(NeurIPS 2025) CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Official implementation of DAC'26 paper "FlowPlace: Flow Matching for Chip Placement"

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images …

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

Awesome Papers related to Agent Memory: methods, benchmarks and surveys. Website: https://yyyujintang.github.io/Awesome-Agent-Memory-Papers/

A general framework for strategically scaling evaluation-driven discovery loops, discovering state-of-the-art solutions on 21 open-ended problems.

Reference code as a part of a tutorial of Bayesian Optimization for scientific discovery

Can LLMs beat classical HPO? A benchmark comparing classical, LLM-based, and hybrid methods on Karpathy's autoresearch.

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…

Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more

让每一次引用都成为可解释的影响力 Turning Every Citation into Explainable Impact

AI-Driven Scientific and Algorithmic Discovery

AI agents running research on single-GPU nanochat training automatically

CycleQD is a framework for parameter space model merging.

Public files for the ATPlace2.5D, including test cases and certain code.

P1: Mastering Physics Olympiads with Reinforcement Learning

A series-symbol (S2) dual-modality data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic representations.

Library for sequence-to-sequence numeric prediction, applicable to any tokenizable input, and allows pretraining and fine-tuning over multiple tasks.

Official implementation of ICML'25 paper "Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings"

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Neural Genetic Search in Discrete Spaces (ICML, 2025)