Tag: Multi-Agent

All the articles with the tag "Multi-Agent".

• Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute

  Published: 10 May, 2025 |  at  10:59 AM

  

  86.42 🤔

  This paper introduces ModelSwitch, a multi-LLM repeated sampling strategy that leverages answer consistency to dynamically switch models, achieving superior performance and 34% sample efficiency over single-LLM self-consistency across diverse datasets.

• Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games

  Published: 24 May, 2025 |  at  11:11 AM

  

  86.31 🤔

  本文提出Divide-Fuse-Conquer框架，通过分组训练、参数融合和持续优化提升大型语言模型在多场景游戏中的泛化能力，实验在TextArena的18个游戏中显示Qwen2.5-32B-Align性能接近Claude3.5，但复杂场景表现仍有限。

• Long Term Memory: The Foundation of AI Self-Evolution

  Published: 17 May, 2025 |  at  11:08 AM

  

  85.57 🤔

  This paper proposes Long-Term Memory (LTM) as a cornerstone for AI self-evolution, demonstrating through multi-agent frameworks like OMNE and diverse experiments that LTM enables personalized, adaptive learning in LLMs during inference, achieving top performance on benchmarks like GAIA.

• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning

  Published: 1 Jun, 2025 |  at  11:53 AM

  

  85.15 🤔

  ReMA通过多智能体强化学习分离元思考和推理过程，提升了大型语言模型在数学推理和LLM-as-a-Judge任务上的性能，尤其在分布外泛化能力上表现出色，但对超参数敏感且多轮设置存在稳定性挑战。

• LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models

  Published: 7 May, 2025 |  at  09:34 AM

  

  85.07 🤔

  本文通过LLM-Coordination基准测试框架，评估大型语言模型在纯协调游戏中的多智能体协调能力，发现其在环境依赖任务中表现优异但在心智理论推理和联合规划中存在显著不足，同时展现出对未见伙伴的零样本适应性。