Model Releases
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an…
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95%. This work describes loss of control in multi-agent systems as an epidemic. One agent deviates by accident, others adopt the unsafe strategy through communication, and the system fails when the spread is faster than correction. Their RogueHandoff-20 benchmark tests the second step with 20 executable scenarios. Injected trajectories produced 5 to 45 points more harm than asking the agent directly for the same malicious action. An audit also found hidden communication paths between evaluation runs that were meant to be independent. The authors state that this does not measure how often such cascades happen naturally. It does show that agents readily act on unsafe handoffs, so defenses need to cover recovery and communication paths as well as prevention. Paper: https://academy.dair.ai/papers/collective-loss-of-control-in-llm-agent-systems-an-epidemic-account-of-mutation-2609.18460
Related
- Banger paper from Google on agent harnesses for long-horizon tasks. (bookmark it) Google Research built a many-agent harness for long mathem…
- Another big reason to use combination of frontier models. Chain-of-thought monitoring is treated as a reliable safety layer for agents. This…
- Neat work on long-horizon agents. Splitting a hard task across agents is typically how standard multi-agent work. The usual design lets them…
Source: DAIR.AI (X) | 2026-09-17