paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification

Dylan Bouchard, Mohit Singh Chauhan, Zeya Ahmad, Ho-Kyeong Ra

Large language models have shown impressive capabilities in code generation, yet they often produce functionally incorrect code. Uncertainty quantification (UQ) methods have emerged as a promising approach for detecting hallucinations in natural language generation, but their effectiveness for code generation tasks remains underexplored. We systematically evaluate how UQ techniques transfer to code generation across three programming languages, five LLMs, and over 1,700 problems. We find that some token-probability-based methods generalize effectively without modification, while sampling-based methods relying on natural language inference (NLI) fail because NLI models cannot distinguish functionally different code, causing most responses to collapse into a single semantic cluster. To address this, we introduce \emph{functional equivalence methods}, a family of code-specific methods that replace NLI-based semantic equivalence with an LLM-based functional equivalence assessment, including functional entropy, a code-specific analog of semantic entropy. Functional equivalence methods achieve top AUROC in 11 out of 15 model-benchmark combinations and the best calibration across most settings, consistently outperforming both NLI-based counterparts and all other methods evaluated.

arXiv

Rethinking the Multilingual Reasoning Gap with Layer Swap

Maxence Lasbordes, Amélie Chatelain, Djamé Seddah

Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior work suggests that forcing the CoT to remain in the input language (native reasoning) substantially degrades performance relative to allowing the model to reason in English before answering in the input language (English-pivoted reasoning). However, most studies of this native reasoning gap rely on inference-time interventions or limited native-language training data. We revisit this comparison at a larger scale and under comparable supervision. We construct long multilingual reasoning datasets across six languages (English, French, German, Spanish, Chinese and Swahili); fine-tune specialists in both native and English-pivoted regimes on top of Qwen/Qwen3-8B-Base, and evaluate across mathematics, science, general knowledge, and code. In this setting, the average native reasoning gap shrinks to 1.9--3.5% across the five non-English languages, considerably smaller than previously reported. Weight-space analysis of the native specialists reveals aligned fine-tuning updates in the middle layers and divergence in the outer layers. This points to a largely language-agnostic reasoning core surrounded by language-specific layers. Exploiting this structure, we introduce a Layer Swap: transferring the English specialist's stronger reasoning mid-layers into each native specialist, closing most of the native reasoning gap across the five non-English languages while preserving CoT in the target language. We release all models and datasets.

arXiv

AgentDiff: Meaning-Bearing Rewrites Trigger Deeper Divergence than Presentation Changes in LLM Agents

Liyun Zhang, Jiayi Guo

LLM agents should respond to what an input means, not how it is presented. We show that they do not treat these two kinds of variation equally. AgentDiff measures the difference between answer changes caused by meaning-bearing rewrites (paraphrase and synonym substitution) and presentation changes (reordering, formatting, and distractors), while matching perturbation severity. Across 68 model--benchmark--scaffold cells spanning ten LLMs from seven architecture families, three benchmarks, 1{,}530 original questions, and approximately 11{,}150 variants, meaning-bearing rewrites produce a $+19.69$ percentage-point higher inconsistency rate (paired $t=9.58$, $p<0.0001$; 64/68 cells positive). The result is stable under four severity proxies ($+18.9$ to $+20.9$~pp, all $p<0.0001$) and remains $+11.10$~pp on the 48 cells outside the qwen family. A fully held-out qwen2.5-14B-Instruct evaluation then tests the structure of this effect on 1{,}800 new trajectories: the pre-registered capable-and-tractable partition is positive in 3/4 held-out cells and remains sharply separated after pooling (Welch $t=3.81$, $p=9.6\!\times\!10^{-4}$). Trace analysis explains how the difference propagates. Meaning-bearing rewrites preserve the first action but reduce thought similarity from step 2 onward by $5.6$--$10.5$ points and extend the resulting cascade by $0.17$ steps (paired $t=7.69$, $p=2.5\!\times\!10^{-14}$), a pattern we call \emph{stealth divergence}. AgentDiff therefore establishes a reproducible directional robustness gap, identifies the regime in which it is most reliable, and connects final-answer inconsistency to a distinct trajectory-level signature. Code, perturbations, trajectories, and analysis scripts are released for review at https://anonymous.4open.science/r/agentdiff-emnlp-0BB4/

arXiv

Amplifying, Not Learning: The Price of Out-of-Distribution Generalization in AI-Text Detection

