ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy

• URL: http://arxiv.org/abs/2605.26178v1
• Date: Mon, 25 May 2026 06:41:11 GMT
• Title: ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy
• Abstract summary: textscATOM generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm.<n>textscATOM achieves state-of-the-art performance while improving token efficiency by up to $30%$ compared to strong baselines.
• Score: 10.833679613026456
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We propose \textsc{ATOM}, an adaptive framework that generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm. Inspired by atomic structures, \textsc{ATOM} employs a nucleus-electron hierarchy: it maintains a stable, offline-learned collaboration backbone (the nucleus) while dynamically activating query-conditioned agents (electrons) during inference. Crucially, a complexity-aware budgeting strategy aligns resource consumption with task demands by estimating query difficulty to strictly regulate electron instantiation. Extensive experiments across six diverse benchmarks demonstrate that \textsc{ATOM} achieves state-of-the-art performance while improving token efficiency by up to $30\%$ compared to strong baselines.

Related papers

• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• The Illusion of Multi-Agent Advantage [63.92466143571383]
  We show that expert-architected Multi-Agent Systems (MAS) consistently outperforms automatically generated architectures in raw performance and cost-efficiency.<n>Existing evaluation frameworks mask critical architectural gaps and inefficiencies by failing to account for the marginal utility of increased computational cost.
  arXiv  Detail & Related papers  (2026-06-11T07:39:24Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• An Empirical Study of Multi-Agent Collaboration for Automated Research [41.906658558789545]
  We present a study investigating the comparative efficacy of distinct multi-agent structures for automated machine learning optimization.<n>We benchmark a single-agent baseline against two multi-agent paradigms: a subagent architecture and an agent team architecture.<n>Our findings reveal a fundamental trade-off between operational stability and theoretical deliberation.
  arXiv  Detail & Related papers  (2026-03-31T11:57:00Z)
• AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents [37.232397795331444]
  We present AgentCollab, a self-driven collaborative inference framework that dynamically coordinates models with different reasoning capacities during agent execution.<n>Instead of relying on external routing modules, the framework uses the agent's own self-reflection signal to determine whether the current reasoning trajectory is making meaningful progress.
  arXiv  Detail & Related papers  (2026-03-27T03:07:34Z)
• Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum [10.35088918434398]
  This article shows that the structure of service-dependency graphs, modelled as DAGs, is a primary determinant of whether decentralised, price-based resource allocation can work reliably at scale.<n>We propose a hybrid management architecture in which cross-domain sub-graphs into resource slices that present a simpler, well-structured interface to the rest of the market.
  arXiv  Detail & Related papers  (2026-03-05T19:14:54Z)
• CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System [43.33554364574611]
  CoWork-X casts peer collaboration as a closed-loop optimization problem across episodes.<n>CoWork-X achieves stable, cumulative performance gains while steadily reducing online latency and token usage.
  arXiv  Detail & Related papers  (2026-02-04T19:42:14Z)
• EvoRoute: Experience-Driven Self-Routing LLM Agent Systems [100.64399490164959]
  EvoRoute is a self-evolving model routing paradigm that transcends static, pre-defined model assignments.<n> Experiments on challenging agentic benchmarks demonstrate that EvoRoute, when integrated into off-the-shelf agentic systems, not only sustains or enhances system performance but also reduces execution cost by up to $80%$ and latency by over $70%$.
  arXiv  Detail & Related papers  (2026-01-06T04:06:46Z)
• Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy [40.173458986694584]
  We introduce Difficulty-Aware Interpolant Policy (DA-SIP), a framework that enables robotic controllers to adaptively adjust their integration horizon in real time based on task difficulty.<n>DA-SIP achieves 2.6-4.4x reduction in total time while maintaining task success rates comparable to fixed maximum-computation baselines.
  arXiv  Detail & Related papers  (2025-11-25T22:46:42Z)
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models [99.85131798240808]
  We introduce a novel generative framework called textitGuided Topology Diffusion (GTD)<n>Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process.<n>At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards.<n>Experiments show that GTD can generate highly task-adaptive, sparse, and efficient communication topologies.
  arXiv  Detail & Related papers  (2025-10-09T05:28:28Z)
• Hierarchical Budget Policy Optimization for Adaptive Reasoning [49.621779447691665]
  We present Hierarchical Budget Policy Optimization (HBPO), a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability.<n>HBPO partitions the exploration space into budget-constrained hierarchies (512-2560 tokens), each with differentiated reward structures that preserve both efficiency incentives and reasoning capabilities.<n>Extensive experiments demonstrate that HBPO reduces average token usage by up to 60.6% while improving accuracy by 3.14% across four reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-07-21T17:52:34Z)
• An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation [8.28760409619167]
  We study cost-efficient collaboration between strong and weak language models for repository-level code generation.<n>We evaluate a broad spectrum of collaboration strategies: context-based, pipeline-based, and dynamic.<n>Our most effective collaborative strategy achieves equivalent performance to the strong model while reducing the cost by 40%.
  arXiv  Detail & Related papers  (2025-05-26T16:25:38Z)
• Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models? [68.72260770171212]
  We propose a paradigm of Self-structured Chain of Thought (SCoT), which is composed of minimal semantic atomic steps.<n>Our method can not only generate cognitive CoT structures for various complex tasks but also mitigates the phenomenon of overthinking.<n>We conduct extensive experiments to show that the proposed AtomThink significantly improves the performance of baseline MLLMs.
  arXiv  Detail & Related papers  (2025-03-08T15:23:47Z)
• Mind Your Solver! On Adversarial Attack and Defense for Combinatorial Optimization [111.78035414744045]
  We take an initiative on developing the mechanisms for adversarial attack and defense towards optimization solvers. We present a simple yet effective defense strategy to modify the graph structure to increase the robustness of solvers.
  arXiv  Detail & Related papers  (2021-12-28T15:10:15Z)

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.