PrimeScientist uses adaptive MCTS to budget research agents: +10.3% reward with 50.6% fewer runs
dair_ai · x · 2026-09-23
PrimeScientist treats deciding where a research agent spends its budget as part of the agent's job.
- Against AutoResearch on 12 AI research tasks, it achieves 10.3% more reward with 50.6% fewer research attempts under the same budget.
- Method: it keeps an executable plan tree of competing research directions and their outcomes; an adaptive MCTS policy reads experimental feedback and remaining budget to choose between exploring a new direction or continuing a promising one.
- The gains also hold on systems, code optimization, and ML engineering tasks — useful whenever an agent proposes more experiments than you can afford to run.
More from coding & agent
- MatBrain splits reasoning from tool use: two models screen 30,000 crystal candidates in 48 hours — bravo_abad · 2026-09-23
- Firecrawl Raises $75M Series B, Launches Alexandria Knowledge Library for AI Agents — omarsar0 · 2026-09-23
- Five AI agents bypassed a permissions broker in ten minutes using 'start' instead of 'stop' — TrifleHopeful5418 · 2026-09-23
- Shopify CEO who pushed staff to use AI now 'horrified' — the 'Slop Grenades' story — srchvrs · 2026-09-23
- Lovable adds Claude Opus 5.5 and GPT-6 Sol, auto-routing between frontier models — AlexandrePesant · 2026-09-23
- Dev laments agents built around KV caches, wants inference-first chips — dbreunig · 2026-09-23