Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline · HackerPapers discussions

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by CamperBob2

Fri, 02 Jan 2026 15:32:53 GMT

Except of course it's not true lol. Horses are smart critters, but they absolutely cannot do arithmetic no matter how much you train them. These things are not horses. How can anyone choose to remain so ignorant in the face of irrefutable evidence that they're wrong? https://arxiv.org/abs/2507.15855 It's as if a disease like COVID swept through the population, and every human's IQ dropped 10 to 15 points while our machines grew smarter to an even larger degree.

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by NitpickLawyer

Wed, 12 Nov 2025 09:49:44 GMT

a) no, gemini 2.5 was shown to "win" gold w/o tools. - https://arxiv.org/html/2507.15855v1 b) reductionism isn't worth our time. Planning works in the real world, today. (try any agentic tool like cc/codex/whatever). And if you're set on the purist view, there's mounting evidence from anthropic that there is planning in the core of an LLM. c) so ... not true? Long context works today. This is simply moving goalposts and nothing more. X can't do Y -> well, here they are doing Y -> well, not like that.

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by impossiblefork

Fri, 10 Oct 2025 21:34:10 GMT

It's reasonable to question it, but there's a fun Chinese paper (https://arxiv.org/abs/2507.15855) where they attempt to create a system of prompts that can be used with commercial LLMs to solve hard maths problems. It turns out that they can use the same prompt system for all of them, with no changes and still solve 5/6 IMO problems. I think this is possibly iffy, since people might have updated the models etc., but it's pretty obvious that this kind of thing is how OpenAI are doing their multi-stage thinking thing for maths internally. Consequently if prompt systems are this transferable…

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by dang

Sun, 05 Oct 2025 17:50:37 GMT

We've changed the top link to that from https://arxiv.org/abs/2507.15855. Thanks!

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by yorwba

Sun, 05 Oct 2025 17:22:49 GMT

I think you meant to link to Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR https://arxiv.org/abs/2509.02522 not Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline https://arxiv.org/abs/2507.15855

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by jsnell

Wed, 17 Sep 2025 19:30:11 GMT

A terse prompt and expecting a one-shot answer is really not how you'd get an LLM to solve complex problems. I don't know what Deepmind and OpenAI did in this case, but to get an idea of the kind of scaffolding and prompting strategy that one might want, have a look at this paper where some floks used the normal generally available Gemini Pro 2.5 to solve 5/6 of the 2025 IMO problems: https://arxiv.org/pdf/2507.15855

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by starchild3001

Mon, 25 Aug 2025 03:28:28 GMT

Hypothesis: If you had ~1M dollar to burn, I think we should try setting up an AI agent to explore and try to invent new mathematics. It turns out agents can get an IMO gold with Gemini 2.5 Pro production model only. Therefore I suspect a swarm of agents burning through tokens like there's no tomorrow can invent new math. Reference: https://arxiv.org/abs/2507.15855 Alternative: If Gemini Deep Think or GPT5-Pro people are listening, I think they should give free access to their models with potential scaffolding (ie. agentic workflow) to say some ~100 researchers to see if any of them can prove…

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by 986aignan

Sat, 09 Aug 2025 17:41:47 GMT

It is possible to take this too far, though - consider the OpenAI IMO proofs[1], for instance, and compare them to Gemini's.[2] [1] https://github.com/aw31/openai-imo-2025-proofs [2] https://arxiv.org/pdf/2507.15855 Appendix A

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by demirbey05

Thu, 07 Aug 2025 17:50:31 GMT

IMO is not breakthrough, if you craft proper prompts you can excel imo with 2.5 Pro. Paper : https://arxiv.org/abs/2507.15855. Google just put whole computational power with very high quality data. It was test-time scaling. Why it didn't solve problem 6 as well? Yes, it was breakthrough but saturated quickly. Wait for next breakthrough. If they can build adapting weights in llm we can talk different things but test time scaling coming to end with increasing hallucination rate. No sign for AGI.

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — HN submission

Fri, 25 Jul 2025 15:24:29 GMT

Gemini 2.5 Pro Capable of Winning Gold at IMO 2025

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — HN submission

Thu, 24 Jul 2025 03:16:37 GMT

Gemini 2.5 Pro Capable of Winning Gold at IMO 2025 with Prompting

4 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — mentioned by bwfan123

Tue, 22 Jul 2025 15:41:20 GMT

This paper [1] shows that gemini pro 2.5 without data-contamination and some minimal prompting (llm orchestration) can solve problems 1-5 on imo 2025. [1] https://arxiv.org/pdf/2507.15855 For problems with 2 page solutions, the search space of solutions is likely limited, and hence could be brute-forced by a search. Combinatorics is likely the hold-out since there are no set approaches one could take ie training data wont cover the space of techniques - which could explain why problem 6 stumped the llms. Also, in the future the minimal diligence IMO problem setters could do is to test against…

Paper and discussion history. A mention is not an endorsement.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline — HN submission

Tue, 22 Jul 2025 04:43:06 GMT

Gemini 2.5 Pro Capable of Winning Gold at IMO 2025

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.