Software World Models: From Consequence Prediction to Decision Value
cs.LG, cs.AI, cs.SE
Submitted: 2026-10-04
Updated: 2026-10-04
Comments: 29 pages, 9 figures, 13 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- CWM: An Open-Weights LLM for Research on Code Generation with World Models
- Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
- World Modelling Improves Language Model Agents
- World Models
- Training Agents Inside of Scalable World Models
- Let Your Graph Do the Talking: Encoding Structured Data for LLMs
- BUMP: A Benchmark of Reproducible Breaking Dependency Updates
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- SWE-World: Building Software Engineering Agents in Docker-Free Environments
- The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
- SWE-smith: Scaling Data for Software Engineering Agents
- Qwen-AgentWorld: Language World Models for General Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks