LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Paper • 2602.23881 • Published 10 days ago • 18
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents Paper • 2505.13652 • Published May 19, 2025
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning Paper • 2508.03501 • Published Aug 5, 2025 • 59
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Paper • 2602.23881 • Published 10 days ago • 18