Pith. sign in

REVIEW 5 cited by

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.18891 v1 pith:WT7ONYIM submitted 2025-03-24 cs.CL cs.AI

classification cs.CLcs.AI
keywords agentdropoutcommunicationperformancetokenachievesagentsconsumptionefficiency
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task performance, making the careful design of the agents' communication topologies particularly important. Inspired by the management theory that roles in an efficient team are often dynamically adjusted, we propose AgentDropout, which identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance. Compared to state-of-the-art methods, AgentDropout achieves an average reduction of 21.6% in prompt token consumption and 18.4% in completion token consumption, along with a performance improvement of 1.14 on the tasks. Furthermore, the extended experiments demonstrate that AgentDropout achieves notable domain transferability and structure robustness, revealing its reliability and effectiveness. We release our code at https://github.com/wangzx1219/AgentDropout.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems

    cs.MA 2025-05 conditional novelty 6.0 of 10

    Moderately sparse communication topologies balance error suppression and insight propagation in LLM multi-agent systems, and the proposed EIB-Learner learns such topologies to outperform prior methods.

  2. Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Agents that start with no game knowledge can build a reusable skill library through trial-and-error and visual feedback, then progress further in two complex games than baseline agents given extra hints.

  3. Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design

    cs.AI 2025-05 conditional novelty 5.0 of 10

    A heuristic framework that decomposes known algorithms into typed LLM-agent subtasks lifts small-model accuracy on knapsack and assignment problems from near-zero to high levels after fixing one bottleneck agent.

  4. GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems

    cs.CL 2025-07 reject novelty 4.0 of 10

    GEMMAS proposes two graph-based metrics for multi-agent LLM collaboration, but its redundancy metric is defined using ground-truth answer correctness rather than actual information redundancy.

  5. Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes Graph-augmented LLM Agent research into planning, memory, tool management, and multi-agent design, and outlines open directions.

Pith tools