CORTEXA
← Browse
arxivcs.CLcs.AI2026-06-29

ARKD: Adaptive Reinforcement Learning-Guided Bidirectional KL Divergence Distillation for Text Generation

Zilong Liu, Xuewen Zhang, Jinrui Xing, Juyi Qiao, Huiyong Wang, Junming Jiao

Knowledge distillation (KD) is a key technique for compressing Large Language Models (LLMs), yet methods relying on a single KL objective often fail to balance primary distribution fitting with long-tail probability modeling, limiting both generation quality and generalization. To address this, we analyze the complementary roles of forward and reverse KL divergence (FKL/RKL) in distribution alignment from theoretical and empirical perspectives. We then propose a reinforcement-learning-based adaptive KL-weighted distillation framework, in which a policy network dynamically assigns weights to FKL and RKL based on teacher-student distributional characteristics, guided by immediate reward signals to achieve dual alignment on principal and long-tail modes. Extensive experiments demonstrate consistent improvements across Rouge-L and BertScore metrics, surpassing greedy heuristics by 0.4-0.6 points and outperforming other baseline methods on diverse benchmarks.

View free PDFSource page

Related papers

arxivcs.CLcs.AI2026-07-21

Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards

Xuefeng Jin, Jiashuo Zhang, Teng Cao, Bin Yang

Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG). However, existing studies rely primarily on prompt engineering or supervised fine-tuning, while systematic research on reinforcement learning (RL) post-…

View free PDFSource page
arxivcs.CLcs.AI2026-07-31

Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation

Yongshi Ye, Biao Fu, Chongxuan Huang, Yidong Chen, Xiaodong Shi

Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains. Inspired by human translators' ability to adapt reasoning effort based on difficulty, we propose TwT (Translation with Thought), a resource-rational fra…

View free PDFSource page
arxivcs.AIcond-mat.mtrl-scics.CLcs.LG2026-07-01

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

Subhadeep Pal, Shashwat Sourav, Tirthankar Ghosal, Markus J. Buehler

Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models often produce fluent but weakly traceable responses to open-ended materials design problems, making…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-07

Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design

Alexander Rombach, Chantale Lauer, Nijat Mehdiyev

Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data. Reinforcement learning (RL) can optimize beyond this ceiling using external…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-08

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang, Hoang Anh Duy Le, Zhaozhuo Xu, Guanchu Wang, et al.

Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rely on uniform credit assignment, broadcasting the same advantage to all tokens regardless of their di…

View free PDFSource page
arxivcs.LGcs.AIcs.CLcs.OS2026-07-19

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning

Ryan Xu, Atlas Zhao, David Bao, Frank Du

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrain…

View free PDFSource page