The paper investigates modular entity disambiguation by separating candidate retrieval from entity selection. It compares sparse retrieval (BM25), Web KB search, and a dense retriever, all paired with large language model selectors. Results show that a training‑free BM25 retriever combined with an LLM selector achieves state‑of‑the‑art performance on the ZELDA benchmark, and the modular approach enables abstention when retrieval fails.
By Fina Polat, Daniel Daza, Pengyu Zhang, Klim Zaporojets, Paul Groth
arXiv:2610.06650v2 Announce Type: replace
Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right en...
By Mohamed Chenene, Carlos Rosas-Hinostroza, Anastasia Stasenko, Shani Evenstein Sigalov, Pierre-Carl Langlais
arXiv:2609.36695v1 Announce Type: new
Abstract: Self-distillation turns knowledge distillation into a closed learning loop and offers a path toward recursive self-improvement. Without an external tea...
By Rui Wang, Ruijie Wang, Bo Chen, Jiangxuan Long, Yingyu Liang
arXiv:2604. 23336v3 Announce Type: replace-cross Abstract: Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs.
By Teng Chen, Sheng Xu, Feixiang Guo, Xiaoyu Wang, Qingqing Gu, Hongyan Li, Luo Ji
arXiv:2602.02518v3 Announce Type: replace-cross
Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many knowledge sources on the Web, such as sc...
By Yuyang Bai, Zhuofeng Li, Ping Nie, Jianwen Xie, Yu Wang, Yu Zhang
arXiv:2607. 24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision.
By Junlin Liu, Jiangwang Chen, Zixin Song, Shuaiyu Zhou, Chunji Lv, Hank Wu, Kailin Jiang, Jinyang Wu, Bohan Yu, Chenxi Zhou
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
By Haoze Wu, Chuqiao Kuang, Tianyi Zhuang, Xiaoguang Li
arXiv:2608.22762v1 Announce Type: new
Abstract: Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-...
By Chenhui Liu, Jianpeng Zhou, Jiahai Wang
arXiv:2610.24899v2 Announce Type: replace-cross
Abstract: While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables...
By Soyoung Yoon, Peiran Xu, Han Wang, Ruofan Wu, Xiaodong Yu, Feng Yan, Mohit Bansal, Debiao Li, Seung-Won Hwang, Yuxiong He, Zhewei Yao
arXiv:2608.28978v1 Announce Type: new
Abstract: Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption th...
By Theo Rusu, Sourena Khanzadeh, Manar Alalfi
D‑Skill is a framework that distills the behavioral advantage of a large language‑model teacher into an interpretable natural‑language skill document, using only paired rollouts and no weight updates. The skill is constructed offline from fixed trajectories, then provided to a smaller student model at inference time. Across benchmarks such as SpreadsheetBench‑Verified, ALFWorld, and chess puzzles, D‑Skill closes 75‑95% of the teacher‑student performance gap and reduces inference cost by 5.7×–8.3× compared to the teacher.
By Shuo Yuan, Dacheng Li, Joseph E. Gonzalez
The paper introduces ResMem, a method that transforms retrieved knowledge into a parametric memory for large language models. By using the LLM as an offline teacher that reads retrieved text, ResMem learns an additive logit residual, avoiding large token storage and improving question‑answering performance. Experiments on Wikipedia and five QA datasets show significant storage savings and higher token F1 scores compared to k‑NN baselines.
By Changjiang Han, Bowei He, Ye Yuan, Weixu Zhang, Haolun Wu, Xue Liu, Jikun Kang