LongCat-Flash-Thinking-2601 Technical Report
Paper
• 2601.16725 • Published
• 178
base
-
-
DeepSeek-OCR 2: Visual Causal Flow
Paper • 2601.20552 • Published • 64 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
BMAM: Brain-inspired Multi-Agent Memory Framework
Paper • 2601.20465 • Published • 4 -
Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
Paper • 2601.22156 • Published • 14 -
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
Paper • 2601.21579 • Published • 6 -
DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
Paper • 2601.20975 • Published • 10 -
ProAct: Agentic Lookahead in Interactive Environments
Paper • 2602.05327 • Published • 25 -
Reinforcement World Model Learning for LLM-based Agents
Paper • 2602.05842 • Published • 27 -
Reinforced Attention Learning
Paper • 2602.04884 • Published • 28 -
AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents
Paper • 2602.06855 • Published • 74 -
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper • 2602.05400 • Published • 347 -
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 255 -
FASA: Frequency-aware Sparse Attention
Paper • 2602.03152 • Published • 150 -
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper • 2601.22975 • Published • 109 -
On Data Engineering for Scaling LLM Terminal Capabilities
Paper • 2602.21193 • Published • 93 -
Towards Autonomous Mathematics Research
Paper • 2602.10177 • Published • 36