Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.17109 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914103711236096 |
|---|---|
| author | Xu, Tianyang Zhang, Dan Mitra, Kushan Hruschka, Estevam |
| author_facet | Xu, Tianyang Zhang, Dan Mitra, Kushan Hruschka, Estevam |
| contents | 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, a framework for multi-agent collaboration with verification-aware 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 multi-agent systems, without relying on external labels or annotations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Verification-Aware Planning for Multi-Agent Systems Xu, Tianyang Zhang, Dan Mitra, Kushan Hruschka, Estevam Computation and Language Artificial Intelligence Machine Learning Multiagent Systems 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, a framework for multi-agent collaboration with verification-aware 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 multi-agent systems, without relying on external labels or annotations. |
| title | Verification-Aware Planning for Multi-Agent Systems |
| topic | Computation and Language Artificial Intelligence Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2510.17109 |