We propose the Epistemic Planning Calibration Agentic Workflow (EPC-AW) to mitigate planning failures in LLM-based multi-agent systems caused by misjudging knowledge about plan feasibility. The method improves system-level success by an average of 9.75%.
LLM-based multi-agent systems can fail even when actions are executed correctly due to 'epistemic miscalibration'—agents misjudging the feasibility of plans during the planning phase. This miscalibration is latent and dynamic, as new information can alter feasibility assessments. To address this, the paper introduces the Epistemic Planning Calibration Agentic Workflow (EPC-AW). EPC-AW assesses plan support under varying information conditions rather than direct feasibility verification. It employs Information-consistency-based Plan Selection and Consistency-guided Epistemic State Refinement to adapt calibration over time by leveraging past discrepancies. Experiments demonstrate that EPC-AW significantly improves system-level success by an average of 9.75%.