in-context-reinforcement-learning

Agent S: the state-of-the-art open source computer use agents

Keras based framework for neuro-symbolic LM systems

[EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —

Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning - - — ICLR 2025

Vintix: Action Model via In-Context Reinforcement Learning - - — ICML 2025

Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"

Next-gen Foundation Model for Embodied AI

[NeurIPS 2025] Official codebase for T2MIR: Mixture-of-Experts Meets In-Context Reinforcement Learning.

Benchmarking general decision-making with open & random worlds

A repo for enhancing spatial reasoning in VLMs using CoT and VoT prompting for 3D visual environments

Toy meta-RL environments for testing algorithms implementations

Code for our paper HeXA: Hierarchical Experimentalist Agents

Grouped-Tied Attention by Zadouri, Strauss, Dao (2025).

Source code for reproducing free random projection

ICLE is a multi-agent AI framework that dynamically trains and orchestrates specialized Expert Agents to solve complex, multi-step tasks.

In-Context Reinforcement Learning for LLMs — no fine-tuning, no gradient updates.

Testing hypotheses of distillation of a learning algorithm on multiple environments

Repository Switched To Xenoverse (https://github.com/FutureAGI/Xenoverse)