Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
cs.LG
Submitted: 2026-06-04
Updated: 2026-11-06
Terminology
Sources
- Is Conditional Generative Modeling all you need for Decision-Making?
- Combating the Compounding-Error Problem with a Multi-step Model
- Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
- The Llama 3 Herd of Models
- Mastering Diverse Domains through World Models
- Classifier-Free Diffusion Guidance
- Vid2World: Crafting Video Diffusion Models to Interactive World Models
- Policy-Guided Diffusion
- Planning with Diffusion for Flexible Behavior Synthesis
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Transformers are Sample-Efficient World Models
- Representation Learning with Contrastive Predictive Coding
- Hyperparameter Selection for Offline Reinforcement Learning
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis