论文检索

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen 等

Recent progress in Large Language Model (LLM) based Table Question Answering (TableQA) has demonstrated strong performance on standard benchmarks. However, existing benchmarks mainly focus on well-structured tables and fail to reflect the irregular structures and complex reasoning commonly encountered in real-world scenarios. We propose CompTab, a benchmark designed to evaluate TableQA under complex reasoning and irregular table conditions. CompTab covers six representative types, including semantic ambiguity, multi-hop reasoning, transposed tables, merged cells, missing values, and outliers. It is constructed from real-world seed tables across multiple domains using controlled LLM based generation and human verification to ensure realism and diversity. In addition, to improve the generalization of LLMs under complex and irregular table settings, we propose a two-stage training framework that progressively aligns models with textual reasoning and executable decision signals, instantiated as CompTabLLM. Evaluations on 38 representative LLMs and CompTabLLM show clear limitations of existing LLMs under realistic conditions, while the proposed framework improves generalization. CompTab thus provides a challenging benchmark for advancing TableQA in real-world.

Xiang Wang, Zongtao Yang, Zhuojian Hong, Shuhao Zhang, Wei Wei

Agentic workflows are commonly used to guide large language models in solving complex reasoning tasks. However, existing automated workflow generation methods primarily rely on stepwise local refinement or tree-based search over a single evolving workflow. Under limited optimization budgets, this paradigm constrains structural depth, hindering the discovery of workflows that require deep compositional structure. To address this limitation, we propose FusionFlow, a framework centered on workflow fusion. Unlike incremental refinement, fusion enables structural leaps by synthesizing multiple independently evolved workflows, allowing exploration of deeper regions of the workflow space within a finite budget. To make fusion effective, FusionFlow integrates local optimization, task-specific differentiation, and a dynamic scheduling mechanism. Experiments on six reasoning benchmarks demonstrate that FusionFlow consistently outperforms existing automated workflow generation methods. Further ablation and analysis confirm that fusion is the key driver of deep structural exploration, highlighting fusion-driven exploration as an effective approach for overcoming depth limitations in automated workflow generation.

Yelin Chen, Fanjin Zhang, Suping Sun, Yunhe Pang, Yuanchun Wang, Jian Song, XiaoYan Li, Lei Hou, Shu Zhao, Jie Tang 等

Understanding research papers remains challenging for foundation models due to specialized scientific discourse and complex figures and tables, yet existing benchmarks offer limited fine-grained evaluation at scale. To address this gap, we introduce RPC-Bench, a large-scale question-answering benchmark built from review–rebuttal exchanges of high-quality computer science papers, containing 15K human-verified QA pairs. We design a fine-grained taxonomy aligned with the scientific research flow to assess models’ ability to understand and answer why, what, and how questions in scholarly contexts. We also define an elaborate LLM–human interaction annotation framework to support large-scale labeling and quality control. Following the LLM-as-a-Judge paradigm, we develop a scalable framework that evaluates models on correctness-completeness and conciseness, with high agreement to human judgment. Experiments reveal that even the strongest models (GPT-5) achieve only 68.2% correctness-completeness, dropping to 37.46% after conciseness adjustment, highlighting substantial gaps in precise academic paper understanding.

Tao Feng, Xinke Jiang, Xinyan Hu, Yonggang Zhang, Zhen Tao, Wentao Zhang, Boyang Liu, Wenhao Jiang, Chao Wu

Agentic search augments large language models (LLMs) with external knowledge through reinforcement learning. However, existing approaches suffer from blind reliance on noisy retrieval and hallucination when both parametric and external knowledge fail—reflecting a lack of calibration regarding the model’s knowledge boundary. We propose Knowledge boundary Policy Optimization (KbPO), a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states. KbPO introduces: (1) a semantic stability metric to delineate reliable parametric knowledge; (2) a four-quadrant taxonomy synthesising internal certainty with retrieval quality; and (3) a quadrant-based reward mechanism incentivising calibrated behaviour. We further adopt an iterative query evolution pipeline to construct boundary-probing training samples. Experiments on ten benchmarks demonstrate that KbPO outperforms strong baselines while exhibiting reduced hallucination rates.

Aafiya Shamshad Hussain, Gaurav Srivastava, Alvi Md Ishmam, Zaber Ibn Abdul Hakim, Chris Thomas

Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulation remains poorly understood. We study a realistic and underexplored threat model: **untargeted, audio-only adversarial attacks** on trimodal audio–video–language models. We analyze six complementary attack objectives that target different stages of multimodal processing, including audio encoder representations, cross-modal attention, hidden states, and output likelihoods. Across four state-of-the-art models and multiple benchmarks, we show that audio-only perturbations can induce severe multimodal failures, achieving up to **96% attack success rate.** We further show that attacks can be successful at low perceptual distortions (LPIPS \leq 0.08, SI-SNR \geq 0 dB) and benefit more from extended optimization than increased data scale. We evaluate the feasibility of these attacks under physically realistic conditions by incorporating room impulse response (RIR) modeling, showing that audio-only perturbations remain effective under environmental transformations and thus highlight the practical risk of single-modality attacks in real-world multimodal systems. Transferability across models and encoders remains limited, while speech recognition systems such as Whisper primarily respond to perturbation magnitude, achieving **>97% attack success** under severe distortion. These results expose a previously overlooked single-modality attack surface in multimodal systems and motivate defenses that enforce cross-modal consistency. Our project website is available at https://aafiya-h.github.io/soundbreak/.

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim

Automated simulator construction requires distributional fidelity, distinguishing it from generic code generation. We identify two failure modes in long-horizon LLM agents: contextual drift and optimization instability arising from conflating structural and parametric errors. We propose SOCIA-EVO, a dual-anchored evolutionary framework. SOCIA-EVO introduces: (1) a static blueprint to enforce empirical constraints; (2) a bi-level optimization to decouple structural refinement from parameter calibration; and (3) a self-curating Strategy Playbook that manages remedial hypotheses via Bayesian-weighted retrieval. By falsifying ineffective strategies through execution feedback, SOCIA-EVO achieves robust convergence, generating simulators that are statistically consistent with observational data. SOCIA-EVO’s code and data are available here: https://github.com/cruiseresearchgroup/SOCIA/tree/evo.

Aoyuan Jiang, Liang Hong, Haoxuan Liu, Rui Wang

Financial numerical reasoning demands rigorous adherence to domain-specific logic and precise evidence foundation. However, large language models (LLMs) are prone to forced generation when confronting ambiguous evidence or complex recursive dependencies, often hallucinating values to bridge information gaps. To address this, we propose graph-bounded financial reasoning (GBFR), a neuro-symbolic framework that imposes semantic and structural constraints via a financial metric knowledge graph (FMKG). Unlike sequential generation paradigms, our approach employs a parallel graph-constrained reasoning algorithm that orchestrates specialized operators to simultaneously explore heterogeneous derivation paths of complex financial metrics. Through cross-path verification, the framework aggregates only semantically consistent results, ensuring reasoning is bounded by available context. Crucially, this approach enables safe abstention by distinguishing genuine data absence from retrieval failure, thereby preventing ungrounded fabrication. To evaluate this capability, we further construct counterfactual samples by perturbing entities, times, and metrics to synthesize unanswerable scenarios. Empirical evaluations on standard benchmarks demonstrate that GBFR significantly outperforms state-of-the-art baselines.

Zhiheng Zhang, Yuanzhe Zhang, Bohan Yu, Daojian Zeng, Kang Liu, Jun Zhao

LLM-based Multi-agent systems (MAS) have shown strong capabilities across a wide range of domains. Their success largely hinges on the collaboration topology design, which has emerged as a central research focus in the automated MAS design.However, existing approaches are fundamentally constrained by their reliance on homogeneous LLMs, which significantly limits overall system intelligence.In response to this limitation, we for the first time propose the concept of **Automated Design of Heterogeneous-LLMs-based MAS (ADHM)**.ADHM sheds light on a promising avenue for advancing collective intelligence, which focuses on the automated design of cost-effective MAS composed of diverse LLMsand roles to suit various queries.Toward this challenging goal, we propose **Hetero-Designer**, a novel pipeline that efficiently encodes intricate dependencies among queries, LLMs and roles through a novel Binary-Star Transformer and constructs Hetero-MAS in an autoregressive graph generation process. Extensive experiments demonstrate that **Hetero-Designer** is: (1) high-performing on various benchmarks, (2) economical in reducing overhead, (3) extensible to unseen LLMs and roles.