Alexander Smirnov

AI-text detectors gate decisions in education, hiring, and publishing, yet they flag the most fluent, formal human writing as machine-generated: they rate the median formal-native human essay as 99.5% likely AI while clearing genuine high-temperature AI at 10.5%. Deployed detectors share it (chatgpt-detector-roberta flags 56% of formal essays at a 1% false-alarm rate). This is not a calibration bug but the signature of one mechanism: a fine-tuned detector does not learn an AI-versus-human boundary, it amplifies an inherited typicality axis (predictability under a language model) that pre-exists fine-tuning, rescaling it rather than constructing one. Decomposing the detector into this inherited reading and a fine-tuned residual, the inherited part carries the bulk of cross-generator transfer and produces the over-flagging of formal humans, while the residual is generator-specific and does not transfer; a frozen-representation probe fit on ~25 labels per class matches the fully fine-tuned detector on unseen generators (cross-generator AUROC 0.893 vs 0.831). This yields a no-go: because the axis that transfers is the axis that over-flags, no training objective, threshold, concept-erasure, or ensemble we test removes the harm while preserving cross-generator detection, across three architectures, fine-tuned decoders, and zero-shot perplexity detectors. A closed-form, training-free operator relocates and diagnoses the bias (reviving a dead deployed detector, true-positive rate 0 to 0.904 at a 1% false-alarm rate) but, consistent with the no-go, is AUROC-neutral on cross-generator detection: it moves the bias, it cannot erase it. The mechanism is not specific to English prose: the over-flag and the decomposition replicate in Chinese and in code. Detector unfairness is a predictable, structural property of the detection paradigm, the price of out-of-distribution generalization.

arXiv

Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization

Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann

Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We introduce Macro, a preference alignment framework that applies Direct Preference Optimization (DPO) to multilingual SCE generation, using a composite scoring function to construct preference pairs that effectively translate the trade-off into measurable preference signals. Experiments across four LLMs and seven typologically diverse languages show that Macro improves validity by 12.55\% on average over the chain-of-thought baseline without degrading minimality, while avoiding the severe minimality violations of the translation-based baseline. Compared to supervised fine-tuning, Macro achieves superior performance on both metrics, confirming that explicit preference optimization is essential for balancing this trade-off. Further analyses reveal that Macro increases cross-lingual perturbation alignment and mitigates common generation errors. Our results highlight preference optimization as a promising direction for enhancing multilingual model explanations.

arXiv

When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models

Ziyu Liu, Tao Li, Tao Yang, Tianjie Ni, Xiaolong Lan, Wengang Ma, Junjiang He

Data-poisoning backdoors pose a practical threat to the fine-tuning of large language models (LLMs). Most existing attacks bind an attacker-selected behavior to fixed tokens, phrases, scenarios, or syntactic structures. These discrete triggers provide concrete handles for defenses based on local token anomalies, pattern matching, or trigger recovery. We found that, \emph{under semantics-preserving rewriting, emotionally styled inputs form representation clusters distinct from their neutral counterparts}. Meanwhile, de-emotionalised controls move back towards the neutral distribution. This observation motivates our method \textbf{Paraesthesia}, a dynamic backdoor attack that encodes its triggering condition in an emotional style. Paraesthesia maps target emotions into a valence--arousal space, rewrites a small subset of clean samples, and retains semantically faithful rewrites for fine-tuning. Across instruction-following and classification tasks evaluated on four major LLMs, Paraesthesia achieves an attack success rate(ASR) above 98.25\%, while introducing only negligible degradation to clean utility across the vast majority of model-task setups. Surface feature controls and paired de-emotionalization experiments demonstrate that no examined token-level cue can fully account for the triggered behavior. ASR remains high after word-level filtering, sample clustering, and subsequent clean-update procedures, whereas a white-box decoding defense with access to a task-aligned clean reference provides a distinct mitigation path. These findings identify emotional style as a concrete backdoor trigger surface beyond fixed lexical and syntactic patterns.\par\smallskip \noindent \textcolor{red}{\textbf{WARNING: }\textnormal{This paper contains risk-related textual content.}}

arXiv

Cubit: Token Mixer with Kernel Ridge Regression

Chuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Liangchen Tan, Mac Schwager, Anderson Schneider, Yuriy Nevmyvaka, Xiaodong Liu

