Research map / Multi-agent systems and games / Human-AI and goal-conditioned
World Models in Pieces: Structural Certification of General Agents
Yikai Lu, Yifei Wu, Xinyu Lu, Tongxin Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use the transition-local certified bound instead of the prior uniform bound | world-model recovery error bound · Key-door grid world, n=100 | upper bound on recovery error (%): 5.31 -> 0.67 | Improved |
| filter to certified transitions rather than using all entries | recovered world model · Grid world, mean absolute recovery error vs goal depth n | mean absolute recovery error | Improved |
| use smaller failure rate delta for certification (ablation) | certified filtering · Grid world, delta in {0.01,0.10,0.20} | mean absolute recovery error | Improved |
Closest papers by meaning
- General agents need world models (ICML 2025 · similarity 0.88)
- WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment (NeurIPS 2024 · similarity 0.87)
- Imperfect World Models are Exploitable (NeurIPS 2026 · similarity 0.85)
- Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback (NeurIPS 2026 · similarity 0.85)
- WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents (NeurIPS 2025 · similarity 0.85)
- MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems (ICML 2026 · similarity 0.85)
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.
