SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
Paper • 2601.01426 • Published • 24
hkust-knowcomp
university
AI & ML interests
None defined yet.
ElvinDu518
authored a
paper 3 months ago
ElvinDu518
authored 3
papers 4 months ago
Bridging the Long-Term Gap: A Memory-Active Policy for Multi-Session Task-Oriented Dialogue
Paper • 2505.20231 • Published
ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Paper • 2508.19996 • Published
Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
Paper • 2512.20092 • Published • 9