SWE-Review
Collection
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review. Benchmark, trajectories, training data, and models for agentic code review. • 7 items • Updated
AI & ML interests
We study code intelligence.
Recent Activity
View all activity
Papers
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
ruoyu001
updated a
collection 20 days ago
ruoyu001
updated a
collection 21 days ago
YuxinJiang
authored 3
papers about 2 months ago
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
Paper • 2608.17393 • Published • 26
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
Paper • 2607.06065 • Published • 11
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Paper • 2606.03461 • Published • 3
YuxinJiang
submitted a
paper to Daily Papers about 2 months ago
ruoyu001
authored 2
papers 3 months ago
ruoyu001
submitted a
paper to Daily Papers 3 months ago
tcftrees
authored a
paper 3 months ago
tcftrees
authored 6
papers 4 months ago
MMFormalizer: Multimodal Autoformalization in the Wild
Paper • 2601.03017 • Published • 49
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
Paper • 2601.12346 • Published • 52
OVD: On-policy Verbal Distillation
Paper • 2601.21968 • Published • 6
From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
Paper • 2601.18533 • Published
GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
Paper • 2604.20659 • Published • 1
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Paper • 2606.03461 • Published • 3
ElvinDu518
authored a
paper 5 months ago
ruoyu001
authored a
paper 9 months ago
tcftrees
authored a
paper 9 months ago
ElvinDu518
authored a
paper 9 months ago