English
Related papers

Related papers: MAVEN: Multi-Agent Verification-Elaboration Networ…

200 papers

We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four…

Artificial Intelligence · Computer Science 2026-04-23 Jan-Philipp Schmidt

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning…

Computation and Language · Computer Science 2026-05-20 Leyao Wang , Yanan He , Peng Chen , Asaf Yehudai , Yixin Liu , Rex Ying , Michal Shmueli-Scheuer , Arman Cohan

Making inferences in text comprehension to understand the meaning is essential in language processing. This work studies the entailment verification (EV) problem of multi-sentence premises that requires a system to make multiple inferences…

Computation and Language · Computer Science 2024-05-29 Soumya Sanyal , Tianyi Xiao , Jiacheng Liu , Wenya Wang , Xiang Ren

The reasoning capabilities of LLM (Large Language Model) are widely acknowledged in recent research, inspiring studies on tool learning and autonomous agents. LLM serves as the "brain" of the agent, orchestrating multiple tools for…

Machine Learning · Computer Science 2024-03-26 Xiangyan Liu , Rongxue Li , Wei Ji , Tao Lin

Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to automatically generate testbenches and reduce verification overhead. However, LLMs have…

Hardware Architecture · Computer Science 2026-05-01 Chang-Chih Meng , Yu-Ren Lu , Guan-Yu Lin , Tsung Tai Yeh , Kai-Chiang Wu , I-Chen Wu

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Rheeya Uppaal , Phu Mon Htut , Min Bai , Nikolaos Pappas , Zheng Qi , Sandesh Swamy

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling…

Multiagent Systems · Computer Science 2025-11-12 Haolun Wu , Zhenkun Li , Lingyao Li

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We…

Computation and Language · Computer Science 2026-04-21 Tunazzina Islam

Advertisement (Ad) video violation detection is critical for ensuring platform compliance, but existing methods struggle with precise temporal grounding, noisy annotations, and limited generalization. We propose RAVEN, a novel framework…

Computation and Language · Computer Science 2025-10-21 Deyi Ji , Yuekui Yang , Haiyang Wu , Shaoping Ma , Tianrun Chen , Lanyun Zhu

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…

Multiagent Systems · Computer Science 2026-04-01 Wonduk Seo , Juhyeon Lee , Junseo Koh , Wonseok Choi , Hyunjin An , Jian Park , Seunghyun lee , Haihua Chen , Yi Bu

Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contamination. Consequently, developing a reliable benchmark that…

Computation and Language · Computer Science 2025-08-14 Zijin Hong , Hao Wu , Su Dong , Junnan Dong , Yilin Xiao , Yujing Zhang , Zhu Wang , Feiran Huang , Linyi Li , Hongxia Yang , Xiao Huang

Vision-and-Language Navigation (VLN) requires an embodied agent to navigate in a complex 3D environment according to natural language instructions. Recent progress in large language models (LLMs) has enabled language-driven navigation with…

Robotics · Computer Science 2026-01-27 Zijun Li , Shijie Li , Zhenxi Zhang , Bin Li , Shoujun Zhou

Informal mathematics has been central to modern large language model (LLM) reasoning, offering flexibility and enabling efficient construction of arguments. However, purely informal reasoning is prone to logical gaps and subtle errors that…

Artificial Intelligence · Computer Science 2025-11-25 Azim Ospanov , Zijin Feng , Jiacheng Sun , Haoli Bai , Xin Shen , Farzan Farnia

Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. These models not only excel in traditional vision-language tasks but also demonstrate impressive performance in contemporary…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Xiaotian Han , Quanzeng You , Yongfei Liu , Wentao Chen , Huangjie Zheng , Khalil Mrini , Xudong Lin , Yiqi Wang , Bohan Zhai , Jianbo Yuan , Heng Wang , Hongxia Yang

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…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Yuchi Wang , Haiyang Yu , Weikang Bian , Jiefeng Long , Xiao Liang , Chao Feng , Hongsheng Li

We introduce I-RAVEN-X, a symbolic benchmark designed to evaluate generalization and robustness in analogical and mathematical reasoning for Large Language Models (LLMs) and Large Reasoning Models (LRMs). I-RAVEN-X extends I-RAVEN by…

Machine Learning · Computer Science 2025-11-03 Giacomo Camposampiero , Michael Hersche , Roger Wattenhofer , Abu Sebastian , Abbas Rahimi

Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and…

Computation and Language · Computer Science 2024-07-12 Haotian Wang , Xiyuan Du , Weijiang Yu , Qianglong Chen , Kun Zhu , Zheng Chu , Lian Yan , Yi Guan

Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jing Jin , Hao Liu , Yan Bai , Yihang Lou , Zhenke Wang , Tianrun Yuan , Juntong Chen , Yongkang Zhu , Fanhu Zeng , Xuanyu Zhu , Tao Feng , Yige Xu

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a wide range of vision-language tasks. However, their performance as embodied agents, which requires multi-round dialogue spatial reasoning and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Xunyi Zhao , Gengze Zhou , Qi Wu

As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison…

Artificial Intelligence · Computer Science 2026-05-12 Pratik Jayarao , Himanshu Gupta , Neeraj Varshney , Chaitanya Dwivedi