mlsanityData to 7 Oct 2026

K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook

arXiv 2610.00074 ↗First posted 4 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher supplies access to a model of their choice, hosted or running locally, and the application supplies everything else: a place for the work to run, a layer of scientific scaffolding, and a complete record. Each project is an ordinary folder, so the data, the code, the results, and the record stay on a machine the researcher administers and can be read years later without the application. Three things separate it from a chat assistant or a general-purpose coding agent. It ships a library of written scientific procedures, guided workflow templates, catalogs of where research data can be found, and reviewer and writer roles the agent can hand work to. It keeps a Living Lab Notebook whose entries link into an argument and are added to but never erased. And it records what happened by watching what the agent does rather than by taking the agent's word for it, in a log the agent has no tool that can write to. That choice targets the most common failure, model overclaiming, in our earlier benchmark of nine frontier models, by making claims checkable rather than preventing them. On twenty interdisciplinary research prompts, scored under a rubric fixed in advance, K-Dense BYOK led two managed platforms on both scientific quality and research execution. Its deliverables were the only ones that recorded the software they ran in, and the only ones that usually arrived with a command that regenerates the results. One of the managed platforms ran the same frontier model and supplied neither. Those environment records were files the agent wrote, not part of the observed log, which does not yet capture the software environment itself. The code is available under the MIT license at https://github.com/K-Dense-AI/k-dense-byok.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 58 references that are in the map. First posted on arXiv 4 Sep 2026.

Builds on

35 of 58 references.

References · 35

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  3. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  4. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  5. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  6. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  7. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  8. 2025Reasoning Models Don't Always Say What They Thinkcited by 388
  9. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  10. 2025PaperBench: Evaluating AI's Ability to Replicate AI Researchcited by 286
  11. 2024Self-Preference Bias in LLM-as-a-Judgecited by 248
  12. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
23 more
  1. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discoverycited by 208
  2. 2024Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Modelscited by 150
  3. 2024Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluationscited by 130
  4. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  5. 2024CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmarkcited by 115
  6. 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attackscited by 82
  7. 2025BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biologycited by 75
  8. 2025Design Patterns for Securing LLM Agents against Prompt Injectionscited by 67
  9. 2026"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wildcited by 46
  10. 2026Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflowscited by 44
  11. 2026Rethinking the Evaluation of Harness Evolution for Agentscited by 39
  12. 2025PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflowscited by 29
  13. 2026From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agentscited by 29
  14. 2026Stop Comparing LLM Agents Without Disclosing the Harnesscited by 25
  15. 2021A large-scale study on research code quality and executioncited by 22
  16. 2025When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validitycited by 11
  17. 2023Recording provenance of workflow runs with RO-Cratecited by 8
  18. 2023Computational reproducibility of Jupyter notebooks from biomedical publicationscited by 6
  19. 2026Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Taskscited by 6
  20. 2025K-Dense Analyst: Towards Fully Automated Scientific Analysiscited by 5
  21. 2026K-Bench: measuring model performance on real scientific agent requestscited by 2
  22. 2026Toward Evaluation Frameworks for Multi-Agent Scientific AI Systemscited by 1
  23. 2026Scientific Agent Skills: A Library of Procedural Knowledge for Research Agentscited by 1

Built on by

Not cited yet.