Year: 2026
Type: conference-paper
Abstract: Large language model (LLM) agents are increasingly deployed to tackle complex tasks, often necessitating collaboration among multiple specialized agents.However, multi-agent collaboration introduces new challenges in planning, coordination, and verification.Execution failures frequently arise not from flawed reasoning alone, but from subtle misalignments in task interpretation, output format, or inter-agent handoffs.To address these challenges, we present VERIMAP 1 , a framework for multi-agent collaboration with verificationaware planning.The VERIMAP planner decomposes tasks, models subtask dependencies, and encodes planner-defined passing criteria as subtask verification functions (VFs) in Python and natural language.We evaluate VERIMAP on diverse datasets, demonstrating that it outperforms both single-and multi-agent baselines while enhancing system robustness and interpretability.Our analysis highlights how verification-aware planning enables reliable coordination and iterative refinement in multiagent systems, without relying on external labels or annotations.
Institution: Purdue University West Lafayette
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140079545