ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models

• URL: http://arxiv.org/abs/2509.04508v1
• Date: Tue, 02 Sep 2025 18:36:52 GMT
• Title: ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models
• Authors: Biddut Sarker Bijoy, Mohammad Saqib Hasan, Pegah Alipoormolabashi, Avirup Sil, Aruna Balasubramanian, Niranjan Balasubramanian,
• Abstract summary: We instantiate single and multi-agent systems for the complex problems in the AppWorld environment.<n>We find that difficulties with long-trajectory learning in smaller language models (SLMs) limit their performance.<n>We introduce a simple progressive sub-task training strategy, which introduces new sub-tasks progressively in each training epoch.
• Score: 17.182616178550795
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems with smaller language models (SLMs) present a viable alternative to single agent systems powered by large language models (LLMs) for addressing complex problems. In this work, we study how these alternatives compare in terms of both effectiveness and efficiency. To study this trade-off, we instantiate single and multi-agent systems for the complex problems in the AppWorld environment using different sized language models. We find that difficulties with long-trajectory learning in smaller language models (SLMs) limit their performance. Even when trained for specialized roles, SLMs fail to learn all subtasks effectively. To address this issue, we introduce a simple progressive sub-task training strategy, which introduces new sub-tasks progressively in each training epoch. We find that this novel strategy, analogous to instance level curriculum learning, consistently improves the effectiveness of multi-agents at all configurations. Our Pareto analysis shows that fine-tuned multi-agent systems yield better effectiveness-efficiency trade-offs. Additional ablations and analyses shows the importance of our progressive training strategy and its ability to reduce subtask error rates.

Related papers

• AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent [57.10083973844841]
  AgentArk is a novel framework to distill multi-agent dynamics into the weights of a single model.<n>We investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios.<n>By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents.
  arXiv  Detail & Related papers  (2026-02-03T19:18:28Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning [54.73049408950049]
  We propose a Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning.<n>Our approach improves unified multimodal retrieval from both structural and learning perspectives.
  arXiv  Detail & Related papers  (2025-07-10T16:47:25Z)
• Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners [60.75160178669076]
  We show that the use of high-capacity value models trained via cross-entropy and conditioned on learnable task embeddings addresses the problem of task interference in online reinforcement learning.<n>We test our approach on 7 multi-task benchmarks with over 280 unique tasks, spanning high degree-of-freedom humanoid control and discrete vision-based RL.
  arXiv  Detail & Related papers  (2025-05-29T06:41:45Z)
• Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One [28.264011412168347]
  Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents.<n>We propose LLM-Ens, a novel approach that enhances RL model ensemble with task-specific semantic understandings.
  arXiv  Detail & Related papers  (2025-05-21T09:35:43Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [66.9481561915524]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation [62.854649499866774]
  Large Language Models (LLMs) have demonstrated remarkable planning abilities across various domains, including robotics manipulation and navigation.<n>We propose a novel multi-agent LLM framework that distributes high-level planning and low-level control code generation across specialized LLM agents.<n>We evaluate our approach on nine RLBench tasks, including long-horizon tasks, and demonstrate its ability to solve robotics manipulation in a zero-shot setting.
  arXiv  Detail & Related papers  (2024-11-26T17:53:44Z)
• CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models [8.793510432881803]
  We introduce the TinyAgent model, trained on a meticulously curated high-quality dataset.<n>We also present the Collaborative Multi-Agent Tuning (CMAT) framework, an innovative system designed to augment language agent capabilities.<n>In this research, we propose a new communication agent framework that integrates multi-agent systems with environmental feedback mechanisms.
  arXiv  Detail & Related papers  (2024-04-02T06:07:35Z)
• JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving [77.51817534090789]
  We propose textbfJiuZhang2.0, a unified Chinese PLM specially for multi-task mathematical problem solving. Our idea is to maintain a moderate-sized model and employ the emphcross-task knowledge sharing to improve the model capacity in a multi-task setting.
  arXiv  Detail & Related papers  (2023-06-19T15:45:36Z)
• MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models [4.84279798426797]
  Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials. We present a novel multi-agent model-based RL algorithm: Multi-Agent Model-Based Policy Optimization (MAMBPO)
  arXiv  Detail & Related papers  (2021-03-05T13:37:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.