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.
Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models
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.
Related stories
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.
arXiv Machine Learning
Sep 3
Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL
The paper introduces DCRL (Divide-and-Conquer RL), a method that recursively decomposes offline goal-conditioned reinforcement learning trajectories into a balanced binary tree. By training values from the leaves up to the root, DCRL avoids noisy max-based backups and reduces bootstrap depth from linear to logarithmic, thereby limiting error accumulation. Experiments on diverse goal-reaching tasks show that DCRL outperforms prior flat offline GCRL methods, achieving a higher average score on the most challenging long-horizon OGBench tasks.
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.
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.
arXiv Machine Learning
4d ago
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
arXiv:2609.36864v1 Announce Type: new Abstract: Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling com...
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.
arXiv Computation and Language
Sep 23
Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models
Informed Masking (IM) is a new technique for aligning Diffusion Large Language Models (dLLMs) with Reinforcement Learning (RL). It identifies a systematic upstream/downstream token structure in dLLM rollouts and shows that masking downstream tokens creates better subproblems for likelihood estimation. When integrated into three state‑of‑the‑art dLLM RL methods on LLaDA‑8B‑Instruct, IM yields up to 2.01%, 8.68%, and 5.77% relative average gains on math and planning benchmarks while improving training stability.
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.
arXiv Machine Learning
Jun 9
CATPO: Critique-Augmented Tree Policy Optimization
arXiv:2606. 08346v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving the reasoning capabilities of large language models (LLMs).
arXiv Machine Learning
Aug 4
Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models
arXiv:2608. 01717v1 Announce Type: new Abstract: Recent reinforcement learning methods for diffusion large language models (dLLMs) commonly rely on on-policy rollouts generated by the target dLLM itself.
arXiv Machine Learning
Aug 31
HARTS: Efficient Agentic Reinforcement Learning for Hybrid-Attention Models over Arbitrary Rollout Trees
HARTS (Hybrid‑Attention RL over Tree Structures) is a new system that jointly plans microbatches, data‑parallel replica assignments, and microbatch‑slot schedules to efficiently train agentic reinforcement learning models with hybrid attention over arbitrary rollout trees. It uses prefix compression and a linear‑time algorithm for chunkwise linear attention to avoid recomputing shared prefixes, enabling activation recomputation and bounded state replay while preserving trajectory‑wise training benefits. In experiments on an Agentic RL workload derived from SWE‑bench tasks, HARTS delivers 4.81–4.87× speedups in forward, backward, and gradient computations across multiple parallel configurations, with numerical differences comparable to baseline self‑rerun variation and a similar reward trend over the first 120 training steps.