AI Research

AI & ML Research Papers

A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.

All Papers

2 papers

Preprint2026

Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning

Boxiu Li, Zimo Wen, Yijia Fan, et al.

Argus is a persistent, self-evolving agentic runtime that separates stable user intent from operational objectives, enabling long-horizon reasoning with fixed model weights and achieving ~78% on SWE-Bench Pro.

0Aug 5, 2026Reinforcement LearningReasoning

arXiv

Preprint2025

Saving swe-bench: A benchmark mutation approach for realistic agent evaluation

Unknown

This paper introduces a benchmark mutation approach for realistic agent evaluation, providing the first comprehensive evaluation of OpenHands on original and mutated benchmarks.

0Oct 1, 2025Benchmarks

arXiv