paper-with-me

Papers

Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones

2025-11-19 · Ranfei Chen, Ming Chen, Kaifei Wang arxiv

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL methods uniformly allocate policy gradients across denoising steps, implicitly treating all steps as equally important. We challenge this assumption by analyzing trajectories with several step-level metrics: entropy-based uncertainty, Confidence-Margin (CM) uncertainty, and Rate of Entropy Change (RoEC). These reveal structured "zones of confusion": transient spikes in uncertainty and instability that strongly predict final success or failure, while most steps remain stable. We propose Adaptive Trajectory Policy Optimization (ATPO), a lightweight step-selection strategy that dynamically reallocates gradient updates to these high-leverage steps without changing the RL objective, rewards, or compute budget. Using a hybrid RoEC+CM rule, ATPO delivers substantial gains in reasoning accuracy and training stability across benchmarks, showing that exploiting trajectory dynamics is key to advancing dLLM RL.

📄 PDF Abstract BibTeX arXiv:2511.15208

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models

2026-06-04 · Jinyang Zhang, Hongxin Ding, Yue Fang, Weibin Liao 외 arxiv

Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reasoning dynamics remains underexplored. We bridge this gap by demonstra…

Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning

2026-05-08 · Gengyang Li, Zheng-Fan Wu, Siqi Bao, Yunfang Wu arxiv

Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models, but its token-level learning signals remain poorly understood. This work studies their he…

Sluggish and Chemically-Biased Interstitial Diffusion in Concentrated Solid Solution Alloys: Mechanisms and Methods

2023-11-28 · Biao Xu, Haijun Fu, Shasha Huang, Shihua Ma 외

Interstitial diffusion is a pivotal process that governs the phase stability and irradiation response of materials in non-equilibrium conditions. In this work, we study sluggish and chemically-biased interstitial diffusi…

Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models

2026-06-03 · Boyan Han, Yiwei Wang, Yi Song, Yujun Cai 외 arxiv

Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation, enabling them to exploit global context and naturally support format-constrained tasks like parseable JSON or reasoning templ…

Reasoning Structure of Large Language Models

2026-06-02 · Frédéric Berdoz, Luca A. Lanzendörfer, Fabian Farestam, Roger Wattenhofer arxiv

Large reasoning models (LRMs) are often evaluated using metrics such as final-answer accuracy or token count. However, identical scores on these metrics can hide fundamentally different reasoning structures. To address t…