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
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 02:35 · 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 2026-11-14 02:48 — 2026-11-15 02:48（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：2026-11-15 02:35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

研究日报 / 周报 →按信源浏览 →

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 17 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 02:34（北京时间）
新论文 · v1arXiv:2611.16072

KVPath: Connecting Key-Value Representations Across Transformer Layers

Xuan Luo, Zhiyuan Wang, Hanzhong Cao, Xifeng Yan

原文摘要

Transformers typically cache an independent key-value (KV) representation for each token at every layer. Recent work reveals that a token's KV representations across neighboring layers are correlated and contain shared information. We hypothesize that this correlation implies incremental inter-layer changes, which can be effectively captured by low-dimensional deltas. Motivated by this, we propose KVPath, a new KV representation paradigm that connects KV representations across the network depth into a path. The path establishes a full-dimensional base KV at the first layer, while subsequent layers generate low-dimensional delta KVs to update the preceding KV, thereby constructing their own KV states. By caching the base KV once alongside these compact delta KVs, KVPath preserves distinct layer-specific representations without storing full KV states at every layer. We develop two variants of KVPath: KVPath-Residual, which updates vector values via residual addition, and KVPath-Rolling, which progressively updates feature dimensions in a rolling manner. Under matched parameter counts, KVPath reduces KV-cache storage by up to 68\% for Grouped-Query Attention (GQA) and 55\% for Multi-Head Latent Attention (MLA), while maintaining or even improving model performance.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14149

From Search to Decision: How Post-Training Shapes Information-Seeking Capabilities in Large Language Models

Haohang Huang, Xuan Lu, Mingjin Kuai, Yuxuan Zhang, Wei Ji, Haiyang Zhang

原文摘要

Information seeking in large language model (LLM) systems increasingly involves decisions about when to acquire information, where to search, and how to evaluate and use evidence. Recent post-training methods have improved several such behaviors, but their objectives and evaluations span different tasks and system settings. This paper organizes research around six interrelated information-seeking capabilities and examines the learning signals, optimization methods, update loci, and credit-assignment mechanisms used to develop them. We synthesize empirical progress in targeted behaviors, end-to-end performance, search control, and generalization. Existing studies report gains in retrieval routing, query refinement, multi-tool exploration, evidence-grounded reasoning, and resource-aware search, although the scope of behavioral evidence varies across capabilities. We identify open challenges in estimating prospective retrieval utility, coordinating information-seeking decisions, and adapting to unfamiliar retrieval environments, and discuss evaluation practices for interpreting future progress.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.17558

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs

Yuxuan Lu, Ziyi Wang, Yingzhou Lu, Yisi Sang, Jiri Gesi, Xianfeng Tang, Yimeng Zhang, Zhenwei Dai 等 15 位作者

原文摘要

Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that diverge from real API behavior or generate tasks without ground-truth outcomes for verification. We present FireFly, a pipeline for generating verified tool-call data from real-world MCP servers. Our key insight is to invert the standard synthesis pipeline: rather than generating tasks and hoping they are solvable, we first let a strong LLM explore real APIs along graph-guided DAG structures, then synthesize tasks backward from observed outcomes, guaranteeing label correctness by construction. To handle the scale of real-world tool spaces (${\sim}$1,000 tools), we build a pairwise tool graph and sample sub-DAGs to focus exploration on semantically coherent workflows. To address environment drift in live APIs, we construct a retrieval-augmented simulator that caches all exploration results and replays them during training and evaluation, enabling fully offline and reproducible RL. Applying this pipeline yields 5,144 verified tasks spanning 240 servers and 993 tools. A 4B-parameter model trained with GRPO on FireFly matches Claude Sonnet 4.6 on our held-out test set and shows improvements on multiple tool-calling benchmarks including Tau2-Bench, MCPMark, and MCP-Atlas.

cs.SE · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2607.24743

ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding

Hangjie Yuan, Yichen Qian, Zhiwei Tang, Xianzhe Xu, Sicheng Yang, Lirong Wu, Jinwang Wang, Pengju Wang 等 25 位作者

