Cover Image

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Zhenlin, Jian, Pu, Deng, Yingzhuo, Wang, Xiaohan, Chai, Jiajun, Hu, Zhexin, Lin, Wei, Zhang, Shanbin, Yin, Guojun
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay
by: Hu, Zhexin, et al.
Published: (2026)

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
by: Lin, Zihan, et al.
Published: (2025)

Rethinking Personalization in Large Language Models at the Token Level
by: Zhang, Chenheng, et al.
Published: (2026)

Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
by: Wang, Zili, et al.
Published: (2026)

$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
by: Zhang, Yaocheng, et al.
Published: (2026)

ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs
by: Chen, Hao, et al.
Published: (2025)

Are Full Rollouts Necessary for On-Policy Distillation?
by: Zhang, Yaocheng, et al.
Published: (2026)

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
by: Wang, Li, et al.
Published: (2026)

TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment
by: Li, Chong, et al.
Published: (2026)

SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
by: Zhang, Qi, et al.
Published: (2026)

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
by: Li, Yu, et al.
Published: (2026)

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
by: Zhang, Kaiyi, et al.
Published: (2026)

Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
by: Wang, Li, et al.
Published: (2026)

AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards
by: Lin, Zihan, et al.
Published: (2025)

Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
by: Hu, Senkang, et al.
Published: (2026)

Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model
by: Li, Chong, et al.
Published: (2025)

Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
by: Jia, Nan, et al.
Published: (2026)

Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
by: Li, Shufan, et al.
Published: (2026)

SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
by: Guo, Xiaojun, et al.
Published: (2025)

SD$^2$: Self-Distilled Sparse Drafters
by: Lasby, Mike, et al.
Published: (2025)

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
by: Lin, Zihan, et al.
Published: (2026)

MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
by: Xu, Zekun, et al.
Published: (2025)

LR^2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems
by: Chen, Jianghao, et al.
Published: (2025)

ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate
by: Lafuente-Mercado, Rodney
Published: (2026)

SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT
by: Cho, Cheol Jun, et al.
Published: (2023)

RTMC: Step-Level Credit Assignment via Rollout Trees
by: Wang, Tao, et al.
Published: (2026)

From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
by: Xia, Siyu, et al.
Published: (2025)

CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling
by: Liu, Dengcan, et al.
Published: (2026)

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
by: Sun, Jingbo, et al.
Published: (2026)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
by: Lu, Xiaodong, et al.
Published: (2026)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
by: Yue, Chuhuai, et al.
Published: (2025)

RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
by: Fu, Yuqian, et al.
Published: (2025)

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
by: Jian, Pu, et al.
Published: (2025)

Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing
by: Kang, Jeongwoo, et al.
Published: (2024)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
by: Zhang, Xiang, et al.
Published: (2025)

MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
by: Liu, Jiarui, et al.
Published: (2026)

Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
by: Wei, Jingxuan, et al.
Published: (2024)

A Data-Driven Based Concurrent Coupling Approach for Cryogenic Propellant Tank Long-term Pressure Control Predictions
by: Cheng, Qiyun, et al.
Published: (2024)

Exact Is Easier: Credit Assignment for Cooperative LLM Agents
by: Chen, Yanjun, et al.
Published: (2026)

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
by: Chen, Xinzhu, et al.
Published: (2026)