stance-based consensus discourse to resolve diagnostic discrepancies. On the RadGenome-ChestCT dataset, MARCH significantly outperforms state-of-the-art baselines in both clinical fidelity and linguistic accuracy. Our work demonstrates that modeling human-like organizational structures enhances the reliability of AI in high-stakes medical domains.

cs.CL · cs.MA · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表