Since its introduction in 2017, the Transformer has become one of the most widely adopted architectures in modern deep learning. Despite extensive efforts to improve positional encoding, attention mechanisms, and feed-forward networks, the core token-mixing mechanism in Transformers remains attention. In this work, we show that the attention module in Transformers can be interpreted as performing Nadaraya-Watson regression, where it computes similarities between tokens and aggregates the corresponding values accordingly. Motivated by this perspective, we propose Cubit, a potential next-generation architecture that leverages Kernel Ridge Regression (KRR), while the vanilla Transformer relies on Nadaraya-Watson regression. Specifically, Cubit modifies the classical attention computation by incorporating the closed-form solution of KRR, combining value aggregation through kernel similarities with normalization via the inverse of the kernel matrix. To improve the training stability, we further propose the Limited-Range Rescale (LRR), which rescales the value layer within a controlled range. We argue that Cubit, as a KRR-based architecture, provides a stronger mathematical foundation than the vanilla Transformer, whose attention mechanism corresponds to Nadaraya-Watson regression. We validate this claim through comprehensive experiments. The experimental results suggest that Cubit may exhibit stronger long-sequence modeling capability. In particular, its performance gain over the Transformer appears to increase as the training sequence length grows.

arXiv

Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG

Yiqun Sun, Pengfei Wei, Lawrence B. Hsieh

Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results, with no view of how the corpus is organized or what it has not yet seen. We present Corpus2Skill, a system-level retrieval architecture for bounded, structurally coherent corpora such as enterprise knowledge bases: an offline compiler distills the corpus into a hierarchical skill directory, and at serve time an LLM agent navigates it, drilling from a bird's-eye view through progressively finer summaries down to documents and backtracking when a branch is unproductive. On an enterprise customer-support benchmark, Corpus2Skill improves both answer quality and grounding over single-shot dense, hybrid, hierarchical-retrieval, and agentic RAG baselines at a moderate cost tradeoff, and the lead persists under encoder-matched controls and paired significance tests. An eleven-dataset study shows that corpus navigation is not a universal replacement for retrieval: it significantly wins on five datasets, ties on three, and loses on three. It helps on single-domain corpora with a recoverable topical taxonomy, but flat retrieval remains preferable on open-domain factoid pools or homogeneous-tabular corpora that defeat top-level clustering. We characterize this scope distinction as a design guideline for knowledge-grounded systems. Code is available at https://github.com/dukesun99/Corpus2Skill.

arXiv

Synthesizing Instruction-Tuning Datasets with Contrastive Decoding

Tatsuya Ichinose, Youmi Ma, Masanari Oi, Ryuto Koike, Naoaki Okazaki

Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the existing literature overlooks a property of LLM-generated responses: they conflate world knowledge acquired during pre-training with instruction-following capabilities acquired during post-training. We hypothesize that disentangling the instruction-following capabilities from pre-trained knowledge improves the effectiveness of instruction tuning. To this end, we propose CoDIT, a method that applies contrastive decoding between a post-trained model and its pre-trained counterpart during response generation. The method suppresses pre-trained knowledge shared between the two models while amplifying the instruction-following behavior acquired via post-training, resulting in responses that more purely reflect instruction-following capabilities. Experiment results demonstrate that models trained on datasets constructed via CoDIT consistently outperform those trained on directly generated responses. Training on our datasets also yields better performance than on existing publicly available instruction-tuning datasets across multiple benchmarks. Furthermore, we theoretically and empirically show that CoDIT can be interpreted as distilling the chat vector from parameter space to text space, enabling the transfer of instruction-tuning capabilities across models of different architectures.

arXiv

Sell More, Play Less: Benchmarking LLM Realistic Selling Skill

Xuanbo Su, Wenhao Hu, Le Zhan, Yuting Xie, Kailin Lyu, Kaijie Chen, Ziwei Li, Yeqiang Wang, Haibo Su, Yunzhang Chen, Ling Huang

