paper-with-me

Papers

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

2025-08-12 · Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li arxiv

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large model interleaves long-horizon reasoning with precise tool operations, leading to cognitive-load interference and unstable coordination. We present MSARL, a Multi-Small-Agent Reinforcement Learning framework that explicitly decouples reasoning from tool use. In MSARL, a Reasoning Agent decomposes problems and plans tool invocations, while multiple Tool Agents specialize in specific external tools, each trained via a combination of imitation learning and reinforcement learning with role-specific rewards. On mathematical problem solving with code execution, MSARL significantly improves reasoning stability and final-answer accuracy over single-agent baselines. Moreover, the architecture generalizes to diverse tool-use tasks, demonstrating that cognitive-role decoupling with small agents is a scalable blueprint for multi-agent AI design.

📄 PDF Abstract BibTeX arXiv:2508.08882

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning

2026-05-18 · Yuval Shemla, Ayal Yakobe, Tanmay Agarwal, Dhaval Patel 외 arxiv

Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to be included in every prompt, creating substantial token overhead an…

parameter-efficient fine-tuningGeneral Knowledge

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

2026-03-24 · Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng 외 arxiv

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning…

Towards a Cognitive Routing Engine for Software Defined Networks

2016-02-01 · Frederic Francois, Erol Gelenbe

Most Software Defined Networks (SDN) traffic engineering applications use excessive and frequent global monitoring in order to find the optimal Quality-of-Service (QoS) paths for the current state of the network. In this…

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents

2026-04-15 · Rafflesia Khan, Nafiul Islam Khan arxiv

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge moni…

CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning

2026-05-28 · Xiang Fang, Wanlong Fang, Changshuo Wang arxiv

Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models in knowledge-intensive question answering by integrating external visual, textual, and …

Question AnsweringKnowledge Graphs