cs.MA · 2026-07-30 · No. 69

Multiagent Systems, 2026-07-30.

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

    DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution

    Hanghui Guo, Weijie Shi, Zhangze Chen, Shengxiang Xu, Yishu Wang, Yimei Zhang, Wangze Ni, Jia Zhu, Shimin Di

    cs.MA · cs.LG

    Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort. Therefore, recent research has increasingly explored harness self-evolution, which iteratively proposes, evaluates, and improves harnesses using historical trial experience. However, accumulated historical experience does not always translate into stable search guidance, and performance often...

    arxiv.org/abs/2607.26722 · PDF

  2. 02

    Living-Harness Is an Interactive-Agent Evolver

    Yuetian Du, Yucheng Wang, He Xu, Jiexu Xu, Shanwen Tan, Bing Zhao, Boyu Yang, Zhijie Xu, Ming Kong, Hu Wei, Jie Liu,...

    cs.MA · cs.AI · cs.CL

    Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions. Static harnesses improve reliability through fixed tools, context, memory, and workflow structures, but remain unchanged after deployment. We propose $\textbf{Living-Harness}$, a self-evolving...

    arxiv.org/abs/2607.26598 · PDF

  3. 03

    One Run Is Not an Idea: The Implementation Lottery in Automated Research

    Jingjie Ning, Shanshan Zhong, Xiaochuan Li, Ji Zeng, Chenyan Xiong

    cs.MA · cs.AI

    Automated research systems use experimental scores both to deliver artifacts and to decide which ideas to retain, transfer, and pursue. Yet one run scores one implementation of an idea. Crediting that realization-level score as evidence about the parent mechanism creates the \emph{implementation lottery}, in which an idea-level conclusion depends on which plausible implementation was sampled. The mismatch is structural whenever one run...

    arxiv.org/abs/2607.26587 · PDF

  4. 04

    A Persona-based Rate Action Index

    Hayden Helm, Andrew Dassori

    cs.MA · cs.AI · cs.LG

    We propose an index for predicting the U.S.\ Federal Open Market Committee (FOMC) decision to hike/hold/cut the current federal funds target rate based on how a collection of personas responds to current market conditions. To construct the index, we collected a new dataset consisting of nearly $25{,}000$ retrievable chunks from publicly available data. We partition the data into per-member corpora and use each as the retrieval database of a...

    arxiv.org/abs/2607.26545 · 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.