Sales dialogues require multi-turn, goal-directed persuasion under asymmetric incentives, which makes them a challenging setting for large language models (LLMs). Yet existing dialogue benchmarks rarely measure deal progression and outcomes. We introduce SalesLLM benchmark, a bilingual (ZH/EN) benchmark derived from realistic applications covering Financial Services and Consumer Goods, built from 30,074 scripted configurations and 1,805 curated multi-turn scenarios with controllable difficulty and personas. We propose a fully automatic evaluation pipeline that combines (i) an LLM judge for sales-process progress, and (ii) fine-tuned BERT classifiers for end-of-dialogue buying intent. To improve simulation fidelity, we train a user model, CustomerLM, with SFT and DPO on 8,000+ crowdworker-involved sales conversations, reducing role inversion from 17.44% (GPT-4o) to 8.8%. SalesLLM benchmark scores correlate strongly with human ratings (average Pearson r=0.86; inter-annotator agreement Krippendorff's alpha=0.86, 500 annotations per model). Across 15 mainstream LLMs, in Chinese the strongest models are competitive with typical (junior-to-intermediate) human salespeople -- not with sales experts -- while weaker ones fall below this baseline, and cross-lingual consistency remains poor. SalesLLM benchmark serves as a scalable benchmark for outcome-oriented sales agents. Our code and data are released at https://github.com/Bairong-Xdynamics/Benchmarking-LLM-Realistic-Selling-Skill

arXiv

MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control

Yuchi Wang, Dingkang Yang, Haiyang Yu, Weikang BIAN, Jiefeng Long, Xiao Liang, Chao Feng, Hongsheng Li

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format of reasoning. Second, reasoning is not universally beneficial for embedding tasks. Enforcing reasoning for all inputs may introduce unnecessary computation and latency, and can even obscure salient semantic signals for simple cases. To address these issues, we propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework. We formulate reasoning as a latent variable and introduce pair-aware reasoning selection that employs counterfactual intervention to identify reasoning paths beneficial for query-target alignment. Furthermore, we adopt reinforcement learning to selectively invoke reasoning only when necessary. Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.

arXiv

Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER

Ahmed Ewais, Ahmed Hashish, Amr Ali

Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, where tokens attend only to preceding context, prevents effective token classification when disambiguation requires future context. Existing approaches use LLMs generatively, prompting them to list entities or produce structured outputs, but suffer from slow autoregressive decoding, hallucinated entities, and formatting errors. We propose Just Pass Twice (JPT), a simple yet effective method that enables causal LLMs to perform discriminative token classification with full bidirectional context. Our key insight is that concatenating the input to itself lets each token in the second pass attend to the complete sentence, requiring no architectural modifications. We combine these representations with definition-guided entity embeddings for flexible zero-shot generalization. Our approach achieves state-of-the-art results on zero-shot NER benchmarks, surpassing the previous best method by +7.9 F1 on average across CrossNER and MIT benchmarks, being over 20x faster than comparable generative methods. Interactive demo and access to the model are available at https://witness-ai-jpt-ner.hf.space/

arXiv

Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval

Seiji Maekawa, Moin Aminnaseri, Pouya Pezeshkpour, Estevam Hruschka

Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collections. While stronger embedders can better understand such queries, re-embedding large corpora or fine-tuning large models is often impractical. We propose Efficient Retrieval Adapter (ERA), a query-side adapter learning framework for re-index-free retrieval adaptation. ERA first aligns the embedding spaces of a strong query embedder and a lightweight document embedder using unlabeled corpus documents, and then adapts the aligned query representation with a small number of labeled query-document pairs. Across 126 MAIR retrieval tasks from six domains, ERA improves average nDCG@10 by up to 8.2 points in symmetric settings and by more than 12 points in asymmetric settings, while using substantially fewer labels than supervised adapter training. These results show that retrieval systems can benefit from stronger query understanding without updating backbone embedders or rebuilding document indexes.

arXiv

Mitigating LLM biases toward spurious social contexts using direct preference optimization

