OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration

• URL: http://arxiv.org/abs/2509.04876v1
• Date: Fri, 05 Sep 2025 07:44:05 GMT
• Title: OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
• Authors: Jusheng Zhang, Yijia Fan, Kaitong Cai, Xiaofei Sun, Keze Wang,
• Abstract summary: OSC (Orchestrating Cognitive Synergy) is a knowledge-aware adaptive collaboration framework.<n>It enhances cognitive synergy in multi-agent systems with large language models.
• Score: 13.032459988986068
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. OSC addresses this gap as a pivotal intermediate layer between selection and aggregation, introducing Collaborator Knowledge Models (CKM) to enable each agent to dynamically perceive its collaborators' cognitive states. Through real-time cognitive gap analysis, agents adaptively adjust communication behaviors, including content focus, detail level, and expression style, using learned strategies. Experiments on complex reasoning and problem-solving benchmarks demonstrate that OSC significantly improves task performance and communication efficiency, transforming "parallel-working individuals'' into a "deeply collaborative cognitive team.'' This framework not only optimizes multi-agent collaboration but also offers new insights into LLM agent interaction behaviors.

Related papers

• EmCoop: A Framework and Benchmark for Embodied Cooperation Among LLM Agents [18.802912315746564]
  EmCoop is a benchmark framework for studying cooperation in embodied multi-agent systems.<n>Our framework separates a high-level cognitive layer from a low-level embodied interaction layer.<n>We propose generalizable, process-level metrics that diagnose collaboration quality and failure modes.
  arXiv  Detail & Related papers  (2026-02-27T22:28:33Z)
• Learning "Partner-Aware" Collaborators in Multi-Party Collaboration [12.287537011305497]
  Large Language Models (LLMs) are increasingly bring deployed in agentic settings where they act as collaborators with humans.<n>This paper builds on the AI alignment and safe interruptability literature to offer novel theoretical insights on collaborative behavior.<n>We propose Interruptible Collaborative Roleplayer (ICR)-a novel partner-aware learning algorithm to train CG-optimal collaborators.
  arXiv  Detail & Related papers  (2025-10-26T00:05:48Z)
• Improving Cooperation in Collaborative Embodied AI [31.991962631895657]
  The integration of Large Language Models into multiagent systems has opened new possibilities for collaborative reasoning and cooperation with AI agents.<n>This paper explores different prompting methods and evaluates their effectiveness in enhancing agent collaborative behaviour and decision-making.<n>We extend our research by integrating speech capabilities, enabling seamless collaborative voice-based interactions.
  arXiv  Detail & Related papers  (2025-10-03T16:25:48Z)
• When LLMs Team Up: The Emergence of Collaborative Affective Computing [17.777196145195866]
  This survey aims to provide a comprehensive overview of Large Language Models (LLMs)-based collaboration systems in Affective Computing (AC)<n>LLMs offer a unified approach to affective understanding and generation tasks, enhancing the potential for dynamic, real-time interactions.<n>This work is the first to systematically explore collaborative intelligence with LLMs in AC, paving the way for more powerful applications that approach human-like social intelligence.
  arXiv  Detail & Related papers  (2025-06-02T14:00:54Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• Multi-Agent Collaboration via Evolving Orchestration [61.93162413517026]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a central orchestrator dynamically directs agents in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)
• Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination [0.9776703963093367]
  Multi-Agent Reinforcement Learning (Dec-MARL) has emerged as a pivotal approach for addressing complex tasks in dynamic environments.<n>This paper presents a novel Dec-MARL framework that integrates peer-to-peer communication and coordination, incorporating goal-awareness and time-awareness into the agents' knowledge-sharing processes.
  arXiv  Detail & Related papers  (2025-01-26T22:49:50Z)
• Communication Learning in Multi-Agent Systems from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time.
  arXiv  Detail & Related papers  (2024-11-01T05:56:51Z)
• Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning [10.932974027102619]
  This study introduces a computational framework based on multi-agent reinforcement learning in the spatial Prisoner's Dilemma game. By modelling each agent using two distinct Q-networks, we disentangle the coevolutionary dynamics between cooperation and interaction.
  arXiv  Detail & Related papers  (2024-05-04T12:42:55Z)
• Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning [57.652899266553035]
  Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server. We propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.
  arXiv  Detail & Related papers  (2024-03-11T09:21:11Z)
• Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction [6.020016097668138]
  CooperKGC is a novel framework challenging the conventional solitary approach of large language models (LLMs) in knowledge graph construction (KGC) CooperKGC establishes a collaborative processing network, assembling a team capable of concurrently addressing entity, relation, and event extraction tasks.
  arXiv  Detail & Related papers  (2023-12-05T07:27:08Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)
• Detecting and Optimising Team Interactions in Software Development [58.720142291102135]
  This paper presents a data-driven approach to detect the functional interaction structure for software development teams. Our approach considers differences in the activity levels of team members and uses a block-constrained configuration model. We show how our approach enables teams to compare their functional interaction structure against synthetically created benchmark scenarios.
  arXiv  Detail & Related papers  (2023-02-28T14:53:29Z)

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.