First runtime self-evolving agent achieves SOTA on SWE-bench
tom_doerr · x · 2026-08-15
Live-SWE-agent claims to be the first live, runtime self-evolving software engineering agent that expands and revises its own capabilities while working on issues.
Key Points:
- SOTA Performance: Achieves 79.2% on SWE-bench Verified with Claude Opus 4.5, leading current open-source scaffolds; scores 77.4% with Gemini 3 Pro.
- SWE-Bench Pro: Achieves a new state-of-the-art solve rate of 45.8%.
- Insight: Agents are software systems; modern LLM agents possess the intrinsic capability to extend or modify their own behavior at runtime.
More from coding & agent
- Coding agents keep opening 3 stacked PRs per chat, and merging them is a nightmare — holdenmatt · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- Pattern MCP makes coding agents check existing components before writing new code — DonR954 · 2026-10-16
- Zero-keyframe procedural spider walks walls and ceilings using pure raycasts — yshan2u · 2026-10-16
- OpenCode v1.19.2 keeps 1.x installs off the 2.x update path — opencode-agent[bot] · 2026-10-16