Google's Cogentic lets Gemini find new proofs for 5 unsolved math problems via multi-agent orchestration
rohanpaul_ai · x · 2026-10-02
A new Google paper presents Cogentic, a system that organizes Gemini like a research team: multiple agents explore different ideas in parallel, checkers treat every step as wrong until proven, and validated results are stored in shared notes for later rounds.
Most problems took only about 100 model calls, and human experts confirmed every proof. The takeaway: for long, hard agent tasks, pair your agents with a strict checker and a running record of proven work rather than relying on a better prompt alone.
Related event: Google's Cogentic Multi-Agent System Tackles Open Math Problems(4 posts)→
More from coding & agent
- Muse vs Dots vs Grok Bot: one reviewer's UX and polish rankings point opposite ways — brandon_galang · 2026-10-03
- Code review tool px0 adds theme-aware Mermaid diagrams and 'your changes vs PR changes' view — arpit_bhayani · 2026-10-03
- AI is turning programming from a writing skill into a reading skill — _jaydeepkarale · 2026-10-03
- OpenWiki: open-source AI agents build evidence-backed wikis for your codebase — abhishek__AI · 2026-10-03
- 'Cursor is cooked' takes it back: the hot take that aged like milk — gabriberton · 2026-10-03
- Obol: free self-hosted MCP gateway with argument-level Cedar policies — ToBeContinuedHermit · 2026-10-03