AI Paper Atlas

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

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

Zhenhao Chen, Yongqiang Chen, Chenxi Liu, Junchi Yu, Xiangchen Song, Zijian Li, Jialin Li, Philip Torr, Bo Han, Kun Zhang

ICML 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 0 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
remove selection bias via balanced sampling (ablation)LLM agents, Agent mode · CausalGamesurvival rate (%): 64.9 -> 74.4Improved
remove selection bias via balanced sampling (ablation)LLM agents, Prompt mode · CausalGamesurvival rate (%): 64.6 -> 72.4Improved
increase reasoning effort from High to XHigh (ablation)GPT-5.5, Agent mode · CausalGamesurvival rate (%): 68.4 -> 65.1Hurt
enable thinking mode (ablation)DeepSeek-V3.2 · CausalGamesurvival rate (%): 61.7 -> 59.9Hurt
use agentic ReAct framework instead of single-turn promptingtop-performing LLMs · CausalGamesurvival rate (%): up to +5.7% (DeepSeek-V4-Pro)Mixed
use OpenCode coding agent instead of ReAct5 LLMs · CausalGamesurvival rate (%): average +6.9%Improved
give a locally optimal design as historyLLM agents · Antenna Trapsurvival rate (%): not givenImproved
move from Antenna Trap to harder Deployment Zone TrapLLM agents · CausalGamesurvival rate (%): not givenHurt
simple non-LLM baselines versus full agentsUniform High / Random / Default · bias-heavy scenariossurvival rate (%): 49.0%-57.5% averageMixed

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