#reinforcement learning
195 papers · 1 filter
Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning
Qiangqiang He, Zhongheng Wu, ZiJian Wang
The paper examines how uniformly assigning credit to all tokens during reinforcement learning for long chain‑of‑thought reasoning can be misleading, and introduces Counterfactual S…
LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts
Ken Ding
The paper introduces LoRA Scaffolded Policy Optimization (LSPO), a sampling-time low-rank adapter method that recovers gradient information for reinforcement learning on difficult…
Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold
Songshuo Lu, Zhi Chen, Yaohua Tang
The paper proposes an expand‑then‑compress framework that builds a diverse set of RL‑trained teacher models and then distills them into a single student model, improving reasoning,…
Hierarchical Latent Reasoning for LLM-based Recommendation
Peiyu Hu, Siying Gu, Weihai Lu +8
The paper introduces HiLaR, a framework that uses hierarchical latent reasoning and layer-aware reinforcement optimization to improve recommendation performance of large language m…
Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO
Xilin Jiang, Riki Shimizu, Sukru Samet Dindar +3
The paper presents Cocktail-Talker, a speech‑language model framework that lets a spoken assistant decide whether to respond, listen, or ignore in multi‑speaker, noisy social conve…
RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation
Shaobo Liu, Feiqiao Mao, Shuaishuai Zhou +4
RefineSVG introduces a closed-loop visual feedback system that lets large multimodal language models iteratively correct SVG code by rendering the output, comparing it to the targe…