arXiv Computation and Language October 16, 2026 By Yingtao Luo, Kangyi Zhao, Shiyi Du, Yubo Li

Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval

Read the original on arXiv Computation and Language →

The paper introduces AURA, a framework that supervises intermediate reasoning states to better separate relevant documents from hard distractors and trains a lightweight utility estimator to adapt reasoning depth during inference. On the BRIGHT benchmark, AURA-4B achieves an average nDCG@10 of 34.7 while using only 2.8 reasoning steps and 96 generated tokens per query, and adaptive stopping reduces latency from 4.6 to 0.76 seconds compared to full-trajectory reasoning. Experiments on MS MARCO indicate that this specialization does not significantly harm conventional in-domain retrieval performance.

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

Jun 15

Implicit Reasoning for Large Language Model-based Generative Recommendation

arXiv:2606. 14142v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge.

By Yinhan He, Liam Collins, Bhuvesh Kumar, Jundong Li, Neil Shah, Donald Loveland

llms rag safety

arXiv AI

Sep 15

Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings

arXiv:2609.15296v1 Announce Type: new Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Rece...

By Mingzhou Jiang, Peixi Wu, Hang Cheng, Yunhao Zhou, Biao Yang, Wei Yuan, Yun Li, Fan Yang, Wenwu Ou, Honghui He

rag efficiency multimodal benchmarks

arXiv Computation and Language

3d ago

MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation

arXiv:2610.29792v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves the performance of Large Language Models (LLMs) by retrieving external knowledge. Recently, some RAG meth...

By Xinze Li, Dingwen Zhang, Zhenghao Liu, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun

llms rag benchmarks

arXiv AI

Aug 17

Retrieval Grounding Latent Reasoning for Dense Retrieval

arXiv:2608. 14107v1 Announce Type: new Abstract: Reasoning-intensive retrieval requires text representations to capture not only semantic similarity, but also the reasoning needed to determine relevance under a given retrieval instruction.

By Gang Zhou, Xiongxi Yu, Hu Tian, Yang Wei, Lu Pan, Ke Zeng, Shibiao Xu, Xiaolong Zheng

rag efficiency benchmarks

arXiv AI

Aug 6

InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval

arXiv:2608. 04761v1 Announce Type: cross Abstract: Self-improving agents accumulate reusable insights from prior trajectories, making retrieval increasingly important for turning accumulated experience into actionable guidance.

By Tsz Ting Chung, Jiangnan Li, Jie Zhou, Mo Yu

rag agents benchmarks

arXiv AI

Jun 9

Generative Reasoning Re-ranker

arXiv:2602. 07774v5 Announce Type: replace-cross Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge.

By Mingfu Liang, Yufei Li, Jay Xu, Kavosh Asadi, Xi Liu, Shuo Gu, Kaushik Rangadurai, Frank Shyu, Shuaiwen Wang, Song Yang, Zhijing Li, Jiang Liu, Mengying Sun, Fei Tian, Xiaohan Wei, Chonglin Sun, Jacob Tao, Shike Mei, Wenlin Chen, Santanu Kolay, Sandeep Pandey, Hamed Firooz, Luke Simon

llms rag nlp reinforcement-learning fine-tuning benchmarks

One email a morning, machine-written

Related stories

Implicit Reasoning for Large Language Model-based Generative Recommendation

Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings

MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation

Retrieval Grounding Latent Reasoning for Dense Retrieval

InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval

Generative Reasoning Re-ranker