Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Paper • 2601.14004 • Published 7 days ago • 45
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution Paper • 2601.10657 • Published 12 days ago • 20
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution Paper • 2601.10657 • Published 12 days ago • 20
MCTSr-Zero: Self-Reflective Psychological Counseling Dialogues Generation via Principles and Adaptive Exploration Paper • 2505.23229 • Published May 29, 2025
SIGMA: An AI-Empowered Training Stack on Early-Life Hardware Paper • 2512.13488 • Published Dec 15, 2025
Economies of Open Intelligence: Tracing Power & Participation in the Model Ecosystem Paper • 2512.03073 • Published Nov 27, 2025 • 5
Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions Paper • 2512.00097 • Published Nov 27, 2025 • 3
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Paper • 2511.11793 • Published Nov 14, 2025 • 186
OpenAgents: An Open Platform for Language Agents in the Wild Paper • 2310.10634 • Published Oct 16, 2023 • 9
LayoutReader: Pre-training of Text and Layout for Reading Order Detection Paper • 2108.11591 • Published Aug 26, 2021 • 1
VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos Paper • 2510.19488 • Published Oct 22, 2025 • 20
Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents Paper • 2510.24702 • Published Oct 28, 2025 • 29