Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making
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 incor...
Heewon Park, Somin Im, Minhae Kwon
· 0 citations