Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experiments, where we propose a novel group discussion framework to enrich the set of discussion mechanisms. Interestingly, our results show that a single-agent LLM with strong prompts can achieve almost the same performance as the best existing discussion approach on a wide range of reasoning tasks and backbone LLMs. We observe that the multi-agent discussion performs better than a single agent only when there is no demonstration in the prompt. Further study reveals the common interaction mechanisms of LLMs during the discussion.
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China(中国人民大学人工智能学院);Beijing Key Laboratory of Research on Large Models(北京大型模型研究关键实验室);Engineering Research Center of Next-Generation Intelligent Search(下一代智能搜索工程研究中心);College of Artificial Intelligence, Tianjin University of Science(天津科技大学人工智能学院)
Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models
State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室);University of Science and Technology of China(中国科学技术大学);The Hong Kong University of Science and Technology(香港科技大学)
Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors
School of Intelligence Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University(智能科学与技术学院,新型软件技术国家重点实验室,南京大学);School of Computing and Information Systems, Singapore Management University(计算与信息系统学院,新加坡管理大学);Central South University(中南大学);School of Global Education and Development, International Chinese Language Education, University of Chinese Academy of Social Sciences(全球教育与发展学院,国际中文教育,中国社会科学院)
Reason to Rote: Rethinking Memorization in Reasoning
Department of ICS, Utrecht University(信息科学与计算系,乌特勒支大学);MaiNLP, Center for Information and Language Processing, LMU Munich(MaiNLP,信息与语言处理中心,慕尼黑大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Saarland Informatics Campus, Saarland University(萨尔兰州信息科学校区,萨尔兰州大学)
Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China(哈尔滨工业大学深圳研究院);Huawei Large Model Data Technology Lab(华为大模型数据技术实验室);Huawei Multimodal Model Lab(华为多模态模型实验室);Department of Statistics and Data Science, Tsinghua University, Beijing, China(清华大学统计与数据科学系)
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院);Kling Team, Kuaishou Technology(快手科技 Kling 团队);Peking University(北京大学);HKUST(香港科技大学);CASIA(中国科学院自动化研究所);Nanjing University(南京大学);Renmin University of China(中国人民大学);Tsinghua University(清华大学)
本文提出LatentOmni框架,通过统一的音频-视觉潜在空间进行多模态推理,利用特征级监督和Omni-Sync Position Embedding保持时间一致性,从而在多个音频-视觉推理基准测试中取得最佳性能。
The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?
The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));National University of Singapore(新加坡国立大学)
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
Zhejiang University(浙江大学);School of Engineering, Westlake University(西湖大学工程学院);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖先进研究院技术研究所);Huawei Noah’s Ark Lab(华为诺亚实验室)
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
TMLR Group, Hong Kong Baptist University(香港 Baptist 大学 TMLR 实验组);The University of Texas at Austin(德克萨斯大学奥斯汀分校);Shanghai Jiao Tong University(上海交通大学);Sydney AI Center, The University of Sydney(悉尼大学悉尼人工智能中心)
Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning
The Hong Kong Polytechnic University(香港理工大学);Meituan(美团);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Xi’an Jiaotong University(西安交通大学);East China Normal University(华东师范大学);Northeastern University(东北大学)
Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);Mila - Quebec AI Institute(Mila - 魁北克人工智能研究所);University of Waterloo(滑铁卢大学);The Chinese University of Hong Kong(香港中文大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室)
Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective
University of Science and Technology of China(中国科学技术大学);The University of Melbourne(墨尔本大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合国家科学中心人工智能研究院)