4 papers · 1 filter
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution
Zhiwei Shang, Yu Huo, Mingrong Gong +6
An agent harness is the code that organizes context, maintains state, and coordinates tool calls for a language model. We study how to improve the harness under a limited evaluatio…
Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs
Haoran Shou, Haoyue Liu, Yu Huo +2
Large language models can solve increasingly diverse reasoning tasks, yet their performance remains highly sensitive to task prompts, intermediate instructions, and the way reusabl…
LemonHarness Technical Report
Kailong Ren, Fubo Sun, Jiachen Liu +18
As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration. However, agents typically observe on…
From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
Siyue Chen, Yifu Guo, Yuquan Lu +9
Standard accuracy metrics cannot explain why LLMs handle variable tracking but fail on semantically equivalent loops. We study an internal lifecycle of code reasoning in which mode…