Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Agent Lightning v1.0: A Lightweight Framework for Harnessed Agentic RL

AI By Crimson AI Hugging Face Papers 19 August 2026 · 00:00 13 views
Share: X Telegram

Hugging Face researchers introduce Agent Lightning v1.0, a compact framework for harnessed agentic RL that improves coding-agent performance significantly with minimal data and compute.

Agent Lightning v1.0: A Lightweight Framework for Harnessed Agentic RL

Key points

Modern AI agents do not operate as standalone LLMs; they run inside agent harnesses that manage tools, context, and control flow. Recognizing the harness as a critical component, Hugging Face researchers have introduced Agent Lightning v1.0, a lightweight framework designed to enable reproducible reinforcement learning (RL) for arbitrary agent harnesses.

The framework builds on the original Agent Lightning architecture, which connects agents to RL training through an LLM endpoint proxy—an approach now adopted by frameworks like verl Uni-Agent, AReaL 2.0, slime, and Polar. This paradigm, termed "harnessed agentic RL," directly involves the deploy-time harness in model post-training, narrowing the gap between training and real-world use.

Harnessed agentic RL differs fundamentally from traditional agentic RL: the harness owns the environment interaction loop, while the training engine observes only LLM request-response pairs. This introduces challenges in retokenization, sample merging, advantage calculation, loss normalization, and backend scheduling, which can destabilize training if not addressed.

Agent Lightning v1.0 implements a solution in approximately 3,500 lines of code, prioritizing simplicity. It supports arbitrary harnesses and serves as a testbed for studying these challenges. The researchers validated it on instruction-following, search, and coding agents, providing a complete reproducible pipeline for coding-agent RL.

Using only 6K training examples and modest compute, RL improved Qwen3.5-9B on SWE-bench Verified from 41.8% to 56.4%, a 14.6-point absolute gain. The complete workflow and training scripts are released to facilitate reproducible research in harnessed agentic RL.

MetricBefore RLAfter RLGain
SWE-bench Verified (Qwen3.5-9B)41.8%56.4%+14.6 pts
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4