Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Stellar Colosseum, a many-agent harness for long-horizon math and TCS research, solves open problems and reaches 71% on TCS-Bench with Gemini models.
Stellar Colosseum is a model-agnostic harness that allocates inference across long-horizon research in mathematics and theoretical computer science, using strategy exploration, a readiness gate, section-level decomposition, and verifier feedback routing. Integrated into Google Antigravity's Teamwork framework as the Long Proof pattern, it obtains new results on open problems from FOCS and JMLR papers using Gemini 3.1 Pro. On TCS-Bench it achieves 71.0% accuracy with Gemini 3.1 Pro and Gemini 3.7 Flash, and a Codeforces evaluation with Gemini 3.1 Pro solves 218 of 222 problems.
- Many-agent harness for long-horizon mathematical and theoretical CS research
- Achieves 71.0% on TCS-Bench with Gemini 3.1 Pro and Gemini 3.7 Flash
- Solves 218 of 222 Codeforces problems with execution feedback
- Integrated into Google Antigravity's Teamwork as the Long Proof pattern
From the original article
1 min read at arxiv.orgLanguage models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdependent decisions. We introduce Stellar Colosseum, a model-agnostic harness for allocating inference across research in mathematics and theoretical computer science.
By Honghao Lin · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.