LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 130
all-a2a
-
-
DAPD: Dual-Anchored Policy Distillation
Paper • 2608.01735 • Published • 57 -
Progressive Agent Skill Generation via Reinforcement Learning
Paper • 2608.01678 • Published • 50 -
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Paper • 2608.02583 • Published • 43 -
Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs
Paper • 2608.01755 • Published • 31 -
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
Paper • 2608.02287 • Published • 27 -
WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning
Paper • 2607.29613 • Published • 22 -
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Paper • 2608.02585 • Published • 21 -
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
Paper • 2607.28802 • Published • 9 -
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems
Paper • 2607.29241 • Published • 7 -
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Paper • 2607.29377 • Published • 5 -
SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space
Paper • 2608.01397 • Published • 1