Papers with single-agent and

2 papers
Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning (2025.naacl-long)

Copied to clipboard

Challenge: Teaching large language models to use tools for solving complex problems can grant them human-like reasoning abilities.
Approach: They propose a multi-agent system that enhances the Deep First Search Decision Tree (DFSDT) to address issues like error propagation and limited exploration in ReAct .
Outcome: The proposed system reduces token usage by 60.9% compared to existing methods and performs on par with GPT-4-DFSDT.
Adapting LLM Agents with Universal Communication Feedback (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have demonstrated potential for LLM agents.
Approach: They propose a universal buffer and iterative pipeline to store feedback and itersative pipelines to enable LLM agents to explore and update their policy in an environment.
Outcome: The proposed approach outperforms supervised instruction fine-tuning baselines on four datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations