IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Paper • 2609.29444 • Published 3 days ago • 9
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Paper • 2609.29444 • Published 3 days ago • 9
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Paper • 2609.20784 • Published 10 days ago • 56
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents Paper • 2609.17653 • Published 12 days ago • 45
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Paper • 2609.20784 • Published 10 days ago • 56 • 3
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Paper • 2609.20784 • Published 10 days ago • 56
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Paper • 2609.20784 • Published 10 days ago • 56
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents Paper • 2609.17653 • Published 12 days ago • 45
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents Paper • 2609.17653 • Published 12 days ago • 45
PaperGym: Rubric-Centered Evolution for Research-Plan Generation Paper • 2608.31119 • Published 27 days ago • 33
PaperGym: Rubric-Centered Evolution for Research-Plan Generation Paper • 2608.31119 • Published 27 days ago • 33
PaperGym: Rubric-Centered Evolution for Research-Plan Generation Paper • 2608.31119 • Published 27 days ago • 33
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search Paper • 2607.24280 • Published Jul 27 • 85
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space Paper • 2607.25675 • Published Jul 28 • 69