ELVA employs a ranking-driven reinforcement learning framework with rule-based rewards, achieving 13.1% improvement on MRBench for multi-grain retrieval.

Yuhan Liu, Pei Fu, Hang Li et al.

ScholarQuest introduces a taxonomy-guided benchmark with over 1000 CS topics, four research intents, and automated answer construction, advancing systematic evaluation of academic search agents.

Tingyue Pan, Mingyue Cheng, Daoyu Wang et al.

This study introduces RecLoop, a closed-loop simulation framework, comparing generative and traditional recommenders; findings show generative models better preserve diversity but still face cocoon effects.

Jiyuan Yang, Gengxin Sun, Mengqi Zhang et al.

Developed a theoretical framework for reranking risk based on DCG variation, validated by experiments on TREC data showing close alignment between predicted and observed deviations.

Debasis Ganguly

CQC-RAG introduces cross-query consistency to enhance robustness in retrieval-augmented generation, outperforming baselines by +4.76 EM on TriviaQA and +9.12 EM on MuSiQue.

Yanjia Sun, Sifan Liu, Jie Shao

miniReranker employs visual cache reuse and interaction sparsity to reduce reranking runtime to <1% with >96% performance, based on Qwen3-VL.

Yingqi Fan, Xuan Lu, Anhao Zhao et al.

Introduces SkillResolve-Bench and SkillResolve, achieving Recall@3 0.766, NDCG@3 0.699, and HSR@3=0, effectively reducing same-capability ambiguity risks.

Jiandong Ding

Popcorn benchmark combines title-aligned full-movie/trailer embeddings with VLM-encoded thumbnails to evaluate visual evidence in multimodal movie recommendation.

Ali Tourani, Fatemeh Nazary, Yashar Deldjoo et al.

Proposes a Constrained Dominant Set (CDS) method for multimodal long-document QA, achieving 66.99 on VisDoMBench, surpassing previous SOTA by 37.1 points.

Ambuj Mehrish, Sebatiano Vascon

Proposes Shallow-RHS, an asymmetric graph architecture for cold-start content recommendation, mapping intrinsic features into a collaborative filtering space for immediate deployment.

Anh Truong, John Trenkle, Yuanbo Chen et al.

StructuredSemanticSearch improves model discovery via structured table retrieval, boosting nugget coverage on 597 queries

Zhengyuan Dong, Renée J. Miller

Aligning Dense Retrievers with LLM Utility via Distillation, UAE improves Recall@1 by 30.59% on QASPER benchmark.

Rajinder Sandhu, Di Mu, Cheng Chang et al.

Research evaluates QPP for selecting the best query variant in RAG pipelines to enhance generation quality.

Negar Arabzadeh, Andrew Drozdov, Michael Bendersky et al.

Introduced TAWin method using WPAUC to optimize RL-based recommenders, enhancing Top-K performance.

Wentao Shi, Qifan Wang, Chen Chen et al.

Proposes a complementarity fusion method for semantic and collaborative views, avoiding global alignment limitations to enhance recommender systems.

Maolin Wang, Dongze Wu, Jianing Zhou et al.

ResRank enhances retrieval efficiency and effectiveness via residual passage compression and end-to-end joint training.

Xiaojie Ke, Shuai Zhang, Liansheng Sun et al.

ECLASS-augmented dense retrieval method achieves 94.3% HitRate@5 in semantic search for electronic components.

Nico Baumgart, Markus Lange-Hegermann, Jan Henze

Diagnosable ColBERT enhances ColBERT model diagnostics by aligning token embeddings to a clinically-grounded reference latent space.

François Remy

LoopCTR enhances CTR prediction through loop scaling, significantly reducing computational costs.

Jiakai Tang, Runfeng Zhang, Weiqiu Wang et al.

CAST framework models semantic-level transitions, achieving 17.6% Recall and 16.0% NDCG gains with 65x training acceleration.

Qian Zhang, Lech Szymanski, Haibo Zhang et al.