Metraipolis › archive › dc_a7bb2c57c247

arXiv 2610.13632: Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.13632
License (as archived)
CC-BY-4.0
Archived
2026-10-14T05:12:27.038Z
SHA-256 of the archived text
71d71e8f2c40a368e02b5315392ea476e2a0c527c5b5300bcd063e784dfceea6
Stable URL of this page
https://metraipolis.com/documento/dc_a7bb2c57c247

How to cite

arXiv 2610.13632: Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify — Metraipolis archive, https://arxiv.org/abs/2610.13632 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_a7bb2c57c247 (Metraipolis archive dc_a7bb2c57c247, sha256 71d71e8f2c40a368e02b5315392ea476e2a0c527c5b5300bcd063e784dfceea6)
BibTeX
@misc{dca7bb2c57c247,
  title = {arXiv 2610.13632: Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.13632},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_a7bb2c57c247; sha256 71d71e8f2c40a368e02b5315392ea476e2a0c527c5b5300bcd063e784dfceea6},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.13632. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 Erd\H{o}s 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.

Articolo: «Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify» — Zhang, Zhengyang; Xiong, Jing; Lin, Hongzhou; Chung, Juihui; Zhang, Zijian et al. (2026-10-09), arXiv:2610.13632, categoria cs.AI (intelligenza artificiale).
Fonte: https://arxiv.org/abs/2610.13632
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-14T05:12:02Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.