AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning

Yichao Liang, Thanh Dat Nguyen, Cambridge Yang, Tianyang Li, Joshua B. Tenenbaum, Carl Edward Rasmussen, Adrian Weller, Zenna Tavares, Tom Silver, Kevin Ellis

ICLR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn abstract causal-process models instead of HRL (MAPLE)ExoPredicator · 5 simulated tabletop environments (held-out tasks)solve rateImproved
learn causal processes instead of prompting a VLM zero-shot (ViLA)ExoPredicator · 5 simulated tabletop environments (held-out tasks)solve rateImproved
add demonstrations to VLM planner (few-shot ViLA)ViLA · 5 simulated tabletop environments (held-out tasks)solve rateMixed
learn causal processes with delays instead of STRIPS-style operators (VisPred)ExoPredicator · 5 simulated tabletop environments (held-out tasks)solve rateImproved
learn abstractions and parameters instead of manual abstractionsExoPredicator · Grow and Dominosolve rateImproved
learn delay parameters via variational inference instead of a single fixed delay (ablation)ExoPredicator (Manual-d ablation) · 5 simulated tabletop environments (held-out tasks)solve rateImproved
add predicate invention and learning versus initial abstractions only (ablation)ExoPredicator (No invent ablation) · 5 simulated tabletop environments (held-out tasks)solve rateImproved
add Bayesian model selection to LLM-proposed processes (ablation)ExoPredicator (No Bayes ablation) · 5 simulated tabletop environments (held-out tasks)solve rateImproved
add LLM guidance for condition proposals instead of a heuristic (ablation)ExoPredicator (No LLM ablation) · 5 simulated tabletop environments (held-out tasks)solve rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy