Weekly Paper Radar

2026-08-24 → 2026-08-30 · scanned 2089 unique arXiv papers · 2 candidate(s)

01

Candidate supply and answer selection shape the value of LLM judging in multi-agent systems

arXiv:2608.25937 · recall: citation · cites 1 seed paper(s)
agentmulti-agent

Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer.

Metadata

Authors: Jia-Hao Ji, Sijie Li, Jiabei Cheng, Zixi She, Jin-Tai Yu, Zhiyuan Yuan

Affiliations: Unknown

Published: 2026-08-26

02

Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems

arXiv:2608.24069 · recall: citation · cites 1 seed paper(s)
agentmulti-agent

LLM-based multi-agent trading systems, in which specialized agents collaborate through structured communication to produce trading decisions, are moving rapidly from research prototypes to live deployments that control real assets.

Metadata

Authors: CheolWon Na, Hao Ni, Lukasz Szpruch, Zhangyang Wang, Dhagash Mehta, Saurabh Nagrecha, Alejandro Lopez-Lira, Chanyeol Choi, Yongjae Lee, Jee-Hyong Lee

Affiliations: Unknown

Published: 2026-08-25