arXiv Computation and Language September 30, 2026 By Kailin Jiang, Lei Liu, Jian Xi, Yangqi Chen, Hui Xu, Hongwei Zhao, Bin Li, Yu Lu, Haibo Shi

AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research

Read the original on arXiv Computation and Language →

AdaTutoRank introduces a setwise document reranker that uses Adaptive Tutoring Optimization (ATO) to provide graded supervision across nine rubric dimensions. By generating hint‑based silver labels, reinforcement rewards, and distillation cues tailored to each rollout’s quality, the method improves credit assignment for individual documents within a set. Experiments on ten benchmarks covering Retrieval‑Augmented Generation (RAG), deep research, and setwise evaluation show that AdaTutoRank achieves superior overall performance while reducing the number of retrieval calls.

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 Computation and Language.

arXiv AI

Aug 13

CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.

By Zhipeng Song, Yizhi Zhou, Xiangyu Kong, Jiulong Jiao, Xuezhou Ye, Chunqi Gao, Xueqing Shi, Yu Wang, Yuhang Zhou, Heng Qi

llms rag

arXiv AI

Sep 2

CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training

arXiv:2609.00892v1 Announce Type: new Abstract: Rubric-based reinforcement learning decomposes open-ended instructions into prompt-specific, flexible rubrics, making it better suited than reinforceme...

By Siyuan Li, Xinxin Song, Chen Ruinian, Jingjing Fan, Tingxiong Xiao, Yangen Hu, Ke Zeng, Jinli Suo

llms reinforcement-learning benchmarks

arXiv AI

Jul 3

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

arXiv:2604. 02091v2 Announce Type: replace-cross Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.

By Yuhang Wu, Xiangqing Shen, Fanfan Wang, Cangqi Zhou, Zhen Wu, Xinyu Dai, Rui Xia

llms rag reinforcement-learning benchmarks

arXiv AI

Aug 6

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.

By Yijun Lu, Rui Ye, Jiajun Wang, Yuwen Du, Tian Jin, Songhua Liu, Siheng Chen

agents reinforcement-learning fine-tuning

arXiv AI

Sep 15

SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution

SkillLift introduces a method for efficiently evolving reusable procedural prompts (skills) in large language model agents by learning a dense rubric that aligns with sparse oracle evaluations. Instead of directly revising skill text based on costly full agent rollouts, the approach decouples skill search from oracle cost through a bilevel optimization framework: an inner loop uses a frozen rubric as a cheap surrogate to guide skill updates, while an outer loop periodically realigns the rubric using a small number of oracle rollouts via rank correlation. Experiments on complex agent task benchmarks demonstrate that SkillLift outperforms existing auto-skill methods while reducing token cost by 40–70% compared to frontier-evolving approaches.

By Haoxiang Kang, Ming Wen

llms agents benchmarks

Hugging Face Trending Papers

Aug 25

RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges

LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or distillation from stron...

llms nlp reinforcement-learning efficiency benchmarks safety

One email a morning, machine-written

Related stories

CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation

CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution

RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges