d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models (2026.acl-long)
Copied to clipboard
Leyi Pan, Shuchang Tao, Yunpeng Zhai, Zheyu Fu, Liancheng Fang, Minghua He, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen
| Challenge: | Existing RL methods suffer from reliability bottlenecks due to reward sparsity and intractable computations . d-TreeRPO provides fine-grained and verifiable step-wise reward signals . |
| Approach: | They propose a reliable reinforcement learning framework for diffusion large language models that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards. |
| Outcome: | The proposed framework outperforms baseline models and achieves significant improvements across reasoning benchmarks. |
Similar Papers
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reinforcement learning (RL) require a large sample size to be implemented. |
| Approach: | They propose a memory-efficient RL algorithm that maximizes a lower bound of the ELBO-based objective. |
| Outcome: | Experiments show that BGPO outperforms previous RL algorithms for diffusion large language models in math problem solving, code generation, and planning tasks. |
Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion Large Language Models (dLLMs) offer parallel decoding and bidirectional context modeling . aligning dLLms with reinforcement learning (RL) remains a challenge . |
| Approach: | They propose a variational framework that reformulates RL for dLLMs as a distribution matching problem. |
| Outcome: | The proposed framework reformulates RL for dLLMs as a distribution matching problem. |
Pseudo-Likelihood Training for Reasoning Diffusion Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are the backbone of modern natural language processing and are powering applications ranging from code generation to autonomous agents. |
| Approach: | They propose a framework that uses pseudo-likelihood based objective for alignment of diffusion based language models (dLLMs). |
| Outcome: | The proposed method matches or surpasses dLLM training baselines on various coding and mathematical reasoning benchmarks. |
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing dLLMs rely on fixed denoising schedules and cannot learn efficient unmasking orders. |
| Approach: | They propose a framework that transforms dLLM decoding into a trajectory-aware policy . it uses a confidence-gated denoising strategy that decides which tokens to unmask . |
| Outcome: | The proposed model can learn which tokens to unmask and how many to unmak per step . it can learn the output quality and efficiency of the decoding path itself . |
From log š to š: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight (2026.acl-long)
Copied to clipboard
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Cong Qin, Zekai Shao, Binbin Zheng, Lu Pan, Ke Zeng
| Challenge: | Standard algorithms for Large Language Models (LLMs) enforce stability via "hard clipping" but relying on log-probability gradient yields divergent weights as probabilities vanish, destabilizing LLM training. |
| Approach: | They propose a decoupled gradient policy optimization that uses a decay mechanism to decouple the probability of a boundary token. |
| Outcome: | The proposed algorithm outperforms baselines on various mathematical benchmarks. |
AG-GRPO: Answer-Guided GRPO for Masked Diffusion Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work on large language models (LLMs) has emphasized not only final-answer accuracy but also reliability of reasoning on challenging tasks. |
| Approach: | They propose an answer-guided group-relative policy optimization for masked diffusion language models which generates text through iterative mangled token restoration. |
| Outcome: | The proposed approach improves over pretrained dLLMs and prior RL methods across mathematics, puzzle-solving, and code-generation benchmarks. |
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization (2026.findings-acl)
Copied to clipboard
Yangyi Fang, Jiaye Lin, Xiaoliang Fu, Cong Qin, Haolin Shi, Chaowen Hu, Lu Pan, Ke Zeng, Xunliang Cai
| Challenge: | Existing methods for reinforcement learning with verifiable rewards are limited by the complexity of the problem and the complexity. |
| Approach: | They propose a theoretically-grounded dual-pronged optimization framework for reinforcement learning with verifiable rewards that compensates for gradient attenuation of high-confidence correct actions while utilizing entropy changes as computable indicators to stabilize excessive update magnitudes. |
| Outcome: | The proposed framework compensates for gradient attenuation of high-confidence correct actions while utilizing entropy changes as computable indicators to stabilize excessive update magnitudes. |
Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing unified optimization strategies overlook the statistical conflict between these distinct gradient signals. |
| Approach: | They propose a framework to reduce bias-variance trade-offs in Large Language Models . they propose DYPO, which leverages intrinsic group dynamics to significantly reduce RL gradient variance . |
| Outcome: | The proposed framework outperforms traditional pipelines on reasoning benchmarks and out-of-distribution tasks. |
G2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in reasoning-centric large language models (LLMs) have significantly expanded the performance boundaries of LLMs, showcasing the immense potential of reasoning-enhanced models. |
| Approach: | They propose an adaptive algorithm that injects ground-truth reasoning steps into roll-out trajectories to compensate for SLMsā inherent weaknesses. |
| Outcome: | Experiments on mathematical reasoning and code-generation benchmarks confirm that G2RPO-A substantially outperforms vanilla GRPO. |
Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration (2026.findings-acl)
Copied to clipboard
Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu
| Challenge: | CadLLM is a plug-and-play model-agnostic with KV caching based dLLMs. |
| Approach: | They propose a lightweight adaptive method that can control the generation block size, step size, and threshold based on the average confidence score of unmasked tokens. |
| Outcome: | The proposed method can increase throughput by up to 1.1-2.28x over the state-of-the-art model with competitive accuracy. |