8000 Lyz1116-FOUND (n-lp) · GitHub
[go: up one dir, main page]

Skip to content
View Lyz1116-FOUND's full-sized avatar
  • FuDan University
  • 中国

Block or report Lyz1116-FOUND

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Lyz1116-FOUND/README.md

Hi, I'm Lyz1116-FOUND 👋

Fudan University undergraduate · AI / Agents / Game AI / Optimization

I like building AI systems that can be run, tested, observed, and evaluated, not just demonstrated in a notebook. My recent work focuses on coding agents, AI product engineering, game AI, reinforcement learning, and real-world combinatorial optimization.

Current interests: LLM Agents · AI Coding · Agent Harness · Game AI · Reinforcement Learning · AI Product Engineering

Featured work

Project What I built Evidence
Agent Replay A recorder, replay UI, evaluator, FastAPI service, and native ReAct coding-agent harness for Codex / Claude Code / OpenCode / Qoder / ZCode-style workflows. Includes tools, grader, retry, context compression, skills, MCP, reviewer, and multi-agent support. Public beta; live demo; 130 live-model runs across 13 variants × 10 tasks; on one model and 10 Python tasks (one run per variant/task), context compression kept 10/10 verified success while using about 47% of full-context total tokens; not a general model ranking.
Beat Greedy A playable ToC algorithm game that turns 0/1 knapsack into a player-vs-greedy-boss experience. Built the product flow, interaction, scoring, visual system, audio, and deployment. React 19 + TypeScript + Vite + Tailwind; 18 automated tests; deployed online.
RealRoute-Bench Research preview of a real-city routing benchmark: problem definitions, data provenance, an independent checker, and traffic-data acquisition; formal baselines and leaderboard remain incomplete. 12 city worlds · 2,400 fixed road access points · N20/50/100/200 nested scales · 48 static duration/distance pairs.
Gorge Chase DIY Agent DIY game agent built on Tencent KaiwuDRL: 16 actions, 1,840-dimensional observations, CNN + MLP Actor-Critic, GAE, masked PPO, and potential-based shaping. Public code and training notes document environment interaction, learner updates, and saved checkpoints; no comparative performance claim.

Agent Replay

Replay what a coding agent did — then verify whether it actually succeeded.

  • Record and replay real coding-agent sessions.
  • Inspect edits, commands, tests, regressions, and recoveries on an interactive timeline.
  • Compare multiple runs of the same task.
  • Run a native Python ReAct harness with six built-in tools, independent grading, retries, context management, Skills, MCP, Reviewer, and Multi-Agent.
  • Expose recording/evaluation through a FastAPI service.
  • Evaluate system choices with measured experiments instead of relying on model self-reports.

Live demo: https://lyz1116-found.github.io/agent-replay/

Beat Greedy

Local optimum ≠ global optimum — turned into a small game.

The player packs a bag while a greedy shopkeeper only looks at value/weight ratio. After submission, the game reveals the player's solution, the greedy baseline, and the true dynamic-programming optimum.

  • Product idea → interaction → implementation → testing → deployment.
  • Drag-and-drop gameplay, difficulty and timing, scoring, boss feedback, local persistence.
  • Original SVG assets and WebAudio sound design.

Play it: https://beat-greedy-da-e676.vercel.app/

Game AI & reinforcement learning

I have hands-on experience with game-agent development using PPO / Actor-Critic / GAE / reward shaping / action masking, including a KaiwuDRL-based real-time game environment. I also received a National Third Prize in the Tencent Kaiwu Reinforcement Learning Competition.

I am a dedicated player of Honor of Kings (王者荣耀) and 王者万象棋, and an invited tester / real user of TapTap GameBuddy, and I am especially interested in AI products that combine visual understanding, domain knowledge, and real-time interaction inside games.

Research & engineering

  • LLM / Agents: ReAct, Function Calling, tool use, context management, evaluator/grader design, agent observability, prompt/agent experiments.
  • ML / DL: PyTorch, Transformer, reinforcement learning, computer vision, conditional generation.
  • Optimization: TSP/VRP-style combinatorial optimization, Gurobi, Concorde, LKH, OSRM-based routing pipelines.
  • Engineering: Python, FastAPI, REST APIs, React, TypeScript, Vite, Tailwind CSS, Git, Docker, Linux.

Selected recognition

  • National Third Prize, Tencent Kaiwu Reinforcement Learning Competition
  • University Second-Class Scholarship
  • Academic performance: top 20% of cohort

What I care about

I prefer projects where an AI system has to survive contact with reality: real tools, real state, real failures, real verification, and a user who needs to understand what happened.

For internships, I am particularly interested in AI product engineering, coding agents, agent infrastructure/evaluation, game AI, and AI-native consumer products.

Coursework and repository attribution

Computer Vision Colorization currently publishes the course specification for grayscale-to-color generation in Lab space; implementation and experimental results are not included in that public repository.

Featured work above describes my project contributions. The Gorge Chase agent builds on Tencent's KaiwuDRL framework; I do not claim authorship of that framework. Forks, upstream mirrors, learning resources, and templates elsewhere in this account are not presented as original portfolio projects.

Pinned Loading

  1. agent-replay agent-replay Public

    Open-source visual debugger for coding agents: see what the agent reported doing and what actually changed.

    TypeScript 1

  2. beat-greedy beat-greedy Public

    A 30-second knapsack duel against a greedy bot. Local optimum is a trap.

    TypeScript

  3. RealRoute-Bench RealRoute-Bench Public

    Python

  4. mobat mobat Public

    KaiwuDRL 峡谷追猎 DIY Agent:16 动作、结构化观测、CNN+MLP Actor-Critic 与 masked PPO;含设计和训练验证记录。

    Python 1

0