ActONOMY: A Taxonomy of Agent Behaviors
DanielKhashabi · x · 2026-07-16
This retweet highlights a research project where the author annotated AI/ML conference papers to build ActONOMY, a taxonomy of agent behaviors.
Instead of asking "can agents reason/plan," the core question is: what do researchers and developers actually expect agents to do. This taxonomy reveals many unspoken yet implicitly assumed behavioral expectations across academic papers.
More from Research
- New prompt template aims to improve spatial reasoning and cut model laziness — legit_api · 2026-07-21
- Style-similarity analysis puts Kimi K3 closer to Claude Fable 5 than to K2.6 — soumitrashukla9 · 2026-07-21
- A GLP1R variant may explain stronger Ozempic weight loss, and the team built an agent workflow — julia_kiseleva · 2026-07-21
- Proceedings for the second geometry-grounded representation learning workshop are now online — erikjbekkers · 2026-07-21
- New survey maps how agentic systems are learning to improve themselves — SchmidhuberAI · 2026-07-21
- A curated TTS list for voice agents tracks latency, cancellation, and evals — mahimairaja · 2026-07-21