arXiv Machine Learning August 12, 2026 By Yikai Wang, Chuansai Zhou, Yuhang Zhou, Weiqiang Wu, Cong Wu, Yue Deng, Ben Feng, Mingming Zhu, Beirong Zhou, Zhibin Wang, Sheng Zhong, Chen Tian, Wangze Zhang

MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training

Read the original on arXiv Machine Learning →

arXiv:2608. 10823v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 12

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

Ecdysis is a framework for training runtime harnesses for large language model agents that reduces training time and improves performance. It distinguishes between model‑specific issues and systematic harness deficiencies by aggregating failures across multiple task instances and uses Failure‑Driven Collaborative Refinement to diagnose and correct harness problems. Experiments show up to a 1.84× speedup in harness training and an 18.56% increase in reasoning accuracy.

By Ruiqing Yue, Yu Cui, Zhuoyu Sun, Sicheng Pan, Xianhong Xue, Tingyu Li, Ting Li, Wenzhuo Zhu, Yi Chen, Yifei Liu, Baohan Huang, Zhe Cui, Haibin Zhang, Cong Zuo

llms agents

Hugging Face Trending Papers

Sep 10

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

Ecdysis is a framework for training runtime harnesses for large language model agents more efficiently. It distinguishes between model‑specific issues and systematic harness deficiencies by aggregating failures across multiple task instances and uses Failure‑Driven Collaborative Refinement to diagnose and fix harness problems. The approach reduces training time by up to 1.84× and improves harness reasoning accuracy by 18.56%.

llms agents

arXiv Machine Learning

Sep 30

RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning

arXiv:2609.36813v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. How...

By Chuanpu Liu, Miao Yu, Yikai Cai, Yuanhe Zhang, Zhenhong Zhou, Li Sun, Zuming Jiang, Yufei Guo

llms reinforcement-learning fine-tuning efficiency safety

arXiv AI

Jul 15

Tracing Agentic Failure from the Flow of Success

arXiv:2607. 12747v1 Announce Type: new Abstract: Failure attribution for LLM-based agentic systems, i.

By Samuel Yeh, Yiwen Zhu, Shaleen Deep, Sharon Li

llms agents diffusion

arXiv AI

Jun 30

Diagnosing and Repairing Factual Errors in RAG under Budget Constraints

arXiv:2606. 29377v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models by grounding responses in external evidence, yet real-world deployments remain fragile.

By Soroush Hashemifar, Havva Alizadeh Noughabi, Fattane Zarrinkalam, Ali Dehghantanha

llms rag fine-tuning

arXiv Machine Learning

Jul 2

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

arXiv:2607. 01232v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers.

By Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li, Chung-Yiu Yau, Hongzhou Lin, Mingyi Hong

llms agents reinforcement-learning

One email a morning, machine-written

Related stories

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning

Tracing Agentic Failure from the Flow of Success

Diagnosing and Repairing Factual Errors in RAG under Budget Constraints

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training