Related papers: Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution

Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution

URL: http://arxiv.org/abs/2605.27621v1
Date: Tue, 26 May 2026 19:39:27 GMT
Title: Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution
Abstract summary: We formalize agent attribution as a cooperative game, parameterized by the coalition distribution, removal protocol, and target metric.<n>We show that Leave-One-Out (LOO) identifies bottleneck agents as effectively as bottleneck methods, but at a fraction of the computational cost.<n>We also apply our framework to audit a medical MAS, revealing that agent contributions to diagnostic accuracy and ethical behavior are often decoupled.
Score: 21.301961149692453
License: http://creativecommons.org/licenses/by/4.0/
Abstract: As multi-agent systems (MAS) become increasingly complex, identifying the contributions of individual agents is critical for system optimization. However, existing approaches lack a rigorous, unified framework for credit assignment. In this work, we formalize agent attribution as a cooperative game, parameterized by the coalition distribution, removal protocol, and target metric. Using this framework, we show that Leave-One-Out (LOO) identifies bottleneck agents as effectively as combinatorial methods, but at a fraction of the computational cost. We also demonstrate that removal protocols induce distinct games: Agent ablation isolates structural bottlenecks, whereas introspective LLM judges fail to faithfully approximate this behavior. Furthermore, to evaluate the utility of specific agent backbones, we introduce attribution via model replacement. By substituting underlying models of low-contribution agents, we improve task performance by up to 17% while reducing cost by up to 35% across three benchmarks. Finally, we apply our framework to audit a medical MAS, revealing that agent contributions to diagnostic accuracy and ethical behavior are often decoupled. By intervening on counterproductive roles, we observe an increase in ethics alignment while maintaining diagnostic accuracy. Overall, this work provides a principled approach for cost-effective MAS attribution and intervention.

Related papers

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents [54.08846865906602]
We characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents.<n>We propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools.
arXiv Detail & Related papers (2026-06-04T07:15:43Z)
AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems [19.373173948984626]
AgentSlimming is a plug-and-play compression framework for graph-structured multi-agent systems.<n>It reduces average token cost by up to 78.9% with negligible performance degradation, and sometimes even improves accuracy.
arXiv Detail & Related papers (2026-05-09T09:03:54Z)
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
arXiv Detail & Related papers (2026-04-21T15:05:58Z)
AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition [62.16431420189863]
LLM-based multimodal emotion recognition relies on static parametric memory and often hallucinates when interpreting nuanced affective states.<n>We introduce AffectAgent, an affect-oriented multi-agent retrieval-augmented generation framework.<n>AffectAgent comprises three jointly optimized agents, namely a query planner, an evidence filter, and an emotion generator.
arXiv Detail & Related papers (2026-04-14T13:49:19Z)
Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning [34.10133693878611]
We propose a multi-agent RL framework that selectively penalizes redundant chunks, while preserving essential reasoning logic.<n>Our framework, Self-Compression via MARL (SCMA), instantiates redundancy detection and evaluation through two specialized agents.<n> Empirical evaluations across model scales demonstrate that SCMA reduces response length by 11.1% to 39.0% while boosting accuracy by 4.33% to 10.02%.
arXiv Detail & Related papers (2026-01-29T16:13:10Z)
Alita-G: Self-Evolving Generative Agent for Agent Generation [54.49365835457433]
We present ALITA-G, a framework that transforms a general-purpose agent into a domain expert.<n>In this framework, a generalist agent executes a curated suite of target-domain tasks.<n>It attains strong gains while reducing computation costs.
arXiv Detail & Related papers (2025-10-27T17:59:14Z)
Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference [8.823529310904162]
Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is hampered by the challenge of failure attribution.<n>We introduce the first failure attribution framework for MAS grounded in multi-granularity causal inference.
arXiv Detail & Related papers (2025-09-10T15:22:00Z)
Self-Regulation and Requesting Interventions [63.5863047447313]
We propose an offline framework that trains a "helper" policy to request interventions.<n>We score optimal intervention timing with PRMs and train the helper model on these labeled trajectories.<n>This offline approach significantly reduces costly intervention calls during training.
arXiv Detail & Related papers (2025-02-07T00:06:17Z)
Free Agent in Agent-Based Mixture-of-Experts Generative AI Framework [0.0]
Reinforcement Learning Free Agent (RLFA) algorithm introduces a reward-based mechanism to detect and remove agents exhibiting persistent underperformance.<n>A primary use case is fraud detection, where RLFA promptly swaps out an agent whose detection accuracy dips below a preset threshold.<n>This dynamic, free-agency cycle ensures sustained accuracy, quicker adaptation to emerging threats, and minimal disruption to ongoing operations.
arXiv Detail & Related papers (2025-01-29T13:00:22Z)
Decentralized scheduling through an adaptive, trading-based multi-agent system [1.7403133838762448]
In multi-agent reinforcement learning systems, the actions of one agent can have a negative impact on the rewards of other agents. This work applies a trading approach to a simulated scheduling environment, where the agents are responsible for the assignment of incoming jobs to compute cores. The agents can trade the usage right of computational cores to process high-priority, high-reward jobs faster than low-priority, low-reward jobs.
arXiv Detail & Related papers (2022-07-05T13:50:18Z)
Formalizing the Problem of Side Effect Regularization [81.97441214404247]
We propose a formal criterion for side effect regularization via the assistance game framework. In these games, the agent solves a partially observable Markov decision process. We show that this POMDP is solved by trading off the proxy reward with the agent's ability to achieve a range of future tasks.
arXiv Detail & Related papers (2022-06-23T16:36:13Z)
VCG Mechanism Design with Unknown Agent Values under Stochastic Bandit Feedback [104.06766271716774]
We study a multi-round welfare-maximising mechanism design problem in instances where agents do not know their values. We first define three notions of regret for the welfare, the individual utilities of each agent and that of the mechanism. Our framework also provides flexibility to control the pricing scheme so as to trade-off between the agent and seller regrets.
arXiv Detail & Related papers (2020-04-19T18:00:58Z)

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