Causal Evidence Reveals Dual Mechanisms in Graph Learning
Discover how large language models use dual mechanisms for in-context graph learning, combining structure inference and local transitions.
CoCoDA: Efficient Tool-Augmented Agents with Compositional DAG
Discover CoCoDA, a novel compositional DAG framework that enhances tool-augmented AI agents with efficient retrieval and adaptive training.
PLACO Framework: Boosting Human-AI Team Performance Efficiently
Discover PLACO, a multi-stage framework enhancing cost-effective performance in human-AI teams through calibrated outputs and Bayesian integration.
SkillLens: Efficient Multi-Granularity Skill Reuse for LLM Agents
Discover SkillLens, the adaptive framework boosting large language model agents' efficiency through multi-granularity skill reuse and cost-effective task e...
MemQ: Q-Learning for Self-Evolving Memory Agents
Discover MemQ, a novel Q-learning method enhancing self-evolving memory agents with Provenance DAGs for improved AI learning and memory management.