SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale Paper • 2602.23866 • Published 5 days ago • 47
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Paper • 2602.23881 • Published 5 days ago • 18
Infinity-Instruct-Completions Collection Training data for speculative decoding draft models, containing model-generated responses for 660K prompts from Infinity-Instruct-0625. • 6 items • Updated 1 day ago • 2
LK-Speculators Collection High-performance speculative decoding draft models trained using LK losses, a novel training objectives that directly optimize acceptance rate • 9 items • Updated about 5 hours ago • 4
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards Paper • 2602.10231 • Published 21 days ago • 12
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning Paper • 2508.03501 • Published Aug 5, 2025 • 59
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents Paper • 2505.20411 • Published May 26, 2025 • 93