arXiv cs.AI· Zhengyang Zhang, Jing Xiong, Hongzhou Lin, Juihui Chung, Zijian Zhang, Song Han, Sihao Liu, Ligeng Zhu·· 6 天前AI 评分62
HOA：面向奥赛解题的多会话智能体工作流，在 IMO、IPhO、IOI 2026 取得满分
Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify
AI 导读
研究者提出 HOA（Humanize Olympiads Agent），一个通过独立评审、结构化 wiki 和 Lean 证明验证三条反馈通道协调多个智能体会话的开放流程级框架。
正文 · 原文
Abstract: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 candidate and provides actionable feedback. Second, a structured wiki supplies task-specific knowledge that may be missing or unreliable in model pretraining. Third, a verifier checks generated Lean proofs against trusted challenge statements. With GPT-5.6 Sol, HOA achieves perfect scores on the IMO, IPhO, and IOI 2026, near-full marks on the IChO 2026 problem set, and solves all 672 problems (100%) on PutnamBench. On the Lean-Eval leaderboard, HOA ranks first, solving 251 of 304 problems (82.6%). We further evaluate HOA with open models. Using Kimi-K3, HOA achieves full scores on the IMO, IPhO, and IOI, and a gold-level score of 97.1% on the IChO. These results closely match the closed-source GPT-5.6 Sol + /Goal baseline on the IMO and IPhO, while exceeding it on the IChO and IOI, demonstrating that systematic feedback can help bridge substantial differences in base-model capability.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.13632 [cs.AI] |
| (or arXiv:2610.13632v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13632 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhengyang Zhang [view email]
[v1]
Fri, 9 Oct 2026 14:14:14 UTC (2,505 KB)
来源：arXiv cs.AI · arxiv.org