Tag
This paper proposes EvoEnv, a method where language models construct verifiable Python environments for self-improvement through reinforcement learning, achieving a 3.3% relative gain on Qwen3-4B-Thinking.
Nous Research's Hermes Agent, a self-improving open-source AI agent framework optimized for local use, has become the most used agent on OpenRouter and is now powered by NVIDIA RTX PCs and DGX Spark for accelerated performance.
Hermes Agent by Nous Research is an open-source, self-improving autonomous agent that learns from every session and builds persistent memory over time. Tavily integrates as its web search backend to improve search quality and prevent bad data from compounding into the agent's long-term memory and skills.
Anthropic announces new features for Claude Managed Agents, including 'dreaming' for self-improving memory, outcome-based evaluation loops, and multiagent orchestration capabilities.
Claude Code can auto-iterate prompts by running evals, rewriting, and keeping winners, boosting a hook-writer skill from 32/50 to 47/50 overnight.
AccelOpt is a self-improving LLM agentic system that autonomously optimizes AI accelerator kernels through iterative generation and optimization memory, achieving 49-61% peak throughput improvements on AWS Trainium while being 26x cheaper than Claude Sonnet 4.
Hermes Agent is an open-source, self-improving AI agent framework by Nous Research featuring a closed learning loop, cross-platform deployment, and compatibility with hundreds of LLMs. It provides a terminal interface, persistent memory, automated scheduling, and research-ready tooling for scaling AI workflows.