LIVE
Google DeepMind Introduces Gemini 3.8 Live and Its Extended Thinking Variant15/09/26 · Google DeepMind|What's at stake in AI's trillion-dollar infrastructure bet15/09/26|A Flaw in Chain-of-Thought Safety Monitoring14/09/26|Stellar Colosseum: A Multi-Agent System for Long-Horizon Mathematical Research14/09/26|Apple Code Hints Siri Could Be Swapped for ChatGPT or Claude14/09/26 · Apple|Anthropic says Houthi-linked actors used Claude Code for missile guidance software13/09/26 · Anthropic|Yoshua Bengio examines why AI agents lie, cheat and coordinate13/09/26|Terence Tao warns of a 'severe misalignment' in OpenAI's mathematical claims11/09/26 · OpenAI|Terence Tao warns of a 'severe misalignment' of AI in mathematics11/09/26|OpenAI's Navier-Stokes release comes with a Lean 4 formal proof10/09/26 · OpenAI|OpenAI publishes documentation for its Agents API10/09/26 · OpenAI|OpenAI Launches the Agents API, a Managed Service for Cloud Agents10/09/26 · OpenAI|Google DeepMind Introduces Gemini 3.8 Live and Its Extended Thinking Variant15/09/26 · Google DeepMind|What's at stake in AI's trillion-dollar infrastructure bet15/09/26|A Flaw in Chain-of-Thought Safety Monitoring14/09/26|Stellar Colosseum: A Multi-Agent System for Long-Horizon Mathematical Research14/09/26|Apple Code Hints Siri Could Be Swapped for ChatGPT or Claude14/09/26 · Apple|Anthropic says Houthi-linked actors used Claude Code for missile guidance software13/09/26 · Anthropic|Yoshua Bengio examines why AI agents lie, cheat and coordinate13/09/26|Terence Tao warns of a 'severe misalignment' in OpenAI's mathematical claims11/09/26 · OpenAI|Terence Tao warns of a 'severe misalignment' of AI in mathematics11/09/26|OpenAI's Navier-Stokes release comes with a Lean 4 formal proof10/09/26 · OpenAI|OpenAI publishes documentation for its Agents API10/09/26 · OpenAI|OpenAI Launches the Agents API, a Managed Service for Cloud Agents10/09/26 · OpenAI|
Research

Stellar Colosseum: A Multi-Agent System for Long-Horizon Mathematical Research

A new multi-agent harness breaks down research problems in mathematics and theoretical computer science into verifiable sub-proofs, achieving strong results on automated theorem-proving benchmarks.

September 14, 20263 min readPublished byarXiv

Researchers have introduced Stellar Colosseum, a model-agnostic harness designed to coordinate long-horizon research efforts in mathematics and theoretical computer science. Rather than asking a single model to produce a proof in one pass, the system first explores alternative strategies and uses a readiness gate to decide when a given approach is mature enough to be broken down into interdependent, section-level subproblems.

The harness generates multiple candidate solutions in parallel, subjects them to targeted falsification, and then merges the proposals along with their critiques into a single research artifact through what the authors call overlapping random-sample tree aggregation. Feedback from verification steps is routed back to the specific part of the argument it affects, allowing errors to be corrected locally rather than forcing a full restart of the reasoning process.

The authors note that this workflow has also been integrated into Google Antigravity's Teamwork framework as a pattern called Long Proof, pointing to an ambition to move the method beyond a purely experimental setting. Testing combined open-ended research exploration with quantitative benchmarks: using Gemini 3.1 Pro, the team reports several new results addressing open problems drawn from papers published at venues such as FOCS and in the journal JMLR.

On TCS-Bench, a set of research-level theorem-proving tasks sourced from FOCS, STOC, and SODA papers, Colosseum reaches 71.0% accuracy when combining Gemini 3.1 Pro and Gemini 3.7 Flash. In a separate Codeforces-style evaluation, the proof-oriented pipeline with execution feedback solves 218 out of 222 problems. If these figures hold up under independent scrutiny, they would suggest meaningful progress in getting AI systems to sustain structured, multi-step reasoning — an area where language models have historically struggled once proofs extend beyond a few steps.

Tags
multi-agentreasoningtheorem-provingllm-agentsbenchmarkmathematics