CV

Weijia (Charlie) Zhang

Incoming M.S. in Computer Science @ Yale

zhangwj.charlie@gmail.com
2172003915
, , US

Summary

Incoming Yale M.S. student in Computer Science, UIUC Computer Science and Mathematics graduate, and NLP/LLM agent researcher.

Education

  • M.S. in Computer Science
    2028-05
    Yale University
  • B.S. in Computer Science and Mathematics
    2026-05
    University of Illinois Urbana-Champaign
    GPA: 3.7/4.0

Work Experience

  • Machine Learning Engineer Intern, RSI / Self-Evolving Agents
    Jun 2026 - Present
    TikTok
    Project lead for TikTok's RSI/Self-Evolving Agent framework, built from 0 to 1.
    • Designed and shipped a closed Solver-Reflector-Evolver loop in which the Solver executes tasks, the Reflector attributes failures, and the Evolver iterates reusable skills; lifted F1 from 62.7% to 81.3% on unoriginal-video detection (9,600 real short videos) and from 76.5% to 87.3% on reposting-account detection (200 accounts).
    • Designed a transferable Online Failure Discovery process: the Reflector mines failure patterns from scenarios and Solver traces, maintains a two-level scenario-to-failure-mode taxonomy, and distills high-value error clusters into reusable skills, so the same framework self-evolves across scenarios without human-predefined error types.
    • Trained a video-understanding model: built an account-level SFT dataset of 74K accounts and 1.33M videos, ran distributed full-parameter SFT of Qwen3-VL 2B/4B/8B on 32 H100s with DeepSpeed, and calibrated thresholds across 53 checkpoints; the final 4B model cut false positives by 42.8% (318 to 182) against the 8B baseline at ~70% recall.
  • Research Intern, Large Language Models
    Jul 2025 - Sep 2025
    Microsoft
    Built the Excel Coding Agent data engine and post-training pipeline for Excel Copilot's code agent.
    • Produced execution-verified SFT/RL data by mining 20,000+ real-world workbooks, back-translating user queries from spreadsheet context, sampling multi-turn Office.js rollouts (write, execute, repair), and using SheetEngine final-state assertions as a programmatic verifier to filter incorrect and reward-hacking solutions.
    • Post-trained the coding agent on this corpus with rejection-sampling SFT and RL over same-task pass/fail rollouts under execution-based reward, improving Office Scripts pass@1 by 15% against the production baseline on a held-out set.
  • Software Development Intern
    Aug 2024 - Sep 2024
    Tencent, WeChat Group (WXG)
    Built cross-platform performance analysis and Unity memory-profiling tools for WeChat Mini Programs.
    • Developed a cross-platform Android and iOS hardware performance analysis tool with WeChat Mini Program telemetry, helping 200+ partner teams identify performance bottlenecks.
    • Built a Unity Mono Memory Profiler that identified 40+ hidden memory allocation sites in a pilot application.
  • AI Agent Engineer
    May 2023 - Jul 2023
    Reborn Network
    Built real-time embodied role-playing agents in Unity VR games.
    • Built an embodied role-playing agent in a Unity VR environment, closing a real-time perception-dialogue-action loop across text, voice, and full-body VR actions at sub-second end-to-end latency.
    • Introduced RAG/vector databases and dual-level (episodic + semantic) memory, improving cross-session recall accuracy from 38% to 61% on an internal multi-session dialogue eval.

Skills

Programming Languages

  • Python
  • C/C++
  • C#

Frameworks and Libraries

  • VERL
  • vLLM
  • LangGraph
  • LangChain
  • PyTorch
  • TensorFlow

AI Focus

  • RL/Post-training
  • LLM Agents
  • Multimodal Reasoning
  • Self-Evolving Agents
  • SFT
  • RAG
  • Evaluation

Publications

  • How Much Vision Does Multimodal Reasoning Need? Vision-Stripping for Multimodal Benchmarks
    2026
    Under review at NeurIPS 2026
    Research on vision-stripping for multimodal reasoning benchmarks.
  • Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs
    2026
    arXiv preprint arXiv:2606.11232
    Research on compressed moral composition in frontier LLMs.
  • SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning in Text-only LLMs
    2025
    arXiv preprint arXiv:2510.25092; under review at AAAI 2026
    Agentic information flow for multimodal reasoning in text-only LLMs.
  • CUADebug: Diagnosing and Repairing Computer-Use Agent Failures
    2026
    EMNLP 2026
    A framework for diagnosing and repairing computer-use agent failures.
  • Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory
    2024
    The First Workshop on AI Behavioral Science, ACM SIGKDD 2024
    A simulated LLM agent society for studying emergent social contracts.
  • Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
    2026
    ACL 2026, Oral
    A study of bias inheritance in synthetic data generated by LLMs.
  • Where LLM Agents Fail and How They Can Learn From Failures
    2025
    arXiv preprint arXiv:2509.25370; Failure Modes in Agentic AI Workshop, ICML 2026
    Research on LLM agent failures and learning from failed trajectories.

Portfolio

  • OpenManus & OpenManus-RL
    2025
    Research
    Core author of OpenManus-RL, a verl-based agent RL post-training framework in an open-source ecosystem with 70,000+ GitHub stars.
  • SeeingEye
    2025
    Research
    Agentic information-flow framework that enables text-only LLMs to perform multimodal reasoning through structured, tool-mediated textual context.
  • AgentDebugX
    2026
    Research
    Comprehensive debugging framework for long-horizon agent trajectories, with a Detect-Attribute-Recover-Rerun loop across multi-agent, tool-using, and computer-use agents.

Interests

  • Research
    LLM agents, VLM/LLM agents, Multimodal reasoning, Agent debugging, Reinforcement learning