Vela: User Behavior as Supervision Sparks LLM Intelligence Paper • 2610.14709 • Published 23 days ago • 86
Vela: User Behavior as Supervision Sparks LLM Intelligence Paper • 2610.14709 • Published 23 days ago • 86
RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems Paper • 2609.09657 • Published Sep 9 • 4
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents Paper • 2609.33772 • Published Sep 27 • 37
RoT: Enhancing Large Language Models with Reflection on Search Trees Paper • 2404.05449 • Published Apr 8, 2024
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents Paper • 2608.26530 • Published Aug 27 • 37
Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset Paper • 2311.05113 • Published Nov 9, 2023 • 1
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published Sep 27 • 33
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published Sep 27 • 33
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published Sep 28 • 35
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published Sep 28 • 35
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published Sep 27 • 33
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published Sep 27 • 33