paper-with-me

Papers

Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning

2026-06-14 · Yu Li, Shu Hong, Tian Lan arxiv

Reinforcement learning from verifiable rewards assigns a single scalar to each rollout, leaving token-level credit assignment underspecified in long reasoning traces. On-policy self-distillation addresses this by letting the same model act as a teacher conditioned on privileged information, producing a dense per-token signal. But the common choice of a ground-truth answer is only an endpoint cue: on terse-answer tasks, the teacher falls silent at the intermediate positions where path-level guidance matters most. We propose Hindsight Self-Distillation (HSD), which conditions the teacher on a successful peer rollout drawn from the current training group. Such a peer is an exact sample from the success-conditioned policy, requiring no additional sampled rollouts. By providing a full successful continuation rather than only the final answer, the resulting credit signal concentrates at the divergence position between a failed rollout and a successful peer. Across Qwen3-8B and Qwen3-32B on math and code benchmarks, HSD obtains the best result against GRPO variants and on-policy distillation baselines, with the largest gains on terse-answer tasks such as AIME.

📄 PDF Abstract BibTeX arXiv:2606.15576

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

2026-06-17 · Yingyu Shan, Yuhang Guo, Zihao Cheng, Zeming Liu 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradien…

Reinforcement LearningKnowledge Distillation

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation

2026-05-12 · Sijia Li, Yuchen Huang, Zifan Liu, Yanping Li 외 arxiv

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment i…

Reinforcement LearningMathematical Reasoning

UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation

2026-06-28 · Songjun Tu, Chengdong Xu, Qichao Zhang, Yiwen Ma 외 arxiv

Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. Thi…

Reinforcement Learning

Agentic Reinforcement Learning with Self-Distilled Reward Shaping

2026-08-04 · Ranxu Zhang, Guinan Chen, Chenshaodong, Jinghao Lin 외 arxiv

Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged…

Reinforcement Learning

IQNN-CS: Interpretable Quantum Neural Network for Credit Scoring

2025-10-16 · Abdul Samad Khan, Nouhaila Innan, Aeysha Khalique, Muhammad Shafique arxiv

Credit scoring is a high-stakes task in financial services, where model decisions directly impact individuals' access to credit and are subject to strict regulatory scrutiny. While Quantum Machine Learning (QML) offers n…

Quantum Machine Learning