Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify· 人类化奥赛代理
Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized resolution of the Navier--Stokes problem and autonomous solutions to four open questions in the Erdős Conjectures database. Yet neither system releases both its underlying model and complete inference stack. More broadly, a single agent session remains brittle on difficult problems: early errors can propagate, missing domain knowledge can stall progress, and apparent success can mask a misinterpretation or weakening of the original task. We introduce HOA (Humanize Olympiads Agent), an open, flow-level framework that coordinates multiple agent sessions through three complementary feedback channels. First, an independent reviewer evaluates each
提出了一种多会话框架，以提高LLM代理解决奥赛问题的能力。
- 核心方法
- 通过三类反馈渠道（评估、维基、验证）协调多个代理会话，形成开放框架HOA。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 解决长时间跨度的科学和奥赛任务中，单一代理会话易出错且难以持续的问题。
- 关键实验
- 通过多个奥赛问题实例展示了HOA框架的有效性；未提供详细实验数据。
- 主要贡献
- 提供了一个可扩展、可复现的多会话解决问题框架，有助于提升LLM代理的可靠性与准确性。
- 意义与局限
- 意义在于系统性改进了LLM代理解决复杂问题的能力，但其实际应用效果和广泛适应性仍需进一步验证。