Azalia Mirhoseini(@Azaliamirh):Check out LLM-as-a-Verifier: a simple, cheap, & general-purpose self-improvement technique that boosts performance on "any" agentic task we've tried. It achieves SOTA on Terminal-Bench V2, SWE-Bench Verified, RoboRewardBench, and MedAgentBench. The key idea: - Use fine-grained scoring granularity (e.g. 1-20) - Scale model responses with repeated sampling and criteria-based scoring - Rank results based on the expected logprobs of said scores We made it easy for you to try: Code: https://t.co/Pjy71RACh7 Claude Code Plugin: https://t.co/D98qcC5M7W Paper: https://t.co/CbNBdxAWvs Work is led by @jackyk02, with an awesome team!

Azalia Mirhoseini

@Azaliamirh

Founder @RicursiveAI, Asst. Prof. of CS at Stanford. Prev: DeepMind, Anthropic, Brain. Co-Creator of MoEs, AlphaChip, Test Time Scaling.

加入 May 2013

638 正在關注 21K 粉絲

Azalia Mirhoseini@Azaliamirh

2026.07.10 14:10

Check out LLM-as-a-Verifier: a simple, cheap, & general-purpose self-improvement technique that boosts performance on "any" agentic task we've tried. It achieves SOTA on Terminal-Bench V2, SWE-Bench Verified, RoboRewardBench, and MedAgentBench. The key idea: - Use fine-grained scoring granularity (e.g. 1-20) - Scale model responses with repeated sampling and criteria-based scoring - Rank results based on the expected logprobs of said scores We made it easy for you to try: Code: Claude Code Plugin: Paper: Work is led by @jackyk02, with an awesome team!