SAO Outperforms GRPO on Coding and Reasoning Benchmarks
ivan_bezdomny · x · 2026-07-15
This repost points out that current improvements primarily stem from Direct Double-Sided Importance Sampling (DIS), rather than vanilla GRPO.
Key takeaways:
- Vanilla GRPO is outdated, but can still linger for a while through various tweaks.
- The new method, SAO (Single-rollout Asynchronous Optimization), appears to have a higher ceiling.
- The paper claims that SAO can stably train for 1000 steps and consistently outperforms GRPO and its variants on benchmarks like SWE-Bench Verified, BeyondAIME, and IMOAnswerBench.
This represents a training method advancement tailored for agentic coding and reasoning tasks.
Related event: SAO Outperforms GRPO in Coding and Reasoning Benchmarks(3 posts)→
More from coding & agent
- Dev builds interactive 3D product experience with GPT-6 Astra + Hyper3D Rodin — nikola_mr64990 · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11