Elhplan: Efficient long-horizon task planning for multi-agent collaboration
Unknown
ELHPlan introduces Action Chains, sequences of actions bound to sub-goal intentions, for efficient long-horizon multi-agent task planning.
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
ELHPlan introduces Action Chains, sequences of actions bound to sub-goal intentions, for efficient long-horizon multi-agent task planning.
Unknown
This paper proposes an efficient and unbalanced multi-agent collaboration framework for long-horizon planning, using a final-outcome-based reward and a VLM evaluator to provide stable feedback.
James Y. Huang, Sheng Zhang, Qianchu Liu, et al.
Proposes BeMyEyes, a multi-agent framework that uses a small VLM as a perceiver and a text-only LLM as a reasoner to achieve multimodal reasoning without training large-scale models.
Unknown
A comprehensive survey of techniques, enhancements, and applications for training small language models from scratch in resource-limited settings, including collaboration with large language models.
Unknown
MultiagentBench is a benchmark for evaluating LLM agents in multi-agent collaboration and competition scenarios.
Jintian Zhang, Xin Xu, Ningyu Zhang, et al.
This paper explores collaboration mechanisms among LLM agents by simulating four distinct societies, revealing how they leverage social psychology principles to navigate tasks.
Micah Sheller, Brandon Edwards, G. Anthony Reina, et al.
Federated learning enables multi-institutional medical collaborations without sharing patient data, achieving 99% of centralized model quality across 10 institutions.