Submitted by Manya Wadhwa 6 Training Reasoning Models to Generate Diverse Scientific Ideas Salesforce AI Research 2 2
Submitted by KaiMei 19 Opera: A Verbal Critic Framework for Long-horizon Coding Agents Salesforce AI Research 9 2
Submitted by Haoxiang Zhang 189 Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Salesforce AI Research 11 2
Submitted by Yifan Zhang 6 CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling Salesforce AI Research 2
Submitted by Jiaxin Zhang 12 Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps Salesforce AI Research 2
Submitted by Yang Li 57 Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents Salesforce AI Research 3
Submitted by Phi Nguyen 20 Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training Salesforce AI Research 2
Submitted by taesiri 19 RISE: Recursive Improvement via Self-Extrapolating Policy Distillation Salesforce AI Research 1
Submitted by Zixuan Ke 32 EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? Salesforce AI Research 2
Submitted by Chengsong Huang 154 Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Salesforce AI Research 73 5
Submitted by Yifan Zhang 121 DarwinX: Evolving Agent Harnesses Through Natural Selection Salesforce AI Research 100 2
Submitted by Ziyang Luo 62 StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Salesforce AI Research 2