From Evidence to Action: How Tool-Using Agents Fail
- 类型：arxiv
- 标识：2610.07753
- 链接：https://arxiv.org/abs/2610.07753
- 主分类：agent
- 形态：method
- TLDR：Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows. Across ten model-harness configurations, strong static action assessment can coexist with much weaker interactive execution. Failures often begin before execution: agents stop with incomplete investigation or act before required evidence is established. Once required evidence is
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-10-07-agent-rag-longcontext-candidates.json