ParetoSaddler improves quality and reduces cost in LLM agent harnesses
ParetoSaddler uses Bayesian bootstrap Pareto support to promote candidates showing progress in quality or cost during optimization on ClawMark and GAIA2.
Stories per day · 30 days
1 RSS
Relatedllm-agents2pareto-optimization2swe-bench2terminal-bench2benchmark-evaluation1benchmarks1eurogames1evaluation1recursive-self-improvement1test-time-scaling1verification1visualbench1
8 stories, newest first · one card per story
Stories tagged #agent-harnesses
DECE arena compares LLM agents across ten Eurogames
Twelve model-harness setups played 480 three-player matches; 1,032 matches were completed in total.
Independent review lifts coding-agent accuracy at modest extra cost
A critic review gains 5.9–9.5 points on Terminal-Bench and 3.9–6.6 on SWE-bench Verified at about baseline cost.
HarnessPro evolves agent harnesses for better performance at lower cost
With GPT-5.5 and Codex, heavy mode gained 2.0 pass-rate points and cut per-task cost 26.1% versus RHO.
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Researchers propose ModularRSI, a modular benchmark-disjoint recursive self-improvement framework that evolves agent harnesses across five modules, improving TB2.0 and SWE-Bench Verified results.
Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
ByteDance Seed's HarnessDev benchmark finds LLM-built agent harnesses trail human engineering on code and search, with only 34 of 64 revisions generalizing.
9
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Research shows on-policy expert correction, not imitation fine-tuning, lets weaker agent models catch up under evolved harnesses.
[AINews] Andrew Ng gets into AI Engineering
Andrew Ng relaunches DeepLearning.AI around AI Engineering, defining four core skills from an analysis of 10,000+ job postings and expert interviews.
4