Skip to content
Log in

Author

Hanqing Zeng

h-index 2 View on Semantic Scholar

We have 1 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

EvoHarness-RL is introduced, which exposes Belief, Progress, and Experience (BPE) as policy-facing harness state and reveals two key dynamics: harness annealing, where training internalizes recurring harness-use patterns into the model policy and shifts the agent from frequent harness calls toward selective external-state access, and harness evolution, where progress updates and experience consolidation refine the harness into a compact, task-adaptive state substrate.

Xuying Ning, Dongqi Fu, Tianxin Wei et al. · 0 citations