Papers with LLM-LRM combinations
LRPLAN: A Multi-Agent Collaboration of Large Language and Reasoning Models for Planning with Implicit & Explicit Constraints (2025.findings-emnlp)
Copied to clipboard
| Challenge: | LRPlan is a language-based multi-agent system for complex planning problems . large language models are often unable to maintain consistency across the planning process . |
| Approach: | They propose a language-based multi-agent architecture where LLM and LRM agents collaborate at training time to abstract important patterns, heuristics and insights about the domain. |
| Outcome: | The proposed language-based multi-agent architecture outperforms existing models and makes it publicly available. |