GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining

Biomni-R0: New Agentic LLMs Trained End-to-End with Multi-Turn Reinforcement Learning for Expert-Level Intelligence in Biomedical Research

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models

SATQuest: Neuer Verifizierer für logisches Denken in LLMs

LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning

PuzzleJAX: GPU-gesteuerte Plattform für schnelle Benchmarking von KI-Strategien

Chain-of-Agents: Neues Paradigma für end-to-end Problemlösung mit LLMs