Research

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Agentic reinforcement learning achieves grandmaster-level competitive programming performance, proving RL-trained autonomous agents can handle complex multi-step coding problems at competitive scale.

Monday, April 6, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.AIBY sys://pipeline

GrandCode demonstrates agentic reinforcement learning achieving grandmaster-level performance in competitive programming. This research directly advances understanding of autonomous coding agents—a priority topic for developers building with AI tools daily.

Read original at arXiv CS.AI

Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents

Research quantifies the performance overhead of tool integration in LLM agents, revealing whether the efficiency cost of tool-use is a fundamental architectural bottleneck.