Hugging Face Trending Papers June 3, 2026

Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models

Read the original on Hugging Face Trending Papers →

Diffusion large language models (dLLMs) generate responses by iteratively unmasking and revising many positions in parallel. This process leaves a rich denoising trace depicting which tokens become confident, which remain unstable, and when commitments form.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 21

Trace-Based On-Policy Distillation for Masked Diffusion Language Models

arXiv:2607. 16872v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation.

By Haolin Ren, Ziyang Huang, Chenhao Yuan, Jun Zhao, Kang Liu

llms diffusion reinforcement-learning fine-tuning efficiency benchmarks

arXiv Machine Learning

Jul 17

Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning

arXiv:2607. 14171v1 Announce Type: new Abstract: Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes.

By Bowei He, Yankai Chen, Xiaokun Zhang, Xue Liu

llms agents reinforcement-learning benchmarks

Hugging Face Trending Papers

Jun 24

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentence- or solution-level search can be computationally expensive and hard to train end-to-end. We introduce Local Branch Routing (LBR), a token-level test-time scaling framework that expands a small local lookahead tree, forwards all sampled branches through the language model, and uses a lightweight router to select the depth-1 subtree to commit.

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 16

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models

arXiv:2602. 00482v2 Announce Type: replace Abstract: Reinforcement learning (RL)-based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that frequently share long token prefixes.

By Jiarui Zhang, Yuchen Yang, Ran Yan, Zhiyu Mei, Liyuan Zhang, Daifeng Li, Wei Fu, Jiaxuan Gao, Shusheng Xu, Yi Wu, Binhang Yuan

llms reinforcement-learning efficiency

arXiv AI

Jul 20

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.

By Xintong Li, Sha Li, Yuwei Zhang, Changlong Yu, Rongmei Lin, Hongye Jin, Shuyi Guan, Xin Liu, Linwei Li, Qingyu Yin, Jingbo Shang

llms agents reinforcement-learning

arXiv AI

Jun 10

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

arXiv:2606. 11119v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.

By Heming Zou, Qi Wang, Yun Qu, Yuhang Jiang, Lizhou Cai, Yixiu Mao, Ru Peng, Xin Xu, Weijie Liu, Kai Yang, Saiyong Yang, Xiangyang Ji

llms agents reinforcement-learning benchmarks

Related stories

Trace-Based On-Policy Distillation for Masked Diffusion Language Models

Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning