BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? Paper • 2603.03194 • Published 10 days ago • 53
Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards Paper • 2512.21625 • Published Dec 25, 2025 • 4
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents Paper • 2509.13309 • Published Sep 16, 2025 • 67