SevenTnewS

reinforcement learning

5 published articles

AI Agents3 min read

AI Agents

OpenManus just killed the invite wall for AI agents. Here's how to run it in ten minutes.

OpenManus is an open-source AI agent framework anyone can install and run immediately: no invite code, no gimmicks, just a Python environment and an API key. Here is why you need it.

2026-07-11

NLP & MLFeatured3 min read

AI Research

Why GPT-5.5 dominates a benchmark that tests how agents improve themselves

EvoPolicyGym isolates a critical but understudied capability: an agent's ability to refine an executable policy through repeated feedback-constrained edits. The benchmark reveals GPT-5.5 as the strongest performer across 16 environments, and provides trajectory-level diagnostics that expose how different agents allocate budget and convert feedback into tuned parameters.

2026-07-11

xAI / GrokFeatured3 min read

Grok 4.5

Cursor's Grok 4.5 was built by AI agents, not humans. That's the real story.

Cursor's Grok 4.5 is a Mixture-of-Experts model built using reinforcement learning in environments created by earlier AI agents, not humans. It handles complex, long-duration tasks across software engineering, data science, finance, and law, and it's available now.

2026-07-10

LLMs & ModelsFeatured1 min read

Coding Agents

Cognition's new coding agent scores near frontier results for pocket change

Cognition's SWE-1.7 coding model narrows the gap to frontier systems at a fraction of the cost, scoring 42.3% on FrontierCode and running at 1,000 tok/s. The model was trained on an improved reinforcement learning pipeline using Kimi K2.7 as the base.

2026-07-09

AI6 min read

AI Research

How maxproof turns generative verifiers into a proof revolution engine

MaxProof is a test-time scaling framework that models mathematical proof generation as an evolutionary search process. By combining Proof RL, verifier alignment, and refinement augmentation, it turns unreliable generative verification into a trustworthy reward system for training and inference.

2026-07-05