Banger paper from MIT and Sakana AI. They show that self-improving coding agents work. The best part is that their approach, Self-Improvemen…

Banger paper from MIT and Sakana AI. They show that self-improving coding agents work. The best part is that their approach, Self-Improvement via Fast Tree-search (SIFT), runs at a tenth of the CPU hours of DGM. They reach 35.1 percent on Polyglot with o3-mini after 30 expansions. DGM reaches 30.7 percent after 80 nodes of tree search. SIFT does it in under 50 CPU hours and under 5 hours of wall clock. The Qwen3-30B configuration runs its full search at 224 CPU hours and $34 of API spend, a tenth of the DGM baseline. The saving comes from where the money goes. Benchmark evaluation is the runtime bottleneck, so an LLM judge ranks candidate self-modifications first and only promising candidates get evaluated. Judge quality decides the run. On TerminalBench, gpt-5.4-high as the pairwise judge finds a 36.7 percent agent against a 29.2 percent starting point. gpt-5 finds 34.5 percent, and its top-ranked candidate is not the best agent its search produced. Paper: https://academy.dair.ai/papers/self-improvement-via-fast-tree-search-2609.19526

Related

• Self Improvement via Fast Tree-search
• // MetaSkill-Evolve // Great paper on self-improving agents. Most self-improving agents rewrite what the agent does and leave how it improve…
• Interesting new approach to recursive self-improvement in agents. Systems that add a meta-level hold that level fixed. Systems that edit the…
• Banger paper from the Qwen team. If you evaluate agents on anything longer than a single session, this one is worth your time. (bookmark it)…

Source: DAIR.AI (X) | 2026-09-19