Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent, high-quality training data. This persistent data scarcity has fundamentally hindered the progress of the broader research community in developing and innovating within this domain. To bridge this gap, we introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance through two core technical innovations: (1) Fact-grounded scalable controllable QA synthesis, which reverse-engineers the web graph via topological expansion and entity obfuscation to generate complex, multi-hop reasoning tasks with controllable coverage and complexity. (2) Denoised trajectory synthesis, which employs a retrospective summarization mechanism to denoise the trajectory, therefore promoting the teacher LLMs to generate high-quality actions. Experimental results demonstrate that OpenSeeker, trained (a single training run) on only 11.7k synthesized samples, achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch. Notably, trained with simple SFT, OpenSeeker significantly outperforms the second-best fully open-source agent DeepDive (e.g., 29.5% v.s. 15.3% on BrowseComp), and even surpasses industrial competitors such as Tongyi DeepResearch (trained via extensive continual pre-training, SFT, and RL) on BrowseComp-ZH (48.4% v.s. 46.7%). We fully open-source the complete training dataset and the model weights to democratize frontier search agent research and foster a more transparent, collaborative ecosystem.
As AI coding agents become both primary producers and consumers of source code, the software industry faces an accelerating loss of institutional knowledge. Each commit captures a code diff but discards the reasoning behind it - the constraints, rejected alternatives, and forward-looking context that shaped the decision. I term this discarded reasoning the Decision Shadow. This paper proposes Lore, a lightweight protocol that restructures commit messages - using native git trailers - into self-contained decision records carrying constraints, rejected alternatives, agent directives, and verification metadata. Lore requires no infrastructure beyond git, is queryable via a standalone CLI tool, and is discoverable by any agent capable of running shell commands. The paper formalizes the protocol, compares it against five competing approaches, stress-tests it against its strongest objections, and outlines an empirical validation path.
📌 请参阅原文实验章节获取详细数据
it represents significant infrastructure investment that most projects cannot undertake. Lore identifies the same problem but proposes a radically lighter-weight treatment: enriching an artifact every project already has (commit messages) using a mechanism git already supports (trailers), queryable through a tool every agent already knows how to use (a CLI). 2.3 Git Context Controller The Git Context Controller (GCC) [3] proposes a structured context management framework for AI agents, using git-inspired operations (COMMIT, BRANCH, MERGE, CONTEXT) over a .GCC/ directory to organize agent memor
Every codebase has lore. Most of it is lost. The protocol proposed here is a first step toward changing that. Disclosure of AI-Assisted Tools The author used AI-assisted tools during the research and writing process for this paper. Specifically, Claude (Anthropic, claude-opus-4-6) was used as an interactive research collab- orator for brainstorming the core thesis, iterating on protocol design decisions, conducting structured literature review, and drafting and refining text. Google NotebookLM w
We present a multi-agentic workflow for critical materials recovery that deploys a series of AI agents and automated instruments to recover critical materials from produced water and magnet leachates. This approach achieves selective precipitation from real-world feedstocks using simple chemicals, accelerating the development of efficient, adaptable, and scalable separations to a timeline of days, rather than months and years.
📌 请参阅原文实验章节获取详细数据
Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation framework. Prior works each employ their own methods to determine task success, such as database lookups, regex match, etc., adding complexity to the development of a unified agent evaluation approach. Moreover, they do not systematically account for the user's role nor expertise in the interaction, providing incomplete insights into the agent's performance. We argue that effective agent evaluation goes beyond correctness alone, incorporating conversation quality, efficiency and systematic diagnosis of agent errors. To address this, we introduce the TED framework (Talk, Evaluate, Diagnose). (1) Talk: We leverage reusable, generic expert and non-expert user persona templates for user-agent interaction. (2) Evaluate: We adapt existing datasets by representing subgoals-such as tool signatures, and responses-as natural language grading notes, evaluated automatically with LLM-as-a-judge. We propose new metrics that capture both turn efficiency and intermediate progress of the agent complementing the user-aware setup. (3) Diagnose: We introduce an automated error analysis tool that analyzes the inconsistencies of the judge and agents, uncovering common errors, and providing actionable feedback for agent improvement. We show that our TED framework reveals new insights regarding agent performance across models and user expertise levels. We also demonstrate potential gains in agent performance with peaks of 8-10% on our proposed metrics after incorporating the identified error remedies into the agent's design.
⚙️ 主要步骤：
Agent should enable Wifi. More examples are in Appendix A.12. 3.2.1 LLM-AS-A-JUDGE AND MAXPROGRESSRATE@k LLM-as-a-judge. We extend beyond the multi-step agent-environment setting and exact match metric (Chang et al., 2024) by evaluating agents in a multi-turn user-agent setup, where grading notes serve as subgoals to assess both intermediate and final states, tool calls, as well as the agent’s output responses. Let D = {(i, Gi) | i ∈I} be the test dataset, where i ∈I is a task instruction, Gi = {gi,1, gi,2, ..., gi,ni} be the set of grading notes associated with the task instruction i, and |Gi
As AI agents move from demos into enterprise deployments, their failure modes become consequential: a misinterpreted tool argument can corrupt production data, a silent reasoning error can go undetected until damage is done, and outputs that violate organizational policy can create legal or compliance risk. Yet, most agent frameworks leave builders to handle these failure modes ad hoc, resulting in brittle, one-off safeguards that are hard to reuse or maintain. We present the Agent Lifecycle Toolkit (ALTK), an open-source collection of modular middleware components that systematically address these gaps across the full agent lifecycle. Across the agent lifecycle, we identify opportunities to intervene and improve, namely, post-user-request, pre-LLM prompt conditioning, post-LLM output processing, pre-tool validation, post-tool result checking, and pre-response assembly. ALTK provides modular middleware that detects, repairs, and mitigates common failure modes. It offers consistent interfaces that fit naturally into existing pipelines. It is compatible with low-code and no-code tools such as the ContextForge MCP Gateway and Langflow. Finally, it significantly reduces the effort of building reliable, production-grade agents.
⚙️ 主要步骤：