Harvey's post-trained RLM agent boosts M&A due diligence pass rate

Harvey and Baseten post-trained a recursive language model agent with RL for end-to-end M&A due diligence, using model-harness co-optimization. The benchmark pass rate jumped from roughly 23–29% to about 62–63%.

2026-09-09 ~ 2026-09-09 · 3 related posts

• Baseten and Harvey boost M&A diligence agent pass rate from 29% to 63% with RL on RLM harness — baseten · 2026-09-09
• RLM harness lifts M&A diligence pass rate from 23.3% to 62.4% across seven models — a1zhang · 2026-09-09
• Harvey post-trains RLM agents for M&A diligence, lifting benchmark pass rate from 23% to 62% — lateinteraction · 2026-09-09