arXiv Machine Learning July 23, 2026 By Shay Seiya McDonnell, Avantika Singh, Quoc-Viet Pham, Vratislav Havlik, Gregory M. P. O'Hare

Harnessing Disagreement: Detecting Correlated Agreement Blindness in Multi-Agent Triage

Read the original on arXiv Machine Learning →

arXiv:2607. 19899v1 Announce Type: cross Abstract: Disagreement-triggered escalation can create a structural blind spot in multi-agent arbitration: as base learners improve, they tend to converge, weakening safety monitoring where correlated failures concentrate.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 2

Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis

arXiv:2606. 00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error.

By VD Doske

llms reinforcement-learning safety

arXiv Machine Learning

Aug 5

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment

arXiv:2608. 02786v1 Announce Type: new Abstract: AI systems can fail silently.

By Priyanka Bajaj (Independent Researcher)

llms fine-tuning benchmarks

arXiv AI

Jun 2

POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems

arXiv:2606. 02282v1 Announce Type: new Abstract: Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist characterisation block their deployment in safety-critical domains -- a gap made legally untenable by emerging AI regulation.

By I\~naki Dellibarda Varela, R. Sendra-Arranz, Pablo Romero-Sorozabal, J. M. Valverde-Garc\'ia, Annemarie F. Laudanski, \'Alvaro Guti\'errez, Eduardo Rocon, Manuel Cebrian

llms agents benchmarks safety

arXiv AI

Aug 11

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

arXiv:2605. 12991v3 Announce Type: replace-cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy.

By Adarsh Kumarappan, Ananya Mujoo

llms agents reinforcement-learning safety

arXiv AI

Aug 12

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

arXiv:2608. 10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks.

By Zixing Chen, Xingyuan Liu, Jie Zhu, Huaixia Dou, Shuo Jiang, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang

llms agents multimodal benchmarks safety

arXiv AI

Jul 13

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors

arXiv:2505. 14300v2 Announce Type: replace Abstract: White-box monitoring is increasingly adopted as an auditing tool as Large Language Models (LLMs) are deployed in daily operations to ensure safe model behavior.

By Maheep Chaudhary, Fazl Barez

llms agents robotics benchmarks

Related stories

Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment

POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors