A curated list for Self-Improvement in Foundation Model Based Agentic Systems.

Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

Adaptive Agent Learning with Evolving Supervision

A Survey on Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Official codebase for the paper "Sharpening Tax in Post-Training"

Technical resources for AI developers to build applications, agents, and systems using Oracle AI Database and OCI services

Official repository for "Context Language Models"

mimalloc is a compact general purpose allocator with excellent performance.

PersonaManifold (NeurIPS 2026): curved geometry, geodesic steering, and behavioral triplet evaluation

A framework for building agentic apps

[NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own

Taste-Bench: measuring the long-horizon judgment of LLM agents at real decision forks

Harness-Zero: Harness Distillation via Agent-as-Harness

A collection of tricks and tools to speed up transformer models

An experimental Rust-native build tool for React apps.

Imitation learning algorithms

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents