Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify
We introduce HOA (Humanize Olympiads Agent), an open, flow-level framework that coordinates multiple agent sessions through three complementary feedback channels.
ProofPaper ↗
Key points
- 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.
Sources (1)
- [1]Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, VerifyarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 02:14 PM
We introduce HOA (Humanize Olympiads Agent), an open, flow-level framework that coordinates multiple agent sessions through three complementary feedback channels.
Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks.
Extractive summary: sentences quoted from the sources.