Minping Chen, Bowen Xiao, Du Liang, Chuxuan Zeng, Zeyi Wen

Hyperparameters are critical to LLM reinforcement learning (RL), but existing hyperparameter optimization (HPO) methods remain inefficient in this area, due to the massive model scale and resource-intensive training cycles. In this paper, we propose Joint Fidelity Hyperparameter Optimization (JF-HPO), which simultaneously adapts both model size and training budget as fidelity. JF-HPO is empowered by: (i) a small proxy model of the target LLM for efficient training and evaluation in each HPO trial; (ii) several carefully designed early-stopping strategies based on training dynamics; (iii) an efficient checkpointing mechanism to eliminate redundant computations. JF-HPO significantly improves the computational efficiency of each trial (up to 14.9\times) compared with existing HPO methods, thus achieving better predictive accuracy in most cases under the same time budget. Notably, JF-HPO delivers performance improvements ranging from 5.8% to 111.6% over VeRL Recipe.

Jiasen Gao, Xiaoliang Chen, Duoqian Miao, Xu Gu, Xianyong Li, Yajun Du

Spurious correlations cause deep learning models to rely on predictive shortcuts that hold in the training data but break under distribution shifts, leading to large performance drops for minority groups. Existing strategies often rely on costly group annotations or employ unstable adversarial training. In this paper, we propose Prototype-guided debiasing using Robust Invariant Feature Transformations (PRIFT), a novel framework that mitigates spurious correlations by manipulating latent space geometry. Specifically, we introduce a prototype-guided modeling approach that leverages natural language prompts to represent confounders, transforming abstract biases into interpretable geometric anchors without auxiliary classifiers. Based on these anchors, we introduce a centered projection operator that adaptively purifies representations by removing confounding deviations specific to instances while preserving essential semantic structure. Furthermore, PRIFT can handle confounding factor information at different levels, ranging from true labels to unsupervised latent inference. Experiments on four text classification benchmarks demonstrate the superiority of our method; notably, PRIFT outperforms state-of-the-art baselines and improves worst-group accuracy by over 20% on the CivilComments dataset compared to standard empirical risk minimization.

Wangtao Sun, Haotian Xu, Huanxuan Liao, Xuanqing Yu, Zhongtao Jiang, Shizhu He, Jun Zhao, Kang Liu

This paper notices that while symbolic instruction and neural parameters play different roles on steering LLMs’ behavior, both instructions and parameters are the compression of task data, they are supposed be strongly correlated and can be learned to predict one from the other. Therefore, This paper proposes a novel neural network framework, SHIP (Shuttle between the Instructions and the Parameters), to model and learn the bi-directional mappings between the instructions and the parameters of LLMs. We verify that SHIP can effectively map one of the instructions/parameters to the other by evaluating it on the tasks of instruction deduction and induction. The results show that SHIP performs better than existing baseline methods in terms of deductive capabilities while significantly surpassing them in inductive capabilities. Moreover, SHIP can effectively combine the two mapping processes to perform excellent inductive reasoning. We further discuss how the latent fusing methods and latent dimensions affect SHIP’s performance, and show SHIP can effectively generalize with pre-training. The code and data for this paper are released at https://anonymous.4open.science/r/Shuttle-Between-Instructions-Parameters

