-
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 257 -
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 85 -
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Paper • 2607.08964 • Published • 74 -
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 143
hh
hafffffff
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
paper updated a collection 1 day ago
paper updated a collection 1 day ago
paperOrganizations
