AI Paper Atlas

Research map / Large language models / Agents, code and math

Code World Models for General Game Playing

Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla, Xinghua Lou, Carter Wendelken, Zun Li, Antoine Dedieu, Marc Lanctot, Atil Iscen, John Schultz, Marcus Chiam, Ian Gemp and 3 more

ICLR 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 26 citations (OpenAlex)

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
use tree-search refinement of CWM instead of conversation refinement (ablation)LLM-synthesized CWM · perfect information gamesCWM accuracyNo clear effect
synthesize a value function for MCTS (ablation)CWM + ISMCTS · Bargaining (CWM agent as player 1)payoffImproved
apply synthesized value functions (ablation)CWM + ISMCTS · other imperfect information gamesplaying performanceNo clear effect
use hidden history inference instead of hidden state inference (ablation)CWM + ISMCTS · imperfect information gamesinference accuracyImproved
go from open deck to closed deck CWM synthesis (ablation)CWM agent · Bargainingtest inference accuracy: 1.0000 -> 0.67359Hurt
go from open deck to closed deck CWM synthesis (ablation)CWM agent · Gin rummytest inference accuracy: 0.5376 -> 0.09523Hurt
go from open deck to closed deck CWM synthesis (ablation)CWM agent · game play vs Gemini 2.5 Prowin/payoffMixed
use CWM + MCTS planning instead of LLM as direct policyGemini 2.5 Pro · Backgammonwin rate: 1.00 (100/100 Gemini forfeits)Improved
use CWM + MCTS planning instead of LLM as direct policyGemini 2.5 Pro · Tic-tac-toewin/draw rate: 0.05 win, 0.95 drawNo clear effect
use CWM + ISMCTS instead of Gemini policyGemini 2.5 Pro · Hand of wargame outcomeHurt
learn Gin rummy rules from trajectoriesCWM synthesis · Gin rummytest transition accuracy: 0.7455Hurt

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