原文摘要

Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment. In this paper, we introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding that systematically addresses these limitations. We propose a compositional and cascaded vision encoder architecture featuring a Cascade Spatial-Aware Locality Fusion operator that unifies diverse 2D and native 3D medical image understanding within a fused encoder. We further introduce a vision-grounded evaluation framework, including MedIF-Bench for instruction-following assessment and a region-of-interest-grounded method for clinically aligned and factualness-driven report generation evaluation. We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks---spanning visual question answering, report generation, and instruction following---as well as textual medical tasks, outperforming leading open-source medical MLLMs (\textit{e.g.}, Hulu-Med, Lingshu) on 20 out of 24 benchmarks and demonstrating multimodal capabilities better than powerful proprietary models such as GPT-5.2 and Gemini-3-Flash on 13 out of 16 benchmarks, and can be further augmented with agentic tool use for retrieval-augmented and tool-assisted clinical workflows. A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports, and validates our RoI-grounded metric as achieving the strongest correlation with expert judgment among all automatic evaluation metrics examined.

cs.CV · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.21071

面向极少标签前视声呐图像语义分割的协同教师框架

CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels

Ping Guo, Chengzhou Li, Guanchen Meng, Qi Jia, Jinyuan Liu, Zhu Liu, Yu Liu, Zhongxuan Luo 等 9 位作者

AI 速读 基于摘要

提出一种由通用教师与多个声呐专用教师组成的多教师协同框架，通过交替引导与跨教师可靠性评估，在极少标注下提升前视声呐图像语义分割性能。

cs.CV · cs.AI

arXiv ↗PDF ↗
查看原文摘要

As one of the most important underwater sensing technologies, forward-looking sonar exhibits unique imaging characteristics. Sonar images are often affected by severe speckle noise, low texture contrast, acoustic shadows, and geometric distortions. These factors make it difficult for traditional teacher-student frameworks to achieve satisfactory performance in sonar semantic segmentation tasks under extremely limited labeled data conditions. To address this issue, we propose a Collaborative Teacher Semantic Segmentation Framework for forward-looking sonar images. This framework introduces a multi-teacher collaborative mechanism composed of one general teacher and multiple sonar-specific teachers. By adopting a multi-teacher alternating guidance strategy, the student model can learn general semantic representations while simultaneously capturing the unique characteristics of sonar images, thereby achieving more comprehensive and robust feature modeling. Considering the challenges of sonar images, which can lead teachers to generate a large number of noisy pseudo-labels, we further design a cross-teacher reliability assessment mechanism. This mechanism dynamically quantifies the reliability of pseudo-labels by evaluating the consistency and stability of predictions across multiple views and multiple teachers, thereby mitigating the negative impact caused by noisy pseudo-labels. Notably, on the FLSMD dataset, when only 2% of the data is labeled, our method achieves a 5.08% improvement in mIoU compared to other state-of-the-art approaches.

新论文 · v1arXiv:2611.07238

How Do AI Agents Waste Your Money?

Huimin Zeng, Yuxuan Lu, Jesse Cai, Eric Hanchen Jiang, Di Wu, Po-Nien Kung, Wenbo Hu, Ziyi Wang 等 11 位作者

原文摘要

AI agents may consume massive tokens across a wide range of tasks, but how many of those tokens are really necessary? Although prior work has shown that agents can incur unexpectedly high token costs, we still lack a systematic way to identify and measure token waste. In this work, we introduce a unified framework for measuring token waste across heterogeneous agent systems. Our framework records and normalizes complete agent trajectories, identifies removable spans using an LLM-as-a-Judge (LLMaJ), and maps the identified text spans back to the original trajectory for token-level measurement. We validate the identified waste through direct interventions by removing marked spans, resuming agent execution, and measuring changes in task outcomes and subsequent actions. In online pruning experiments, we remove 41-46% of the model's reasoning while largely preserving task performance across two distinct agent benchmarks. Using this framework, we analyze agents across multiple settings. Our analysis shows that token waste has a system-level structure that aggregate token usage alone cannot reveal. First, waste varies more across tasks and agent settings than across models. Second, reasoning and visible execution can exhibit different waste patterns. Third, different harnesses can introduce distinct sources of inefficiency even under the same model and task. Overall, our framework transforms token waste into an actionable optimization signal, enabling researchers and practitioners to train more efficient models, design better reasoning strategies, and optimize agent harnesses toward reducing unnecessary computation rather than merely reducing token usage.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.05721

SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation

Yimeng Zhang, Yingying Zhuang, Ziyi Wang, Yuxuan Lu, Pei Chen, Aman Gupta, Zhe Su, Ming Tan 等 15 位作者

原文摘要

Uncertainty estimation is essential for the trustworthy deployment of LLMs: it underpins self-refinement and serves as a decision signal for downstream systems, from verifiers to collaborating agents. However, existing approaches operate at suboptimal granularities: token-level scores lack semantic coherence, while sequence-level scores fail to localize errors. We formalize Span-Level Uncertainty Estimation (SLUE), a new task that targets the natural granularity for uncertainty: semantically coherent text spans, each conveying a single assessable unit of meaning. To address this task, we introduce SPANUQ, a lightweight probe that distills the uncertainty knowledge from expensive multi-sample inference into a single forward pass over LLM hidden states. SPANUQ employs a DETR-style span decoder to simultaneously detect spans and estimate their uncertainty via a Mixture of Beta distribution, trained with a principled combination of Beta NLL regression and contrastive ranking objectives. We construct SPANUQ-BENCH, the first span-level uncertainty benchmark comprising 20K prompts, 293K annotated spans, and continuous soft labels derived from multi-sample claim verification. Experiments on five LLM backbones show that SPANUQ consistently achieves the best span-level uncertainty quality , outperforming the strongest probe baseline and all sampling-based methods while being 10~20x faster. Its DETR-based span detector attains 0.910 F1, surpassing the best heuristic by 39.4%, enabling precise error localization that sequence-level methods cannot provide. The same architecture ports to five LLMs spanning two model families, with one probe trained per backbone, and we additionally observe that sequence-level uncertainty is partially decomposable, suggesting that span-level estimation subsumes sequence-level as a special case. The project page is available damon-demon.github.io/SpanUQ.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01047

How Close to the Theme? Similarity-Label Conditioning for Game Music Generation

Shangxuan Luo, Zixun Guo, Jinjie Shi, Joshua Reiss

原文摘要

Composers develop music from an original idea, controlling how similar each new section is to it, from near repetition to new material. Game music needs this often, as its material repeats over long play. Music models, however, rarely learn to control similarity from real pieces. We further train a pretrained MIDI model on section pairs from Super Mario pieces. A label states each pair's similarity, and a context vector summarises the given section, or context. For 157 test contexts, the model generates six outputs per label. Twelve measures score the outputs; one main measure each covers melody, pitch content, rhythm and note length. On average, outputs requested as similar are more similar to their context than those requested as dissimilar, and not to other pieces. All twelve measures favour them; each main measure stays significant after correction for multiple tests. On melody, the gap comes mainly from more frequent restatement of the context's melody. Against an otherwise identical model without a label, only the request for high similarity makes outputs more similar. In a listening test, ratings followed melodic overlap with the context most closely of all measures.

cs.SD · cs.LG · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.06388

Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration

Jiaju Chen, Yuxuan Lu, Jiayi Su, Chaoran Chen, Songlin Xiao, Zheng Zhang, Yun Wang, Yunyao Li 等 13 位作者

原文摘要

Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as collaborative partners in human workflows. Effective collaboration, however, requires collaborators to continuously maintain and align mental models of their own reasoning, partners' intentions, and shared goals during the collaborative process. Today's agents rarely develop such capabilities since they are primarily optimized for task completion rather than for maintaining the underlying mental models required for collaborative processes. Moreover, the community lacks authentic human collaboration data with action-level mental model annotations that could guide agents toward collaborative competence. To bridge this gap, we present ALMANAC, a dataset of Action-Level Mental model ANnotations for Agent Collaboration built from the Map Task, a classic dyadic routing task from social science. ALMANAC contains 2,987 collaboration actions, each paired with theory-informed mental model annotations that record the participants' self-reasoning, perceived partner intent, and perceived team goal. We benchmark six LLMs on predicting humans' next-turn behavior and mental models. Our results demonstrate ALMANAC's utility in evaluating models' ability to simulate human collaborative behaviors and infer their underlying mental models. The project page is available at https://human-agent-collab.hailab.io/almanac.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.18587

Dual Dimensionality for Local and Global Attention

Zhiyuan Wang, Xuan Luo, Sirui Zeng, Xifeng Yan

原文摘要

Decoder-only Transformers compute attention over the KV cache of preceding tokens. Keys and Values are typically represented with the same dimensionality, regardless of their distance from the prediction target. In natural language, however, the next word is most strongly influenced by the immediately preceding tokens. We hypothesize that local and distant tokens impose asymmetric demands on representational capacity: local tokens are more critical for predicting immediate outputs and thus require richer representations, whereas distant tokens primarily serve as long-range memory, for which lower-dimensional representations may suffice. We formalize this idea as Distance-Adaptive Representation (DAR), which preserves full-dimensional representations within a local context window while assigning reduced-dimensional representations (e.g. 1/2 or 1/4 of the original dimensionality) to tokens beyond that window. Across multiple pretraining scales (70M to 410M parameters), as well as continued supervised fine-tuning on a 1B-scale model, this approach closely matches the performance of full-dimensional baselines. In contrast, uniformly reducing dimensionality across all token positions leads to worse performance. These results challenge the common assumption that key and value dimensionality should be uniform across token positions. We further develop an efficient realization of DAR that achieves model quality comparable to the MLA baseline while reducing the average KV-cache size by 68.8\% at 8K context and achieving up to a $1.9\times$ decoding speedup at 128K context on the evaluated models. Our findings suggest a new direction for designing attention architectures that allocate representational capacity according to token distance to reduce KV-cache during inference.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01377

A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development

Leming Shen, Qiang Yang, Xinyu Huang, Zijing Ma, Yuanqing Zheng, Chris Xiaoxuan Lu

原文摘要

Large Language Models (LLMs) exhibit powerful code generation abilities, fostering agentic systems to automate edge AI application development. However, existing agents typically operate via fixed agentic workflows and predefined design spaces, struggling to handle rapidly evolving demands of real-world scenarios (e.g., heterogeneous data modalities, diverse task pipelines). Unlike prior systems that treat LLMs mainly as code generators following rigid workflows, we fully exploit their reasoning capabilities to allow agents to determine their own workflows on the fly. To this end, we propose SE2, a self-exploring and self-evolving paradigm for adaptive edge AI development. Inspired by human learning processes, we distill development into four atomic operations (retrieve, reason, code, test), and empower agents to explore workflows by dynamically and adaptively selecting an appropriate next operation based on the current context. Extensive evaluations show that, with adaptive workflows, the synthesized programs achieve up to 26% higher accuracy and consume 28% lower resources than state-of-the-art baselines, while maintaining superior adaptability to unforeseen edge AI scenarios. This highlights the potential of reasoning-driven adaptive agentic workflow in edge AI development.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2033ACL Anthology · ACL 2026

OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation

Ziyi Wang, Yuxuan Lu, Wenbo Li, Amirali Amini Northeastern University and Sharif University of Technology, Bo Sun Northeastern University, Yakov Bart Northeastern University, Weimin Lyu Amazon, Jiri Gesi Amazon Science 等 16 位作者

原文摘要

Can Large Language models (LLMs) accurately simulate the next web action of a specific user? While LLMs have shown promising capabilities in generating believable human behaviors, evaluating their ability to mimic real user behaviors remains an open challenge, largely due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual human user. To address this gap, we introduce OPeRA, a novel dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions. OPeRA is the first public dataset that comprehensively captures: user personas, browser observations, fine-grained web actions, and self-reported just-in-time rationales. We developed both an online questionnaire and a custom browser plugin to gather this dataset with high fidelity. Using OPeRA, we establish the first benchmark to evaluate how well current LLMs can predict a specific user’s next action and rationale with a given persona and history. This dataset lays the groundwork for future research into LLM agents that aim to act as personalized digital twins for human.

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-long.2034ACL Anthology · ACL 2026

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data

Yuxuan Lu, Jing Huang Amazon, Yan Han, Bingsheng Yao Northeastern University, Sisong Bei Amazon, Yaochen Xie Amazon, Yisi Sang Amazon, Qi He 等 9 位作者

原文摘要

Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human’s behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs’ ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models’ performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark and dataset for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.

