self-evolving

Tag

Cards List
#self-evolving

A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

Hugging Face Daily Papers · 2026-04-21 Cached

TACO introduces a self-evolving compression framework that automatically learns to shrink redundant terminal interaction history, cutting token overhead ~10% while boosting accuracy 1-4% across TerminalBench and other code-agent benchmarks.

0 favorites 0 likes
#self-evolving

@dair_ai: NEW paper from NVIDIA. EDA tools like ABC have been hand-tuned by humans for decades. New research from NVIDIA shows th…

X AI KOLs Following · 2026-04-20 Cached

NVIDIA researchers present the first self-evolving logic synthesis framework where multi-agent LLMs autonomously refine the ABC EDA tool codebase.

0 favorites 0 likes
#self-evolving

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Hugging Face Daily Papers · 2026-04-20 Cached

Agent-World introduces a self-evolving training framework for general agent intelligence that autonomously discovers real-world environments and tasks via the Model Context Protocol, enabling continuous learning. Agent-World-8B and 14B models outperform strong proprietary models across 23 challenging agent benchmarks.

0 favorites 0 likes
#self-evolving

EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale

Hugging Face Daily Papers · 2026-04-19 Cached

EvoMaster is a scalable, self-evolving agent framework for large-scale scientific discovery that enables iterative hypothesis refinement and knowledge accumulation across experimental cycles. It achieves state-of-the-art results on four benchmarks including Humanity's Last Exam (41.1%) and MLE-Bench Lite (75.8%), outperforming general-purpose baselines by up to 316%.

0 favorites 0 likes
#self-evolving

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

Papers with Code Trending · 2026-04-18 Cached

This paper introduces GenericAgent, a self-evolving LLM agent system designed to maximize context information density. It addresses long-horizon limitations through hierarchical memory, reusable SOPs, and efficient compression, achieving better performance with fewer tokens compared to leading agents.

0 favorites 0 likes
#self-evolving

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks

Hugging Face Daily Papers · 2026-04-13 Cached

Researchers introduce BEHEMOTH benchmark and CluE cluster-based prompt optimization to enable LLMs to extract and retain heterogeneous memory across diverse tasks, achieving 9% gains over prior self-evolving frameworks.

0 favorites 0 likes
← Back to home

Submit Feedback