AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
The paper introduces Asymmetric Meta-Reflective Self-Distillation (AMR-SD) as a solution for token-level credit assignment in Large Language Models. It addresses the limitations of existing algorithms that apply uniform rewards, leading to credit-assignment bottlenecks. The proposed method enhances performance by using reflective bottlenecks and causal information gain to improve stability and prevent training collapse.
- ▪AMR-SD aims to improve the alignment of Large Language Models for complex reasoning tasks.
- ▪The method incorporates a reflection bottleneck to compress diagnostic signals into concise hints and critiques.
- ▪Experiments show that AMR-SD significantly outperforms existing baselines across various benchmarks.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.18529 |
| Publication time | Tue, 19 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-19T04:04:57.272Z |
| Last seen | 2026-05-19T04:04:57.272Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | xZDyadro7Q7P |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.18529 (cs) [Submitted on 18 May 2026] Title:AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment Authors:Zhenlin Wei, Pu Jian, Yingzhuo Deng, Xiaohan Wang, Jiajun Chai, Zhexin Hu, Wei Lin, Shanbin Zhang, Guojun Yin View a PDF of the paper titled AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment, by Zhenlin Wei and 8 other authors View PDF HTML (experimental) Abstract:The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO apply sequence-level rewards uniformly to all tokens, creating a severe credit-assignment bottleneck.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
