cs.MA · 2026-05-30 · No. 12

Multiagent Systems, 2026-05-30.

4 new papers in cs.MA. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

4 entries
  1. 01

    Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization

    Wenwu Li, Yuran Song, Mingze Zhao, Bo Jin, Wenhao Li

    cs.MA · cs.AI

    While Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning tasks through collaborative interaction, optimizing their dynamics remains a formidable challenge due to the discrete, non-differentiable nature of the computation graph and the sparsity of global supervisory signals. Existing black-box optimizers struggle to attribute trajectory-level failure to specific local components, resulting in inefficient,...

    arxiv.org/abs/2605.30227 · PDF

  2. 02

    When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems

    Corrado Rainone, Davide Belli, Bence Major, Arash Behboodi

    cs.MA · cs.AI

    The design space of agentic AI inference spans two extremes: frontier large language models (LLMs), typically hosted in the cloud and offering strong performance across a wide range of tasks at substantially high cost, and more cost-efficient small language models (SLMs), which are amenable to on-device inference. Hybrid multi-agent systems (MASs) combining on-device and cloud models offer a promising middle ground, but they also introduce a...

    arxiv.org/abs/2605.30102 · PDF

  3. 03

    Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas

    Víctor Gallego

    cs.MA · cs.AI · cs.LG

    We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential Social Dilemmas (SSDs). A researcher agent $\mathcal{R}$ (run as a coding agent) reads the inner-loop source code, edits system prompts, feedback functions, helper libraries, and iteration logic, runs evaluations, and decides what to keep, following the autoresearch...

    arxiv.org/abs/2605.30003 · PDF

  4. 04

    Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension

    Francisco León Zúñiga Bolívar

    cs.MA · cs.AI · cs.GT

    Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or does scale and provider diversity reshape equilibrium behaviour in competitive multi-agent settings? Willis et al. established a benchmark for this question using evolutionary game theory and the Iterated Prisoner's Dilemma (IPD), finding consistent cooperative biases in ChatGPT-4o and Claude 3.5 Sonnet. We extend this benchmark to four frontier...

    arxiv.org/abs/2605.29874 · PDF

This edition is part of The Daily Abstract — cs.MA archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.