Papers5

#Curriculum learning

Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models

This paper shows a simple way to turn many 'too-easy' questions into harder, still-checkable ones so that AI keeps learning instead of stalling.

#Reinforcement Learning with Verifiable Rewards#Compositional prompts#Sequential Prompt Composition

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

Intermediate

Yanqi Dai, Yuxiang Ji et al.Jan 28arXiv

This paper says that to make math-solving AIs smarter, we should train them more on the hardest questions they can almost solve.

#Mathematical reasoning#RLVR#GRPO

LongCat-Flash-Thinking-2601 Technical Report

Beginner

Meituan LongCat Team, Anchun Gui et al.Jan 23arXiv

LongCat-Flash-Thinking-2601 is a huge 560-billion-parameter Mixture-of-Experts model built to act like a careful helper that can use tools, browse, code, and solve multi-step tasks.

#Agentic reasoning#Mixture-of-Experts#Asynchronous reinforcement learning

Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition

Intermediate

Warit Sirichotedumrong, Adisai Na-Thalang et al.Jan 19arXiv

Big models like Whisper are great for accuracy but too slow for live captions; this paper builds a smaller, faster Thai speech recognizer for real-time use.

#Thai ASR#Streaming speech recognition#FastConformer-Transducer

SmartSearch: Process Reward-Guided Query Refinement for Search Agents

Intermediate

Tongyu Wen, Guanting Dong et al.Jan 8arXiv

SmartSearch teaches search agents to fix their own bad search queries while they are thinking, not just their final answers.

#Search agents#Process rewards#Query refinement