Search-G1 is a reward framework that encourages language agents to retrieve external information only when necessary and to ground their answers in that evidence. It uses two hidden‑state readouts—one predicting whether a closed‑book answer suffices and another measuring sensitivity to evidence deletion—to calibrate retrieval necessity and evidence reliance. The reward system gates evidence credit by necessity, rewards sufficient direct answers, and penalizes redundant searches, all without requiring costly annotations or LLM‑judge inference.
By Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang, Junming Zhang, Ranjie Duan, Qiaolin Xia, Hao Wang, Yu Lu, Haibo Shi, Xingjun Ma
arXiv:2609.39026v1 Announce Type: new
Abstract: Deep Research agents synthesize evidence into cited reports, yet a well-cited report can still reach a misleading conclusion. Citation correctness chec...
By Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Chaoyang Mei, Fanlin Meng, Lulu Wang, Ziming Yu, Junxi Yin
The paper critiques current agent memory benchmarks that rely on downstream QA accuracy, arguing they conflate memory correctness with retrieval and generation quality, leading to misleading results. It introduces FEB-30, a new benchmark of 30 fact‑evolution trajectories across six diagnostic categories and three difficulty levels, generated automatically to provide deterministic ground truth. Using FEB-30, the authors show a significant divergence between intrinsic and extrinsic evaluations, revealing that a representative memory system correctly classifies memory operations only 20% of the time—an error invisible to traditional QA metrics.
By Sebastian-Antonio Toma, Jean de Kernier, Mike Ply, Oliviu Matei
arXiv:2609.10092v1 Announce Type: cross
Abstract: Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate be...
By Yingqian Wu, Jingcong Liang, Siyuan Wang, Zhenfei Yin, Philip Torr, Junchi Yu, Zhongyu Wei
arXiv:2608. 02011v2 Announce Type: replace Abstract: Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspecting them.
By Daeyoung Roh, Donghee Han
arXiv:2609.14412v1 Announce Type: new
Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmar...
By Radin Hamidi Rad, Amin Bigdeli, Negar Arabzadeh, Sajad Ebrahimi, Charles L. A. Clarke, Benjamin C. M. Fung, Ebrahim Bagheri
The paper investigates why large language models (LLMs) sometimes give outdated answers even when recent evidence is available through web search. By creating temporal facts that changed after the models’ training cutoffs, the authors evaluate a proprietary model with deployed search and six open-weight models with controlled retrieval. They find that models often rely on search snippets without opening source pages, leading to more outdated answers and unfaithful citations, and that even when retrieved evidence influences internal predictions, the final answer may still favor outdated information.
By Owen Walters, Lihu Chen, Francesca Toni
The paper introduces QEMem, a framework that rethinks how large language model agents use long‑term memory by constructing query‑specific evidence sets rather than relying on individual memory relevance. QEMem combines query‑guided discovery, source‑grounded reification into structured ViewCards, and sufficiency‑guided refinement to assemble comprehensive evidence from multiple memory granularities. Experiments show that QEMem achieves 91.43% LLM‑judge accuracy on LoCoMo with Claude Opus 4.5, surpassing leading baselines by significant margins and improving evidence coverage for cross‑session queries.
By Shixuan Li, Wei Yang, Peiyu Zhang, Anzhe Cheng, Heng Ping, Xiaole Zhang, Jesse Thomason, Xuezhe Ma, Yue Zhao, Paul Bogdan
The paper introduces Research Attention Prediction (RAP), a benchmark designed to evaluate large language model (LLM) agents’ ability to infer changes across entire research fields from limited evidence gathered during online scholarly searches. RAP is built on a local search environment comprising 356,357 dated arXiv papers and includes two evaluation sets: a Core set of 2,160 questions covering 54 AI/ML fields and an Extended set spanning 269 fields. Experiments show that while search improves agents’ recognition of recent changes, their forecasting of future shifts remains limited or even negative, indicating that LLM agents can detect some recent developments but struggle to reliably anticipate future research activity.
By Yingqian Wu, Jingcong Liang, Shengbin Yue, Siyuan Wang, Zhenfei Yin, Junchi Yu, Zhongyu Wei
arXiv:2609.01294v1 Announce Type: new
Abstract: Deep-research agents answer complex questions by interacting with search and browsing tools, yet they often search along a single evolving trajectory....
By Ruochen Zhou, Zhengyu Chen, Luan Zhang, Siyang Gao, Yee Whye Teh, Shiqi Chen
The paper introduces SEEDS, a preview-guided evidence admission framework that allows search agents to selectively admit retrieved documents into their reasoning process. SEEDS exposes lightweight previews of candidates and lets the agent decide which and how many to fully inspect based on its current reasoning state, enabling arbitrary subset selection rather than fixed or rank-based policies. Experiments on nine knowledge-intensive QA benchmarks show that SEEDS improves search effectiveness and reduces full-evidence consumption compared to traditional retrieval prefixes.
By Jiajin Liu, Chenxi Xu, Dongzhe Fan, Yuanfu Sun, Qiaoyu Tan
JevGPT is a dual‑system architecture for autonomous research that combines fast evidence processing (System One) with deliberative research planning (System Two). System One quickly locates and evaluates relevant passages, while System Two sets evidence objectives and integrates findings into subsequent research steps. Experiments on question answering and document ranking demonstrate that JevGPT outperforms comparable agents, achieving faster completion, lower cost, and broader source coverage.
By Yasheng Sun, Yanning Dai, Yimeng Chen, Nanbo Li, Firas Laakom, Yifan Xu, Piotr Pi\k{e}kos, Mateusz Ostaszewski, Wenyi Wang, Cheng Luo, Yuhui Wang, J\"urgen Schmidhuber