arXiv Computation and Language
Reinforcement World Model Learning for LLM-based Agents
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jul 21
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
arXiv:2607. 16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments.
arXiv Computation and Language
Sep 10
Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explora...
arXiv AI
Jun 2
Policy and World Modeling Co-Training for Language Agents
arXiv:2606. 02388v1 Announce Type: cross Abstract: Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment.
Hugging Face Trending Papers
5d ago
RLiD: Reinforcement Learning in the Decision Plane for Language Agents and LLMs
Reinforcement learning (RL) has improved the capabilities of large language models (LLMs) across a wide range of tasks. However, token-level RL assigns an action's advantage to the entire generated re...
arXiv AI
Oct 19
Language Models Learn to Improve Language Models
The paper introduces LM2LM, a method that trains large language models (LLMs) to propose improvements for other LLMs using reinforcement learning (RL). It employs a frozen research world model (RWM) to predict the gains of proposals, providing a cheaper surrogate reward, and periodically validates high‑scoring proposals to keep feedback reliable. Experiments across eight LM development environments show that LM2LM enables a Qwen3.8‑27B model to outperform GPT‑6‑sol on held‑out tasks while reducing data‑generation cost by 33%, and it generalizes to unseen model families.
arXiv Computation and Language
Oct 1
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
arXiv:2609.38334v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-mode...