arXiv AI

Iris: Climbing to the Search Frontier

The paper introduces Iris-mini and Iris-pro, two search agents trained at 35B and 397B parameter scales. They use a novel data pipeline that constructs reverse‑engineered multi‑hop queries from web hyperlinks, filters trajectories, and alternates supervised fine‑tuning with reinforcement learning in a process called SFT‑RL climbing. Evaluations on several benchmarks show that, with inference‑time context management, the agents achieve the best open‑source results in their parameter ranges.

arXiv AI
Aug 24

Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration

Clarify-Then-Search is a benchmark that tests whether large language models can ask clarification questions to improve the usefulness of deep search results. It uses 518 real-world query pairs from Baidu, where each intent query is paired with an underspecified version. The evaluation involves a clarifier asking up to three questions, a user answerer providing only explicit information, and a rewriter generating a new query that is then searched; performance is measured by a weighted nugget-recall score.

By Deqiang Huang, Jingbo Zhou, Xinjiang Lu, Tong Xu, Hua Wu, Enhong Chen
arXiv Computation and Language
4d ago

Benchmarking Hybrid Deep Research Across Database Querying and Web Search

arXiv:2609.09410v1 Announce Type: new Abstract: While autonomous agents have made significant strides in "deep research" by iteratively navigating the open web to synthesize information, real-world p...

By Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li, Yuxiong He, Zhewei Yao
arXiv AI
Jul 31

SimpleWikiSearch: A Clean Offline Wikipedia Environment for Agentic Search

arXiv:2607. 26070v1 Announce Type: cross Abstract: Large language model (LLM)-based agentic search systems are often evaluated as if the underlying LLM were the only component that matters, yet their measured performance also depends on the surrounding search environment: the Wikipedia snapshot, preprocessing pipeline, chunking policy, retrieval backend, tool schema, observation format, and answer submission rule.

By Guanming Xiong, Penghui Zhang
arXiv Computation and Language
3d ago

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

OpenResearcher is a fully open, reproducible pipeline for generating long‑horizon deep research trajectories that interleave search, evidence aggregation, and multi‑step reasoning. It decouples corpus bootstrapping from trajectory synthesis and runs the search‑and‑browse loop offline using three browser primitives over a 15M‑document corpus. Using GPT‑OSS‑120B as a teacher, the pipeline produced over 97K trajectories, enabling a 30B‑A3B model to achieve 54.8% accuracy on BrowseComp‑Plus and providing insights into pipeline design through controlled analysis.

By Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen
arXiv AI
2d ago

MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG

MOSAIC is a training‑free framework that adapts Graph Retrieval‑Augmented Generation (GraphRAG) to each query by converting query‑specific evidence needs into a bounded policy over seed selection, traversal, stopping, and evidence selection. It keeps the corpus graph, indexes, scoring, grounding, and answer generation shared, while an LLM analyzer tailors the exploration strategy per query. On GraphRAG‑Bench, MOSAIC improves answer correctness by over 5 points on Medical and 4 points on Novel, achieves high evidence recall and context relevancy, and reduces path and evidence evaluations compared to fixed policies.

By EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, Minsang Song, Hyeongjun Jang, Junyoung Youn
arXiv AI
Sep 1

post-graph-rag: A PostgreSQL-Native Bi-Temporal Graph RAG Engine with Temporal Grounding at Synthesis

post-graph-rag is an open‑source PostgreSQL‑native engine that unifies chunks, embeddings, a canonical entity graph, and community summaries in a single database, using pgvector for search and edge tables for traversal. It validates extraction output—rejecting vague predicates, normalising predicates, resolving entities to unique vertices, and flagging negations—before writing, and employs a bi‑temporal layer to record when a relation held and when the system believed it, superseding incompatible earlier assertions. In benchmarks against LightRAG, it builds denser, more queryable graphs and achieves higher scores on LongMemEval, largely due to its temporal grounding in prompts.

By Chandan Rajah
arXiv Computation and Language
Sep 1

Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents

Agent Zero Memory is a provenance‑aware long‑term memory system for large language model agents that distills user interactions into three parallel memory structures: an episodic timeline, an associative entity‑event knowledge graph, and a semantic, citation‑locked hierarchical documentary memory. Retrieval is performed via an intent gate, source router, and concurrent searches across the three systems, producing integrated, cited answers that exclude fabrication and require evidence the reader has opened. The system achieves state‑of‑the‑art performance on LongMemEval (95.60%) and LoCoMo (93.60%) while offering a favorable accuracy‑cost‑latency trade‑off across multiple backbone LLMs.

By Ming Wu, Pengyuan Zhu
arXiv AI
Aug 24

RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation

The paper argues that retrieval‑augmented question‑answering systems should perform semantic compilation at ingest time rather than re‑deriving meaning at query time. By building a maintained structure—incrementally updated embeddings and validated atomic claims—read operations become far cheaper, with experimental results showing higher accuracy and lower token usage compared to traditional chunk‑based retrieval. The authors present two proofs: cheaper incremental updates and superior performance on broadcast‑interview transcripts, suggesting a new systems agenda for compilation and read planning.

By Kyle Wild, Yusuke Takahashi, Asako Uraki
arXiv AI
Sep 2

APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay

APEX-EM is a non‑parametric experience memory that stores full procedural‑episodic traces in a typed Procedural Knowledge Graph and retrieves them via semantic search, structural‑signature matching, and graph traversal. It uses a Plan‑Retrieve‑Generate‑Iterate‑Ingest workflow to produce, quality‑gate, and commit experiences, indexing both successes and failures so the agent learns what to reuse and what to avoid. Evaluations on five benchmarks with a shared GPT‑4o backbone show significant performance gains, such as +7.6 pp on BigCodeBench transfer and +1.4 pp on Lifelong Agent Bench, demonstrating that the memory adds to model capability rather than replacing it.

By Pratyay Banerjee, Masud Moshtaghi, Ankit Chadha
arXiv Machine Learning
Aug 12

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

arXiv:2607. 24850v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons.

By Lang Mei, Xiaohan Yu, Chong Chen, Liyan Liu, Xiangnan Chen, Jinchao Ma, Chao Feng, Li Huang, Siyu Mo, Sichen Kang, Yunkun Xu, Zhihan Yang, Zhujun Xue, Jingren Zhang, Qing He, Yingdi Huang, Hao Jiang, Ziao Ma, Zewei Pan, Minhao Sun, Zhuo Tao, Jinzhao Xiao, Gangtao Xin, Huanyao Zhang, Wenjian Zhang, Jiangshan Zhang, Guojie Zhu, Fangzhou Zou, Jiaxin Mao, Wentao Zhang
arXiv Machine Learning
Jun 30

Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation

arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.

By Zhe Dong (University of Maine at Presque Isle), Fang Qin (Stanford University), Manish Shah (Independent Researcher), Yicheng Wang (Independent Researcher)