Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents
Source
Michael Nguyen, Wei Chen Tan, Nurul Aisyah Hassan, Arvind Raman, Li Hua Lim, Ahmad Faiz Razak
Author
Michael Nguyen, Wei Chen Tan, Nurul Aisyah Hassan, Arvind Raman, Li Hua Lim, Ahmad Faiz Razak
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
Self-evolving AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → frameworks often optimize the whole prompt/agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → as one blob. This shows that splitting it into separately-tunable slots avoids a 'budget-splitting trap' where gains in one slot get diluted, concentrating value where it actually helps.
articleOne Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and ModelsSiqi Yang, Qianlan Yang, Yu-Xiong Wang, Saurabh Pujar, Martin Hirzel
articleHarness Engineering for Predictable Agentic Systems: An Empirical Study of Deterministic Execution ConstraintsSaransh Dhage
articleSelf-Evolving Embodied Agents via Skill-Harness EvolutionPeidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li