Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning

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.

Similar Papers

Overview

Challenge

Approach

Outcome

NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy (2026.acl-long)

Copied to clipboard

Jiye Wang, Yu Wang, Jianbin Li, Shiduo Yang, Kenan Guo, Yuanhe Zhao

Robustness in NLP

Challenge:	Existing approaches to multi-agent problem solving rely on hand-crafted protocols or automatically designed topologies.
Approach:	They propose a state-driven framework that formulates multi-agent problem solving as a finite-state execution process.
Outcome:	The proposed framework outperforms baselines on diverse benchmarks by 6.74%–19.39% while reducing token consumption.

Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant (2025.findings-emnlp)

Copied to clipboard

Lei Shen, Xiaoyu Shen

Challenge:	Auto-SLURP is a benchmark dataset for evaluating multi-agent frameworks powered by large language models.
Approach:	Auto-SLURP is a benchmark dataset aimed at evaluating LLM-based multi-agent frameworks . authors propose it extends original SLURP dataset by relabeling data and integrating simulated servers and external services.
Outcome:	The proposed dataset extends the original SLURP dataset for natural language understanding tasks.

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models (2024.emnlp-main)

Copied to clipboard

Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar

Language Models

Challenge:	Large language models (LLMs) are prohibitive to use under resource constraints due to their high latency and high latex.
Approach:	They propose to use a contextual bandit to help choose a model based on a context to improve performance.
Outcome:	The proposed model can be used to improve performance on multiple domains even without prior knowledge of the model.

DocAgent: An Agentic Framework for Multi-Modal Long-Context Document Understanding (2025.emnlp-main)

Copied to clipboard

Li Sun, Liu He, Shuyue Jia, Yangfan He, Chenyu You

Multimodality

Challenge:	Existing approaches to document understanding are limited due to limited context length or fail to fully leverage multi-modal information.
Approach:	They propose a multi-agent framework for long-context document understanding that imitates human reading practice.
Outcome:	The proposed framework surpasses human-level benchmarks on long-context document understanding while maintaining a short context length.

ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution (2026.acl-long)

Copied to clipboard

Shouzheng Huang, Meishan Zhang, Baotian Hu, Min Zhang

Information Retrieval

Challenge:	Existing methods for large language models struggle to align user intent with tool semantics or generalize to unseen tools.
Approach:	They propose a framework that enables LLMs for open-world tool use by proactive retrieval and grounded execution within a reasoning loop.
Outcome:	The proposed framework surpasses baselines in retrieval and execution efficiency by +10.8%.

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench (2025.findings-emnlp)

Copied to clipboard

Venkatesh Mishra, Amir Saeidi, Satyam Raj, Mutsumi Nakamura, Gaowen Liu, Ali Payani, Jayanth Srinivasa, Chitta Baral

Reasoning

Challenge:	Recent advances in reasoning and planning capabilities of large language models have enabled their potential as autonomous agents capable of tool use in dynamic environments.
Approach:	They propose an input-reformulation multi-agent framework that reformulates user queries .
Outcome:	The proposed framework outperforms ReAct, Function Calling, and Self-Reflection in overall pass5 scores.

MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs (2025.findings-acl)

Copied to clipboard

Qian Wang, Tianyu Wang, Zhenheng Tang, Qinbin Li, Nuo Chen, Jingsheng Liang, Bingsheng He

Green & Sustainable NLP

Challenge:	Existing multi-agent systems lack agent coordination and rely on predefined procedures . existing systems lack adaptive task coordination when task is big and complex .
Approach:	They propose a large-scale autonomous LLM-based multi-agent system that generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication and comprehensive system monitoring.
Outcome:	The proposed system outperforms existing systems in task completion efficiency and scalability.

AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems (2026.acl-long)

Copied to clipboard

Yulang Chen, Haoxuan Peng, Jinyan Liu, Zichen Wen, Dongrui Liu, Linfeng Zhang

Green & Sustainable NLP

Challenge:	Automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption.
Approach:	They propose a plug-and-play compression framework for graph-structured multi-agent workflows . they estimate the importance score of each agent and remove redundant agents .
Outcome:	Experiments show that AgentSlimming reduces average token cost by 78.9% with negligible performance degradation.

Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning (2025.findings-emnlp)

Copied to clipboard

Song Yu, Xiaofei Xu, Ke Deng, Li Li, Lin Tian

Language Models

Challenge:	Large language models face persistent challenges when handling long-context tasks . existing methods that reduce input have the risk of discarding key information .
Approach:	To address this issue, we propose a multi-agent reasoning framework called Tree of Agents . the framework segments input into chunks processed by independent agents .
Outcome:	The proposed model outperforms baseline models on long-context tasks.

DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments (2025.emnlp-main)

Copied to clipboard

Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu

Language Models

Challenge:	Large Language Models (LLMs) with web search capabilities show significant potential for deep research.
Approach:	They introduce a framework for end-to-end training of LLM-based deep research agents . they implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures.
Outcome:	The proposed framework improves on open-domain research tasks by 28.9 points over prompt engineering and 7.2 points over RAG-based RL agents.