mlsanityData to 14 Oct 2026

mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers

arXiv 2609.00453 ↗First posted 31 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These are different claims. We test each one. mimeo is an open-source tool that finds a person's public work, checks each extracted quotation against the cached source text, and writes a file an agent can load. Eight logged builds averaged 38 model calls; the check rejects 13.2% of extracted quotations. We tested four expert files with one coding-agent harness. Knowledge access was clearest: mimeo answered all 20 obscure, quotation-heavy questions; no closed-book condition answered more than 10. Keyword search (BM25) over the same pages answered 15-17, a gap this sample cannot resolve. Grounding showed one clear benefit: personas written from model memory misstated a documented position on 1-4 of 20 answers under every grader; the plain agent and mimeo never did. Every persona was easy to spot on short open prompts, and adding task material lowered identification by 18-23 points. mimeo was no more identifiable than a from-memory profile. Judgment transfer remained unresolved because both tests hit their ceiling: every condition found 94-97% of the problems planted in engineering tasks and scored 94-100% on 16 new application scenarios. An AI-judged "sounds like the expert" score changed with the judge: two of four preferred answers based on a model's stereotype, while two found no difference on the same text. That is a caution against relying on a single AI judge. The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment. Toolkit and expert profiles: https://github.com/K-Dense-AI/mimeo

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 56 of its 73 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

56 of 73 references.

References · 56

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  5. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  9. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  10. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  11. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  12. 2023Large Language Models as Optimizerscited by 864
38 more
  1. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
  2. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  3. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  4. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 542
  5. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  6. 2024Agent Workflow Memorycited by 383
  7. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 345
  8. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 341
  9. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  10. 2024JudgeBench: A Benchmark for Evaluating LLM-based Judgescited by 318
  11. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 315
  12. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  13. 2022Teaching language models to support answers with verified quotescited by 292
  14. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  15. 2024Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judgecited by 269
  16. 2024Self-Preference Bias in LLM-as-a-Judgecited by 258
  17. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  18. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  19. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  20. 2023Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMscited by 178
  21. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 175
  22. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  23. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 168
  24. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 142
  25. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forwardcited by 113
  26. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
  27. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 97
  28. 2026SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?cited by 82
  29. 2023When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Modelscited by 53
  30. 2026SkillGen: Verified Inference-Time Agent Skill Synthesiscited by 36
  31. 2025How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulationcited by 22
  32. 2024Helpful assistant or fruitful facilitator? Investigating how personas affect language model behaviorcited by 21
  33. 2025Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performancecited by 18
  34. 2026SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agentscited by 18
  35. 2026CODESKILL: Learning Self-Evolving Skills for Coding Agentscited by 12
  36. 2026AI Can Learn Scientific Tastecited by 11
  37. 2026Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISMcited by 9
  38. 2026Agent Skill Evaluation and Evolution: Frameworks and Benchmarkscited by 8

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.