This work presents SimpleWikiSearch, whose corpus construction, retrieval stack, tool contract, and evaluation protocol are explicit and runnable and provides a domain-specific agent harness and a controlled offline environment for reproducible agentic-search evaluation.
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. These details are frequently under-specified, making it difficult to compare results or reproduce reported baselines. We present SimpleWikiSearch, whose corpus construction, retrieval stack, tool contract, and evaluation protocol are explicit and runnable. The environment starts from a full English Wikipedia dump, cleans and chunks the corpus, builds keyword and dense retrieval indexes, and exposes a minimal tool interface consisting of \texttt{search}, \texttt{open\_url}, and \texttt{submit\_answer}. We report baseline results on six QA datasets using open-source LLMs and provide a random-300 subset for comparisons with closed-source commercial models. SimpleWikiSearch provides a domain-specific agent harness and a controlled offline environment for reproducible agentic-search evaluation. Its contribution is this specified reference setup, rather than a new agent algorithm. Code and data will be available at: https://github.com/JimXiongGM/simple_wiki_search.
This work reveals that retrieval from a structured agent repository provides a cost-efficient, accurate, and controllable alternative to dynamic agent generation, responding to the strict demands of industrial applications.
Vitalii Belov, Artyom Sosedka, Andrey Sakhovskiy et al.· Annual International ACM SIG...· 0 citations
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries, and/or answers to hard-to-locate factual questions. However, most existing systems rely on dynamic commercial search APIs, which pose reproducibility and transparency challenges, in addition to high costs. To address these limitations, we introduce DeepResearchGym as a free and open-source search sandbox for reproducible research on deep research systems. The sandbox provides a search API that indexes large-scale public web corpora, namely ClueWeb22 and FineWeb, using a state-of-the-art dense retriever and approximate nearest neighbor search via DiskANN. It achieves comparable latency to popular commercial APIs while ensuring stable document rankings across runs. We demonstrate the sandbox's utility through two use cases. For training, we synthesize queries grounded in the indexed corpora and show that search agents trained within the sandbox generalize to commercial search at inference time, enabling cost-effective reinforcement learning. For evaluation, we extend the Researchy Questions benchmark with LLM-as-a-judge metrics to measure alignment with users' information needs, retrieval faithfulness, and report quality. Evaluation results show that system rankings remain consistent when switching from commercial APIs to ours.
João Coelho, Jingjie Ning, Jingyuan He et al.· International Conference on...· 2 citations
Existing deep-search agents use a Search-Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata. This prevents agents from directly constraining retrieval to parts of a webpage and often carries irrelevant content into their context. We introduce Sieve, a search-inspect-fetch strategy driven by a Boolean Query Language (BQL): it searches webpage fields to filter candidates, uses an interchangeable ranker to order them, presents structure-rich result cards for inspection, and fetches only selected sections. Across three QA collections, Sieve is more accurate than the strongest conventional Search-Visit configuration on each collection while using 20.7-50.6% fewer tokens. Boolean filtering improves every tested ranker, and the accuracy-context advantage persists across retriever choices and agent backbones. Our implementation is included in the SkimSearchAgent library https://github.com/ielab/skim-search-agent.
Shuai Wang, Haodong Chen, Yu Yin et al.· 2 citations
Large language model (LLM)-based web search agents have demonstrated remarkable capabilities in autonomous information retrieval and multi-step reasoning. However, their robustness under real-world distribution shifts, such as evolving webpage structures, dynamic content layouts, and unseen task environments, remains a critical open challenge. Existing approaches predominantly rely on static supervised fine-tuning with human-annotated trajectories, which not only incurs substantial labeling cost but also lacks the adaptive capacity to handle the inherent stochasticity of live web environments. In this paper, we propose TAPE (Trajectory Alignment and exPerience pool Evolution), a novel self-evolving fine-tuning framework designed to enhance the generalization and robustness of web search agents without requiring large-scale human annotation. TAPE introduces a dual-stream experience pool that continuously accumulates both successful and failed agent trajectories during self-play execution. A trajectory alignment module maps heterogeneous execution paths into a unified semantic space, enabling contrastive learning to identify failure-inducing operations and reward generalizable search strategies. The framework further incorporates an adaptive pool evolution mechanism that filters, reweights, and distills experiences to prevent knowledge stagnation and distributional collapse. Extensive experiments on the GAIA benchmark and BrowseComp dataset demonstrate that TAPE consistently outperforms strong baselines across all three difficulty levels, achieving up to 6.2% absolute improvement in task success rate on GAIA Level-2 tasks (a 134.8% relative gain over the SFT-Only baseline on the GAIA validation split) and 1.3% absolute (217% relative) improvement on BrowseComp hard-tier queries, while exhibiting significantly greater resilience to webpage structure perturbations. These improvements are consistent across three open base models spanning two model families and the 7B–14B scale range. Our analysis further suggests that the contrastive self-play signal can serve as a useful partial surrogate for human preference labeling in agent trajectory optimization, substantially reducing, though not eliminating, reliance on human-annotated trajectories.
Minjae Rhee, Jitong Zou, Tianjun Mo et al.· IEEE Access· 0 citations
A unified taxonomy of 8 categories covering ambiguous and unanswerable questions is addressed, a multi-agent generation pipeline with a two-stage process (NLQ generation followed by SQL grounding) and an explicit Category Conformance validation stage are addressed.
Giovanni Sullutrone, Luca Sala, Sania Aftar et al.· 0 citations
An agent skill is a folder containing a SKILL.md file with instructions for a language-model agent, optionally accompanied by scripts and reference files. The agent loads the skill when it judges that a task matches the skill description. Anthropic introduced the format in October 2025 as an open specification. Nine months later, we find that skill files in the millions sit in public GitHub repositories. Skills are unlike the artifacts the SE research community usually mines: they are written mainly in natural language, a model selects them probabilistically at run time, and no compiler or type checker verifies the selection. They also have no central registry or package manager, so they spread by copying folders between repositories. How developers write, reuse, and maintain skills is therefore an empirical question, and no existing dataset records this population. We present GitSkills, a dataset of 3,797,117 SKILL.md files collected from 282,200 public repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. It groups identical files into 1,877,981 distinct contents and enriches one representative per group with the full text, parsed front matter, folder contents, repository metadata, and, for a subset, the commit history of the file. A single self- contained SQLite file supports research on the adoption, reuse, structure, authorship, maintenance, and security of agent skills.
Giuseppe Destefanis, Daniel Graziotin, Matteo Vaccargiu et al.· 0 citations