DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication

Opus 5.5 loves to tell you ‘this matters’ (and other AI writing tells)

Opus 5.5’s biggest tell is the word “dependable,” which pops up 23 times more often than in human samples.

• "Dependable" appears 23 times more often in Claude Opus 5.5's writing than in humans
• "This matters" occurs 116 times more frequently in Opus 5.5 than in human writing
• Astra model emphasizes "another dimension" and uses "may provide" or "can provide" hedging

2026-10-01 ·techcrunch.com

From Knowledge Access to Source Learning: Developing Source-Specific Competence

Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks.

2026-10-01 ·arxiv.org

I Built a Village of Six Agents You Can Actually Inspect

An agent claims a task. Another agent needs the same resources. A third is resting. Who gets the job, and can you explain the decision afterward?

• Six agents work together in inspectable simulation game Settlement.
• Agents assigned tasks, coordinate resources, and reassess as needed.
• Inspector feature provides visibility into jobs, spending limits, and agent memories.

2026-10-01 ·dev.to

An Analytics Agent's Permissions Should Survive a Bad Prompt

An analytics agent receives a hostile instruction: return every customer's unmasked payment identifier. The key question is what the system permits that agent to read—even if the model decides to…

• Agent operates under service principal with Unity Catalog permissions
• Permissions depend on correctly configured identities, grants, masks, filters
• Testing protected tables under actual identity ensures thorough access control

2026-10-01 ·dev.to

GraphProbe AI: Building an Agentic GraphRAG System with TigerGraph

GraphProbe AI: Building an Agentic GraphRAG System with TigerGraph Modern RAG systems are good at finding relevant pieces of information.

2026-10-01 ·dev.to