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-long.2037ACL Anthology · ACL 2026

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents

Ziyi Wang, Yuxuan Lu, Yimeng Zhang Amazon, Pei Chen Amazon, Ziwei Dong, Jing Huang Amazon, Jiri Gesi Amazon Science, Xianfeng Tang Amazon 等 15 位作者

原文摘要

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks.In real-world applications, user requests are often (1) ambiguous, (2) changing over time, or (3) infeasible due to policy constraints, and training and evaluation data that cover these diverse, complex interaction patterns remain under-represented.To bridge the gap, we present Trajectory2Task a verifiable data generation pipeline for studying tool use at scale under three realistic user scenarios: ambiguous intent, changing intent, and infeasible intents.The pipeline first conducts multi-turn exploration to produce valid tool-call trajectories. It then converts these trajectories into user-facing tasks with controlled intent adaptations. This process yields verifiable task that support closed-loop evaluation and training. We benchmark several state-of-the-art LLMs on the generated complex user scenario tasks and observe frequent failures.Finally, using successful trajectories obtained from task rollouts, we fine-tune lightweight LLMs and find consistent improvements across all three conditions, along with better generalization to unseen tool-use domains, indicating stronger tool-calling ability.

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-long.277ACL Anthology · ACL 2026

Structured Episodic Event Memory

Zhengxuan Lu, Dongfang Li, Yukun Shi, Beilun Wang Southeast University, Longyue Wang Alibaba Group, Baotian Hu Harbin Institute of Technology

原文摘要

Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex reasoning. For autonomous agents, these passive and flat architectures lack the cognitive organization necessary to model the dynamic and associative nature of long-term interaction. To address this, we propose Structured Episodic Event Memory (SEEM), a hierarchical framework that synergizes a graph memory layer for relational facts with a dynamic episodic memory layer for narrative progression. Grounded in cognitive frame theory, SEEM transforms interaction streams into structured Episodic Event Frames (EEFs) anchored by precise provenance pointers. Furthermore, we introduce an agentic associative fusion and Reverse Provenance Expansion (RPE) mechanism to reconstruct coherent narrative contexts from fragmented evidence. Experimental results on the LoCoMo and LongMemEval benchmarks demonstrate that SEEM significantly outperforms baselines, enabling agents to maintain superior narrative coherence and logical consistency.

cs.CL · cs.AI

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.790ACL Anthology · ACL 2026

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation

Jiaju Chen, Yuxuan Lu, Xiaojie Wang Amazon, Huimin Zeng, Jing Huang Amazon, Jiri Gesi Amazon Science, Ying Xu Harvard University, Harvard University, Bingsheng Yao Northeastern University 等 9 位作者

原文摘要

Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging “LLM-as-a-judge” paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts’ ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods.

cs.CL · cs.MA

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-srw.77ACL Anthology · ACL 2026

LLMs for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Tasks

Yuxuan Lu, Bingsheng Yao Northeastern University, Shao Zhang Shanghai Artificial Intelligence Laboratory, Yisi Sang Amazon, Yun Wang Microsoft Research, Hansu Gu Amazon, Peng Zhang, Tun Lu Fudan University 等 10 位作者

原文摘要

Deploying machine learning models in real-world domain-specific scenarios is challenged by the scarcity of expert annotations and by data drift, where the statistical properties of incoming data continuously evolve. Active Learning (AL) iteratively improves compact models with expert annotations but suffers from recurring cold-start degradation, while LLMs provide strong off-the-shelf performance yet cannot leverage newly accumulated labels, raising the question: how can we better leverage LLMs to assist the active learning process? Through an empirical study on five legal and biomedical datasets, we reveal a complementary temporal dynamic: LLMs excel during early and post-drift stages, while AL-assisted compact models eventually surpass them as annotations accumulate. Motivated by this finding, we propose an ensemble system that combines an LLM, an AL-assisted compact model, and an automatic switch module that routes predictions to the better-performing model in real time. Evaluated under simulated data drift on two mental health datasets, our system achieves 96–98% switch accuracy and consistently outperforms either model used alone.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) · 2026 · 正式发表