Victor Morand, Nadi Tomeh, Josiane Mothe, Benjamin Piwowarski

Identifying which text spans refer to entities - mention detection- is both foundational for information extraction and a known performance bottleneck. We introduce ToMMeR, a lightweight model (<300K parameters) probing mention detection capabilities from early LLM layers. Across 13 NER benchmarks, ToMMeR achieves 93% recall zero-shot, with an estimated 90% precision under a human-calibrated LLM-judge protocol, showing that ToMMeR rarely produces spurious predictions despite high recall. Cross-model analysis reveals that diverse architectures (14M-15B parameters) converge on similar mention boundaries (DICE >75%), confirming that mention detection emerges naturally from language modeling. When extended with span classification heads, ToMMeR achieves competitive NER performance (80-87% F1 on standard benchmarks). Our work provides evidence that structured entity representations exist in early transformer layers and can be efficiently recovered with minimal parameters.

Seonjeong Hwang, Jun Seo, Hyounghun Kim, Gary Lee

Recent studies in difficulty-controlled reading comprehension item generation have leveraged large language models (LLMs) to produce items by adjusting difficulty-related features. However, existing methods typically rely on a single-agent prompting approach, which often fails to consistently satisfy specified feature constraints, resulting in items that deviate from the target difficulty level. To address this limitation, we introduce MAFIG, a Multi-agent Framework for Feature-constrained Item Generation, where multiple LLM agents and feature-specific evaluators collaborate to generate and iteratively revise items based on intended constraints. Furthermore, to verify the efficacy of MAFIG in difficulty control, we propose a method for constructing a sequence of feature constraint sets that yield items with monotonically increasing difficulty. Experimental results demonstrate that MAFIG generates items that adhere to target constraints at a significantly higher rate than baselines, achieving robust difficulty control through the difficulty-calibrated constraint sequence.

Han Zhang, Zihan Gu, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu, Xinyan Zhang, Yuhao Wei, Cheng Hua

While Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. To address this issue, we introduce Neo-Classic, an evaluation benchmark that combines a constructionist Out-of-Sample (OOS) dataset with a suite of reverse understanding probes. Unlike traditional benchmarks that rely on verification or generation over historical corpora, Neo-Classic comprises strictly metrical poetry authored by contemporary experts, reducing the possibility of direct retrieval. We evaluate state-of-the-art models, including Qwen3-Max, Gemini-3-Pro, and DeepSeek-V3.2, across five behavioral probes designed to test hierarchical constraint satisfaction. Our results reveal two primary limitations. First, a performance gap of 20%–50% emerges when models transition from historical to contemporary texts. Second, models exhibit substantial difficulties in discourse-level ordering tasks, with standard accuracy remaining low (0–13%). Although expert-level guidance improves the performance of reasoning-enhanced models to 36%, a notable gap with human experts persists. These findings suggest that while current LLMs capture local formal patterns, they struggle with global hierarchical planning required for robust Linguistic-Aesthetic Reasoning.

Ao Sun, Xiaoyu Wang, Zhe Tan, Yu Li, Jiachen Zhu, Yuheng Jia, Shu Su

As Large Language Models (LLMs) serve a global audience, alignment must transition from enforcing universal consensus to respecting cultural pluralism. We demonstrate that dense models, when forced to fit conflicting value distributions, suffer from Mean Collapse, converging to a generic average that fails to represent diverse groups. We attribute this to Cultural Sparsity, where gradient interference prevents dense parameters from spanning distinct cultural modes. To resolve this, we propose CuMA (Cultural Mixture of Adapters), a framework that frames alignment as a conditional capacity separation problem. By incorporating demographic-aware routing, CuMA internalizes a Latent Cultural Topology to explicitly disentangle conflicting gradients into specialized expert subspaces. Extensive evaluations on WorldValuesBench, Community Alignment, and PRISM demonstrate that CuMA achieves competitive performance, outperforming both dense baselines and semantic-only MoEs. Our analysis confirms that CuMA effectively mitigates mean collapse and preserves cultural diversity. Our code is available at https://github.com/Throll/CuMA.

Hongcheng Liu, Pingjie Wang, Yuhao Wang, Siqu Ou, Yanfeng Wang, Yu Wang

Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where models perform step-by-step reasoning under complete information. This setup is misaligned with real-world use, where seeing is not enough. This raises a fundamental question: Can MLLMs actively acquire missing evidence under incomplete information? To bridge this gap, we require the MLLMs to actively acquire missing evidence and iteratively refine decisions under incomplete information, by selecting a target image from a candidate pool without task-specific priors. To support systematic study, we propose GuessBench, a benchmark with both perception-oriented and knowledge-oriented images for evaluating active reasoning in MLLMs. We evaluate 20 superior MLLMs and find that performance on active reasoning lags far behind it on passive settings, indicating substantial room for improvement. Further analysis identifies fine-grained perception and timely decision-making as key challenges. Ablation studies show that perceptual enhancements benefit smaller models, whereas thinking-oriented methods provide consistent gains across model sizes. These results suggest promising directions for future research on multimodal active reasoning.

Dexuan Xu, Yuan Jiayin, Jianing Wang, Yanyuan Chen, Hanpin Wang, Yu Huang

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in interpreting single medical images. However, real-world clinical diagnosis is intrinsically a multi-view process, requiring the synthesis of information across volumetric slices, temporal sequences, and comparative modalities. Existing benchmarks fail to capture this complexity, limiting the assessment of models in realistic clinical workflows. To bridge this gap, we introduce MedMultiBench, the first large-scale benchmark specifically designed for medical multi-image understanding. Comprising 11,392 expert-curated samples, MedMultiBench evaluates MLLMs across four distinct dimensions: Joint Reasoning, Comparative Analysis, Comprehensive Perception, and In-Context Learning. We benchmark 13 state-of-the-art MLLMs, revealing that while current models excel in single-view tasks, they struggle significantly with multi-image contexts. Our experiments identify a performance degradation in open-source models when processing increased visual loads, whereas closed-source models demonstrate better scalability. MedMultiBench provides a robust framework to facilitate the development of MLLMs capable of holistic clinical reasoning.

Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang, Xin Zhang, Wenshan Wu, Qihao Zhao, Hao Li, Yuanyuan Gao, Kim-Hui Yap 等

Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. While data selection has been widely studied, the strategic data organization for enhanced training remains an underexplored area, particularly since current LLMs are often trained for only one or a few epochs. This paper systematically explores the influence of data organization on LLM training by reusing pre-computed sample-level scores originally generated for data efficiency, thereby incurring minimal additional computational overhead. We identify and formalize four key guidances for optimizing data organization: Boundary Sharpening, Cyclic Scheduling, Curriculum Continuity, and Local Diversity. Guided by them, we introduce two novel data ordering methods termed STR and SAW. Extensive experiments across different model scales and data sizes, encompassing both pre-training and SFT stages, validate the effectiveness of our summarized guidances. They also demonstrate the robustness of our proposed data ordering methods in enhancing the stability and performance of LLM training.

Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou, Jiajun Guo

Creativity has become a core competence in the era of LLMs and human–AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics.

Jiahe Guo, Xiangran Guo, Yulin Hu, Zimo Long, Xingyu Sui, Xuda Zhi, Yongbo Huang, Hao He, Weixiang Zhao, Yanyan Zhao 等

Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions.However, most work on personalized agents prioritizes utility and user experience, treating memory as a neutral component and largely overlooking its safety implications.In this paper, we reveal intent legitimation, a previously underexplored safety failure in personalized agents, where benign personal memories bias intent inference and cause models to legitimize inherently harmful queries.To study this phenomenon, we introduce PS-Bench, a benchmark designed to identify and quantify intent legitimation in personalized interactions.Across multiple memory-augmented agent frameworks and base LLMs, personalization increases attack success rates by **15.8%–243.7%** relative to stateless baselines.We further provide mechanistic evidence for intent legitimation from internal representation space, and propose a lightweight detection–reflection method that effectively reduces safety degradation.Overall, our work provides the first systematic exploration and evaluation of intent legitimation as a safety failure mode that naturally arises from benign, real-world personalization, highlighting the importance of assessing safety under long-term personal context. **WARNING:** This paper may contain harmful content.