共进化LLM决策与技能库代理以应对长周期任务
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
AI总结：
本文提出COSPLAY框架，通过LLM决策代理与技能库代理的共进化，提升长周期任务中的技能检索与决策能力，实验显示在六个游戏环境中，COSPLAY在单人游戏基准上平均奖励提升超过25.1%。
摘要：
长周期交互环境是评估代理技能使用能力的测试场。这些环境要求多步骤推理、多个技能在多个时间步的链式使用，以及在延迟奖励和部分可观察性下做出稳健决策。游戏是评估代理技能使用能力的良好测试场。大型语言模型（LLM）提供了一个有前景的替代方案作为游戏扮演代理，但它们在一致的长周期决策上常常遇到困难，因为它们缺乏发现、保留和重用跨回合结构化技能的机制。我们提出了COSPLAY，一个共进化框架，其中LLM决策代理从可学习的技能库中检索技能以指导行动，而由代理管理的技能管道从代理的未标记回放中发现可重用的技能以形成技能库。我们的框架提高了决策代理学习更好技能检索和行动生成的能力，同时技能库代理持续地提取、精炼和更新技能及其合同。在六个游戏环境中的实验表明，COSPLAY在8B基础模型下在单人游戏基准上相对于四个前沿LLM基线平均奖励提升超过25.1%，同时在多人社交推理游戏中保持竞争力。
英文摘要：
Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills over many timesteps, and robust decision making under delayed rewards and partial observability. Games are a good testbed for evaluating agent skill usage in environments. Large Language Models (LLMs) offer a promising alternative as game playing agents, but they often struggle with consistent long horizon decision making because they lack a mechanism to discover, retain, and reuse structured skills across episodes. We present COSPLAY, a co evolution framework in which an LLM decision agent retrieves skills from a learnable skill bank to guide action taking, while an agent managed skill pipeline discovers reusable skills from the agents unlabeled rollouts to form a skill bank. Our framework improves both the decision agent to learn better skill retrieval and action generation, while the skill bank agent continually extracts, refines, and updates skills together with their contracts. Experiments across six game environments show that COSPLAY with an 8B base model achieves over 25.1 percent average reward improvement against four frontier LLM baselines on single player game benchmarks while remaining competitive on multi player social reasoning games.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