HyunJi Nam, Dorottya Demszky

LLMs are increasingly used for high-stakes decision-making, yet their sensitivity to spurious context can introduce harmful biases. This is a critical concern when models are deployed for tasks like evaluating teachers' instructional quality, where biased assessment can affect teachers' professional development and career. We investigate model robustness to spurious social contexts about teachers using the largest publicly available dataset of U.S. classroom transcripts (NCTE) paired with expert evaluation scores. Evaluating seven frontier and open-weight models across seven categories of spurious contexts -- including teacher experience, education level, demographic identity, and sycophancy-inducing framings -- we find that irrelevant contexts can shift model-generated ratings by up to 1.48 points on a 7-point scale. Prompt-based mitigations and popular post-training methods, such as Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO), fall short of addressing the issue. We propose Debiasing-DPO, which combines contrastive reasoning-augmented DPO with SFT on expert labels to reduce the effect of spurious context while avoiding mode collapse. Applied to Llama and Qwen Instruct models of 3-8B parameters, Debiasing-DPO reduces bias by 84% and improves predictive accuracy by 52% on average across models. Our findings from the educational dataset highlight that stronger models may exhibit greater sensitivity despite higher accuracy, and Debiasing-DPO can improve both accuracy and robustness in prompt-based prediction tasks.

arXiv

TTSR: Test-Time Self-Evolving via Reflection

Haoyang He, Zihua Rong, Yunjia Zhao, LAN YANG, Jian Chang, Honggang Zhang

Test-time training (TTT) adapts large language models (LLMs) during inference using only unlabeled test inputs. Existing methods, however, face two major bottlenecks on hard reasoning tasks: (1) \emph{lack of learnable samples}, as self-generated pseudo-labels on difficult questions are often noisy and yield unstable rewards; and (2) \emph{inefficient exploration}, as performance gains depend on repeatedly sampling many rollouts without explicit diagnosis of why previous attempts fail. We propose \textbf{TTSR} (\textbf{T}est-\textbf{T}ime \textbf{S}elf-\textbf{R}eflection), a self-evolving framework based on a \emph{reflect-then-synthesize} paradigm. A single pretrained model alternates between a \textit{Student} role and a \textit{Teacher} role: the Student solves test questions and updates, while the Teacher analyzes failed trajectories and synthesizes targeted variant questions closer to the Student's capability frontier. TTSR further maintains a cross-iteration \textit{weakness memory} and compiles persistent weaknesses into a lightweight \textit{strategy note} prepended to subsequent Student inputs, so diagnostic knowledge can guide exploration and gradually fade as weaknesses are resolved. Experiments on challenging mathematical reasoning benchmarks show consistent test-time improvements, strong cross-backbone generalization, and transfer to general-domain reasoning tasks.

arXiv

Tool Verification for Test-Time Reinforcement Learning

Ruotong Liao, Nikolai Röhrich, Xiaohan Wang, Yuhui Zhang, Yasaman Samadzadeh, Volker Tresp, Serena Yeung-Levy

Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for Recursive Self-Improving AI (RSI) by adapting Large Reasoning Models (LRMs) on unlabeled test inputs, using self-consensus rewards derived from majority voting over sampled rollouts. However, majority voting can mistake popularity for correctness: a spurious yet high-frequency unverified consensus may become a biased reward signal, causing test-time RL to reinforce frequent but wrong answers and collapse into an incorrect mode. We address this false-popular failure mode with T$^3$RL (Tool-Verification for Test-Time Reinforcement Learning), a verification-aware test-time RL framework. T$^3$RL grounds pseudo-label construction in external tool evidence. Concretely, a verifier utilizes external tool evidence (e.g., from code execution) to upweight verified rollouts during a verification-aware voting, producing more reliable pseudo-labels for training. Across various math difficulties (MATH-500, AMC, and AIME 2024) and diverse backbone families, T$^3$RL significantly improves over TTRL, with better performance on harder problems. T$^3$RL is positioned as a verified online data synthesizer, highlighting the role of tool verification in reliable online adaptation. T$^3$RL is extensible to verifiable domains and provides training and inference efficiency.

arXiv

Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation

Yinzhu Chen, Abdine Maiga, Hossein A. Rahmani, Emine Yilmaz

Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical errors are often missed by generic metrics and LLM judges using general criteria, while expert-authored fine-grained rubrics are expensive and difficult to scale. In this paper, we propose a retrieval-augmented multi-agent framework for automatically generating instance-specific evaluation rubrics. Our approach grounds evaluation in authoritative medical evidence by decomposing retrieved content into atomic facts and synthesizing them with user interaction constraints to form fine-grained evaluation criteria. Evaluated on HealthBench and LLMEval-Med, our framework achieves Clinical Intent Alignment (CIA) scores of 50.20% and 31.90%, significantly outperforming the GPT-4o baseline and showing consistent improvements across English and Chinese medical benchmarks. In discriminative tests on HealthBench, our rubrics achieve a 7.8% point higher win rate than GPT-4o and increase the mean score difference from 4.972 to 8.658. Ablation studies further show that individual components contribute differently across datasets, with interaction-intent modeling providing the most consistent contribution to clinical-criterion coverage. Beyond evaluation, our rubrics guide response refinement, improving response quality by 9.2%. These results suggest that automated, knowledge-grounded rubric generation provides a scalable foundation for evaluating and improving medical LLMs. The code is available at https://anonymous.4open.science/r/Automated-Rubric-Generation-E716/.

arXiv

Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent

Mingyue Cheng, Daoyu Wang, Qi Liu, Shuo Yu, Xiaoyu Tao, Yuqian Wang, Chengzhong Chu, Yu Duan, Mingkang Long, Enhong Chen

Synthesizing informative commercial reports from massive and noisy web sources is critical for high-stakes business decisions. Although recent deep research agents (DRAs) achieve notable progress, their reports remain limited in quality, reliability, and coverage. These mainly stem from ambiguous intents that cause search drift, retrieved web content that rapidly saturates the context window, and single-pass synthesis that limits report comprehensiveness. In this work, we propose Mind2Report, a cognitive deep research agent that emulates commercial analysts to synthesize expert-level reports. Mind2Report first probes fine-grained commercial intent to establish a structured outline, then recursively explores web sources and distills validated evidence into research memory to preserve context efficiency. Meanwhile, the research memory and outline continuously co-evolve, refining the report structure to avoid rigid initial planning. Finally, Mind2Report iteratively synthesizes the report based on the evolving outline and accumulated evidence. Together, these designs enable reliable and context-efficient long-horizon commercial deep research. To rigorously evaluate commercial DRAs, we further construct QRC-Eval, comprising 200 real-world commercial tasks and a holistic evaluation framework covering report quality, reliability, and coverage. Extensive experiments demonstrate that Mind2Report consistently outperforms leading proprietary and open-source DRAs, while ablations verify the effectiveness of each module and further analyze the challenges they address. We expect this work to advance the development of commercial deep research agents.

arXiv

From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset

Haneul Yoo, Won Ik Cho, Geunhye Kim, Jiyoon Han

Large language models (LLMs) achieve strong performance on many tasks, but their progress remains uneven across languages and cultures, often reflecting values latent in English-centric training data. To enable practical cultural alignment, we propose a scalable approach that leverages national social studies curricula as a foundation for culture-aware supervision. We introduce CuCu, an automated multi-agent LLM framework that transforms national textbook curricula into open-ended, culture-specific question-answer pairs for supervised fine-tuning (SFT). Applying CuCu to the Korean national social studies curriculum, we construct KCaQA, comprising 34.1k open-ended QA pairs. Our analyses and training experiments suggest that KCaQA covers culture-specific topics and produces responses grounded in local sociocultural contexts.

arXiv

Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization

Yao Dou, Benjamin Mamut, Wei Xu

Large language models (LLMs) now support contexts of up to 1M tokens, but their strengths and weaknesses on complex long-context tasks remain unclear. To study this, we focus on multi-document legal case summarization, where a single case often spans many documents exceeding 100K tokens. We systematically evaluate 12 frontier LLMs with Gavel, which consists of Gavel-Ref, a reference-based evaluation framework with checklist, residual-fact, and writing-style evaluations, and Gavel-Agent, a reference-free agent for evaluating factual coverage directly from source documents. Our results show that current models are more prone to omitting key information than hallucinating. They all perform well on simple checklist items, such as filing date, but struggle with rare and complex items, such as settlements. Performance also declines as case length increases. To meta-evaluate Gavel, we collect 160 hours of human annotations. Gavel-Agent reduces token usage by at least 36% compared to end-to-end and chunk-by-chunk methods while achieving competitive performance. Gavel-Agent also generalizes to the medical domain, performing the best with at least 77% fewer tokens.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →