Reinforcement learning

Jun 02, 2026

Task Fidelity Scaling Laws — Kobie Crawdord, Snorkel

An experiment by Snorkel AI reveals that in agentic AI training, the quality of tasks is paramount. Using the same model and compute, fine-tuning on high-quality tasks yielded a 6% performance improvement, a 5x greater uplift compared to the 1% gain from low-quality tasks. The key difference lies in the nature of the tasks: high-quality tasks are genuinely harder, featuring more tool calls and cleaner failure modes that provide a meaningful learning signal. In contrast, low-quality tasks often fail due to ambiguity and environmental noise, hindering effective model improvement.

May 26, 2026

Q-learning with Flow-Matching Policies

This talk explores methods for optimizing expressive, multi-modal policies, such as those based on flow-matching, with off-policy reinforcement learning. The speaker presents two novel algorithms, FQ-RL and CAM, designed to overcome the instability of backpropagation through multi-step generative models, enabling effective online self-improvement and adaptation for robotic manipulation tasks.

May 26, 2026

How Cursor Trained Composer on Fireworks: Distributed Infrastructure for High-Performance RL

Cursor's Federico Cassano and Fireworks' Dmytro Dzhulgakov detail their collaboration on Composer 2, a specialized foundation model for software engineering. They discuss their top-down training strategy, the infrastructure challenges of large-scale distributed Reinforcement Learning on sparse models, and how model specialization achieves frontier performance with superior efficiency.

May 26, 2026

End-to-End Foundation Models for the Energy Industry — with Jazmia Henry

Jazmia Henry details the end-to-end process of building specialized foundation models for the energy industry. She covers the four key stages from data curation of unstructured, handwritten documents to optimizing inference, and introduces her Grounded Continuous Evaluation (GCE) framework to combat reward hacking in reinforcement learning.

May 13, 2026

The Founders Who Left Tesla to Rebuild America | a16z

Erin Price-Wright, Turner Caldwell (Mariana Minerals), and Drew Baglino (Heron Power) discuss closing America's critical minerals gap and modernizing the power grid for the AI economy. They cover how automation, reinforcement learning, and lessons from Tesla can accelerate mining, refining, and grid infrastructure development to compete with China and enable re-industrialization.

May 12, 2026

Lessons from Trillion Token Deployments at Fortune 500s — Alessandro Cappelli, Adaptive ML

95% of GenAI pilots fail due to feedback integration issues, not deployment challenges. Alessandro Cappelli argues that Reinforcement Learning (RL) provides the only systematic way to incorporate business metrics and production signals to continuously improve models, especially for complex agent-based systems.