研究人员推出ACCORD，一个旨在通过使语言代理能够更好地将其动作与观察到的环境上下文对齐来提高其性能的新框架。ACCORD通过在每个动作之前主动探查缺失信息并整合代理历史中的相关上下文来解决指令不明确的问题。该方法显著提高了任务完成率，在AppWorld基准测试中，使用GPT-5-mini的完成率提高了多达20.6个百分点，并且在Claude-4.5-sonnet和Qwen3.5-27B-FP8等其他模型上也显示出收益。 AI
影响 通过改进上下文对齐和任务完成来增强LLM代理的性能。
排序理由 该集群包含一篇详细介绍语言代理新框架的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.16432v1 Announce Type: cross Abstract: User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment. For large language model (LLM) agents operating in information-rich digital and physical environments, these…
User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment. For large language model (LLM) agents operating in information-rich digital and physical environments, these assumptions cannot be inferred from the instructi…