Abstract:LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights or evaluation environments. Life-Harness evolves from training trajectories by converting recurring interaction failures into reusable interventions across environment contracts, procedural skills, action realization, and trajectory regulation, and remains fixed during held-out evaluation. On seven deterministic environments from $\tau$-bench, $\tau^2$-bench, and AgentBench, Life-Harness improves 116 out of 126 model--environment settings across 18 model backbones, with an average relative improvement of 88.5%. Harnesses evolved only from Qwen3-4B-Instruct trajectories transfer to 17 other models, showing that Life-Harness captures reusable environment-side structure rather than model-specific behavior. These results position runtime interface adaptation as a complementary alternative to model-centric agent training. Code is available at GitHub.
| Comments: | Work in progress |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.22166 [cs.AI] |
| (or arXiv:2605.22166v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22166 arXiv-issued DOI via DataCite (pending registration) |
From: Tianshi Xu [view email]
[v1]
Thu, 21 May 2026 08:36:49 UTC (1,723 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。