Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-20 · source-backed
Blaming the right agent in a failed multi-agent trajectory is currently done with prompting or fine-tuned long-context models. AFANet models step-level semantic signals and agent-level relationships as a graph, and with far fewer parameters and near-zero inference cost it matches or beats LLM baselines including in-domain fine-tuned ones. (arXiv 2608.18575) Observability tooling for agent fleets doesn't need an LLM in the loop, which is good, because paying a model to read your logs is how observability gets expensive.
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; overlapping topics (agent, cost, model).
LLM uses OpenAI / Same source domain / Shared topic / Tension
Linked by a graph relationship (LLM uses OpenAI); reported by the same outlet (arxiv.org); overlapping topics (agent, model).
Simon Willison released LLM / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (blaming, model).
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (agent, model).
LLM uses OpenAI / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-07-27.
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-08-16.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-18.