arXiv AI August 17, 2026 By Babak Abbaschian

Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents

arXiv:2608. 13604v1 Announce Type: new Abstract: Detection of misunderstanding is an urgent problem to solve because communication has moved away from real-time, in-person interaction and is increasingly handled by AI-mediated channels.

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

agents

arXiv AI

Jul 28

Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure

arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.

By Camilo Chac\'on Sartori

llms agents

arXiv AI

Jul 28

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory

arXiv:2607. 23927v1 Announce Type: new Abstract: A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts.

By Saurabh Ranjan, Konstantina Sokratous, Brian Odegaard

llms agents benchmarks safety

arXiv AI

2d ago

When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict

arXiv:2608. 13921v1 Announce Type: new Abstract: LLM agents increasingly maintain personal memory across sessions, but it can conflict.

By Lu Yang, Shusheng Xu, Zhuoran Li, Tongkai Yang, Longbo Huang

llms agents benchmarks

arXiv AI

Jun 9

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

arXiv:2606. 07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction.

By Sanjay Kariyappa, G. Edward Suh

llms agents benchmarks

arXiv AI

Jun 10

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

arXiv:2606. 10747v1 Announce Type: new Abstract: As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiating, and acting on shared tasks.

By Filippo Tonini, Federico Torrielli, Anton Danholt Lautrup, Peter Schneider-Kamp, Mustafa Mert \c{C}elikok, Lukas Galke Poech

agents

arXiv AI

Aug 11

Private Etymology: Designing Relational Reuse of Shared Symbols in Long-Term Human-AI Interaction

arXiv:2608. 08443v1 Announce Type: cross Abstract: Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a relational microculture.

By Miki Ueno

llms agents

Related stories

Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory

When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

Private Etymology: Designing Relational Reuse of Shared Symbols in Long-Term Human-AI Interaction