Skip to content
View Yu-Fangxu's full-sized avatar

Highlights

  • Pro

Organizations

@tianyi-lab

Block or report Yu-Fangxu

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
Showing results

Official repository for "Context Language Models"

Python 908 101 Updated Nov 17, 2026

SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning

Python 75 9 Updated Oct 28, 2026

Self-HPO: self-improving harness + policy co-optimization for agentic SWE

Python 68 4 Updated Oct 19, 2026

A curated list of papers and selected technical blogs on Loop Models.

Python 489 17 Updated Nov 21, 2026

T2J-Bench: A benchmark testing whether coding agents can migrate real PyTorch training and inference repositories to native JAX/Flax.

Python 14 1 Updated Nov 18, 2026

[arXiv] ExpHarness: Model-Agnostic Experience Learning through a Trainable Harness

Python 3 1 Updated Oct 4, 2026

[arXiv] ElasticMem: Latent Memory as a Learnable Resource for LLM Agents.

Python 7 1 Updated Oct 4, 2026

[arXiv] CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery

Python 3 Updated Oct 4, 2026

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Python 762 85 Updated Oct 19, 2026

SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses

TypeScript 3,693 303 Updated Nov 22, 2026

A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

Python 1,152 133 Updated Nov 3, 2026

Official Project Page for KL-Regularized Policy Optimization (KLPO) (https://arxiv.org/abs/2610.08963)

Python 193 17 Updated Nov 5, 2026

A curated list of agentic environment synthesis, evolution, quality & scaling — built on three surveys (AEE, Environment Scaling, ACE lens)

11 Updated Nov 16, 2026

SciLaws-Bench: Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

Python 10 Updated Nov 9, 2026

The offical repo for "Dream-RSI: Recursive Self-Improvement through Evolving Worlds"

1,621 141 Updated Oct 23, 2026

A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.

Python 620 69 Updated Oct 2, 2026

AgentENV (AENV) is a distributed platform for running agent environments at scale.

Rust 3,775 375 Updated Nov 20, 2026

FinanceHarness: Autonomous Financial Deep Research Framework

Python 226 40 Updated Nov 18, 2026

Framework for evaluating and improving agents

Python 7,324 2,272 Updated Nov 21, 2026
Python 678 61 Updated Aug 21, 2026

Test-Time Learning with an Evolving Library

SAS 40 3 Updated Jun 10, 2026

Track 52,867+ AI benchmark, eval, dataset, and data-quality records from 41 public sources, with linked evidence and daily updates.

Python 411 66 Updated Nov 22, 2026

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

Python 5,445 344 Updated Nov 22, 2026

RL-training knowledge-work agents on APEX-Agents data with SkyRL + Harbor

Python 228 19 Updated Sep 1, 2026
Python 131 10 Updated Oct 6, 2026

The roadmap of long-horizon agents

877 59 Updated Nov 2, 2026

Official codebase of "Update Your Transformer to the Latest Release: Re-Basin of Task Vectors" - ICML 2025

Python 24 Updated Jul 30, 2025

Model merging, task-vector rebasin, and fine-tuning for vision and LLM models.

Python 41 6 Updated Nov 19, 2026

A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.

C++ 351 54 Updated Nov 20, 2026
Next