HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

Excerpt

arXiv:2610.06563v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap as the problem of agentic abstention, and existing approaches typically optimize a model or agent harness against a fixed set of tasks, leading to limited generalization to unseen failure modes. We introduce HERA