AgentSWE: Can Coding Agents Build the Agent You Actually Want?
Paper • 2610.13361 • Published • 233
Marcus Santos
immarcussantos
AI & ML interests
computer vision
Recent Activity
liked a model 3 days ago
autotrust/JEV-27B-VL updated a model 4 days ago
immarcussantos/perceiver-multitask-study published a model 4 days ago
immarcussantos/perceiver-multitask-studyOrganizations
None yet
upvoted a paper 4 days ago
upvoted 3
papers 7 days ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 665
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
Paper • 2610.06647 • Published • 152
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 93