Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making

Excerpt

arXiv:2610.07335v1 Announce Type: new Abstract: Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous agents interacting with complex environments, early mistakes can propagate through trajectories and cause cascading failures. Recent approaches improve reliability by incorporating external critique or deliberation, but invoking these mechanisms at every step substantially increases token consumption an