Yimin Liu

Experience

• Research Engineer Intern Sep 2026 — present

  Deffai · Remote

  • Building a full-stack FDA review agent: a RAG retrieval layer over FDA regulations and guidance documents, a multi-step review workflow with citation provenance, and the client-facing application.
  • Designing FDABench, an end-to-end evaluation of the review workflow that scores agent outputs against reference reviews.
• Open-Source Contributor & Maintainer Jan 2026 — present

  BenchFlow · San Francisco, CA

  Research Scientist Intern: May — Aug 2026

  • Evaluation Infrastructure
    • Built the BenchFlow evaluation environment and runtime for containerized benchmark suites spanning coding, terminal, and productivity tasks.
  • BenchShield – Reward Integrity for Agent Evaluation
    • Hardened runtime evidence checks against tampered event annotations and unsupported verdicts; added regression tests for missing evidence and action attribution.
    • Built a resumable annotation runner that validates completion from generated artifacts and records token usage and cost for each model call.
  • SkillsBench – Agent Skill Evaluation
    • Built the agent sandbox across 18 model–harness configurations, with per-trial container isolation, raw trajectories, usage accounting, and pass/fail evidence.
    • Designed paired evaluations across 87 tasks with task-macro pass rates and 95% CIs; curated Skills raised pass rates from 33.9% to 50.5% (+16.6 pp).
  • ClawsBench – Capability and Safety Evaluation
    • Built a benchmark of 44 tasks across five simulated services (Gmail, Slack, Calendar, Docs, Drive), evaluating agent capability and safety in shared workspaces.
• Independent Research Collaborator Jun 2026 — present

  AutoRSI, AgentFuzzBench & ScienceIDE · Remote

  Collaborators: Yuxuan Jiang (AutoRSI); Security Lab, UC Davis (AgentFuzzBench); AItonomy Foundation (ScienceIDE)

  • AgentFuzzBench – End-to-End Agentic Fuzzing
    • Built reproducible task packages for eight pinned OSS targets, combining Docker environments, task contracts, and verifiers for the full fuzzing lifecycle.
    • Packaged the hosted benchmark with committed AFL++ oracle evidence and hardened the trust boundary between agent-controlled output and scored-coverage grading.
  • AutoRSI – Iterative Method Improvement
    • Building a propose–implement–evaluate–reflect pipeline that constructs and refines improvement plans, replacing a fixed library of candidate methods.
  • ScienceIDE – Scientific Codebases as Agent-Learnable Environments
    • Packaged Scirpy (single-cell immune-receptor repertoire analysis) as the bioinformatics environment in a 64-environment registry of executable scientific-code tasks, with acceptance criteria that check scientific outputs, not just successful execution.
• Graduate Research Assistant Mar 2023 — present

  The Ohio State University · Columbus, OH

  Advisor: Professor Lijun Cheng

  • Developed DG-scRNA, a graph-convolutional network that annotates cell types from scRNA-seq data, 97.2% accuracy on 150K+ cells (first-author manuscript).
  • Integrated scRNA-seq and spatial transcriptomics from 25 thyroid cancer samples; identified 50+ ligand-receptor interactions and two novel cell subtypes.
  • Benchmarked CNN, RNN, and Transformer architectures for CRISPR gRNA on-target prediction over 50K+ curated sequences.
• Research Collaborator Sep 2025 — Nov 2025

  Wuhan University of Science and Technology · Wuhan, CN (remote)

  Collaborator: Shuting Jin, School of Computer Science and Technology

  • DeepDR – Drug Repositioning Web Platform: Built the web platform: 15+ deep learning models over a 5.9M-edge knowledge graph, with visualizations explaining each recommendation.
• Research Assistant Aug 2021 — Oct 2021

  Harvard Medical School · Boston, MA

  • Built automated mutation-calling pipeline (GATK, R) on 50K+ scRNA-seq cells; clustered SNV and expression profiles to predict variant–phenotype relationships in cancer.
• Research Assistant Mar 2021 — Aug 2021

  Beijing Institute of Genomics, Chinese Academy of Sciences · Beijing, CN

  • Built a pipeline optimizing COVID-19 hybrid-capture probes; redesigned low-efficiency regions, raising sensitivity 25%.
• Research Assistant Nov 2019 — Feb 2021

  Dalian University of Technology · Dalian, CN

  • Undergraduate research on O-GlcNAc chromatin regulation in breast cancer (proteomics, ChIP-seq, RNA-seq); co-authored Nature Communications 2020, Cell Biology International 2021, and BBA – General Subjects 2021.