SWE-bench Lite
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Google researchers propose a self-improving AI agent Harness
Google researchers proposed a Harness that lets an optimization model revise the runtime code around an AI agent and retain changes that pass validation. On 40 SWE-bench Lite tasks excluded from optimization, the reported modular method raised task success from 5.0% to 40.0% with Gemini 3.8 Flash, while unrestricted whole-Harness rewriting reached 42.5% but used substantially more tokens. Prompt-only changes reportedly reduced success to 2.5%, and transfer without re-optimization to Gemini 4 Argon produced 37.5% success for the modular approach versus 30.0% for whole-Harness rewriting.
IT之家 AI · 🔥 10
Experience and discussion from the community
Share my SWE-bench Lite experienceAsk about SWE-bench Lite
Nobody has shared their experience with SWE-bench Lite yet.