Posterior Sampling for Offline Policy Optimization in RL
Discover how Posterior Sampling improves offline policy optimization, balancing generalization and robustness in reinforcement learning models.
GraphReAct: Advanced Multi-Step Graph Reasoning Framework
Discover GraphReAct, a novel framework enhancing multi-step graph inference by combining reasoning and acting for superior graph learning results.
CASPO: Boosting Reliability in Reasoning Large Language Models
Discover how CASPO enhances reasoning reliability in LLMs with confidence-aware alignment and efficient inference for accurate AI outputs.
FlowAgent: Continuous Tool Orchestration for AI Reasoning
Discover FlowAgent, a new AI framework enabling continuous tool orchestration to enhance reasoning, robustness, and adaptability in large language models.
Discovering ODEs with LLM-Based Qualitative & Quantitative Methods
Explore DoLQ, an innovative LLM-driven approach for accurate and physically consistent discovery of ordinary differential equations from data.