Policy and World Modeling Co-Training for Language Agents

arXiv:2606.02388 · cs.LG, cs.AI · Submitted 2026-06-01 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-06-01

Updated: 2026-09-14

Comments: EMNLP 2026 Main Camera Ready

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 56× in this paper · explained in 6 episodes
• World Model — 15× in this paper · explained in 7 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Agentic Task — 6× in this paper · explained in 1 episode
• Actor — 4× in this paper · explained in 3 episodes
• Agentic Tasks — 4× in this paper · explained in 1 episode
• Reinforcement Learning (RL) — 3× in this paper · explained in 25 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adaptive Lookahead — 2× in this paper · explained in 1 episode
• Computational overhead — 2× in this paper · explained in 2 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Action-Conditioned Dynamics — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
• GLM-5: from Vibe Coding to Agentic Engineering
• The Llama 3 Herd of Models
• GPT-4 Technical Report
• World Modelling Improves Language Model Agents
• FireAct: Toward Language Agent Fine-tuning
• World Models
• When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
• Measuring and Narrowing the Compositionality Gap in Language Models
• Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
• Qwen3 Technical Report
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
• From Word to World: Can Large Language Models be Implicit Text-based World Models?
• ZeroSearch: Incentivize the Search Capability of LLMs without Searching
• Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
• Gemini: A Family of Highly Capable Multimodal Models
• Self-Distilled Agentic Reinforcement Learning
• A Survey on Large Language Model based Autonomous 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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks