# Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

arXiv: https://arxiv.org/abs/2508.00414 · HTML: https://mlsanity.com/paper/2508.00414/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 23 of 23)

- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [TACO: Topics in Algorithmic COde generation dataset](https://mlsanity.com/paper/2312.14852/) (2023)
- [OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation](https://mlsanity.com/paper/2505.23885/) (2025)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [Scaling Test-time Compute for LLM Agents](https://mlsanity.com/paper/2506.12928/) (2025)
- [RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge](https://mlsanity.com/paper/2101.00376/) (2021)
- [WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model](https://mlsanity.com/paper/2504.21024/) (2025)
- [AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents](https://mlsanity.com/paper/2502.05957/) (2025)
- [OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization](https://mlsanity.com/paper/2410.19609/) (2024)
- [DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems](https://mlsanity.com/paper/2407.10701/) (2024)
- [LogiCoT: Logical Chain-of-Thought Instruction-Tuning](https://mlsanity.com/paper/2305.12147/) (2023)
- [WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback](https://mlsanity.com/paper/2505.20013/) (2025)
- [WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms](https://mlsanity.com/paper/2504.11788/) (2025)
- [TapeAgents: a Holistic Framework for Agent Development and Optimization](https://mlsanity.com/paper/2412.08445/) (2024)
- [Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots](https://mlsanity.com/paper/2409.10277/) (2024)

## Built on by (most cited first, 30 of 42)

- [MemEvolve: Meta-Evolution of Agent Memory Systems](https://mlsanity.com/paper/2512.18746/) (2025)
- [MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling](https://mlsanity.com/paper/2511.11793/) (2025)
- [Scaling Agents via Continual Pre-training](https://mlsanity.com/paper/2509.13310/) (2025)
- [Agentic Entropy-Balanced Policy Optimization](https://mlsanity.com/paper/2510.14545/) (2025)
- [OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis](https://mlsanity.com/paper/2603.20278/) (2026)
- [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026)
- [Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification](https://mlsanity.com/paper/2601.15808/) (2026)
- [DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking](https://mlsanity.com/paper/2510.20168/) (2025)
- [Open Data Synthesis For Deep Research](https://mlsanity.com/paper/2509.00375/) (2025)
- [EvoRoute: Experience-Driven Self-Routing LLM Agent Systems](https://mlsanity.com/paper/2601.02695/) (2026)
- [SmartSearch: Process Reward-Guided Query Refinement for Search Agents](https://mlsanity.com/paper/2601.04888/) (2026)
- [DynaWeb: Model-Based Reinforcement Learning of Web Agents](https://mlsanity.com/paper/2601.22149/) (2026)
- [Verified Critical Step Optimization for LLM Agents](https://mlsanity.com/paper/2602.03412/) (2026)
- [How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization](https://mlsanity.com/paper/2602.19208/) (2026)
- [OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents](https://mlsanity.com/paper/2601.18467/) (2026)
- [WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models](https://mlsanity.com/paper/2510.14438/) (2025)
- [Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors](https://mlsanity.com/paper/2601.15625/) (2026)
- [SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks](https://mlsanity.com/paper/2604.08865/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development](https://mlsanity.com/paper/2509.25297/) (2025)
- [Understanding DeepResearch via Reports](https://mlsanity.com/paper/2510.07861/) (2025)
- [Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm](https://mlsanity.com/paper/2510.00415/) (2025)
- [The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas](https://mlsanity.com/paper/2510.07091/) (2025)
- [DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping](https://mlsanity.com/paper/2510.12979/) (2025)
- [HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application](https://mlsanity.com/paper/2510.19631/) (2025)
- [A-MapReduce: Executing Wide Search via Agentic MapReduce](https://mlsanity.com/paper/2602.01331/) (2026)
- [Efficient Tree-Structured Deep Research with Adaptive Resource Allocation](https://mlsanity.com/paper/2510.05145/) (2025)
- [BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search](https://mlsanity.com/paper/2601.11037/) (2026)
- [Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration](https://mlsanity.com/paper/2604.18131/) (2026)
- [Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?](https://mlsanity.com/paper/2603.03202/) (2026)

## Abstract (arXiv)

General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools, limiting accessibility and reproducibility for the research community. In this work, we present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework designed to democratize the development and evaluation of advanced AI agents. Within Cognitive Kernel-Pro, we systematically investigate the curation of high-quality training data for Agent Foundation Models, focusing on the construction of queries, trajectories, and verifiable answers across four key domains: web, file, code, and general reasoning. Furthermore, we explore novel strategies for agent test-time reflection and voting to enhance agent robustness and performance. We evaluate Cognitive Kernel-Pro on GAIA, achieving state-of-the-art results among open-source and free agents. Notably, our 8B-parameter open-source model surpasses previous leading systems such as WebDancer and WebSailor, establishing a new performance standard for accessible, high-capability AI agents. Code is available at https://github.com/Tencent/CognitiveKernel-Pro