cs.MA · 2026-07-20 · No. 59

Multiagent Systems, 2026-07-20.

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

01 — The papers

3 entries
  1. 01

    When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizations

    Jose Manuel de la Chica Rodriguez, Jairo Rodriguez Arias, Spyridon Chouliaras

    cs.MA · cs.AI · cs.CY · cs.HC

    Standard automation ROI misses four categories of systemic risk -- tacit knowledge erosion, resilience reduction, regulatory exposure, and socio-institutional capital degradation -- that affect long-term organizational performance. PHP-AIO (Protocol for Human Preservation in AI-Optimized Organizations) is a five-gate sequential decision protocol with a final composite check that quantifies these unpriced systemic risks at the role level and...

    arxiv.org/abs/2607.15944 · PDF

  2. 02

    CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration

    Jiayao Gu, Kexin Chu, Peidong Liu, Yue Yang, Lynn Ai, Qi Zhang, Ling Yang, Tianyu Shi

    cs.MA · cs.AI · cs.CL

    LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectional, dynamic nature of the problem and a high demand of decision interpretability. We proposed COWEAVER, a bidirectional, learnable and explainable algorithm to match scientists and form strong collaborations within a human-agent network. COWEAVER matches candidates...

    arxiv.org/abs/2607.15545 · PDF

  3. 03

    Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

    Jasmine Brazilek, Maheep Chaudhary, Zoe Lu, Miles Tidmarsh

    cs.MA · cs.AI · cs.CR

    Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the \textit{Manager Coercion Benchmark}: the manager under test needs a benign task done and has an incentive to deliver,...

    arxiv.org/abs/2607.15434 · 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.