Papers5

#AIME

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability

Xiao Liang, Zhong-Zhi Li et al.Feb 2arXiv

The paper trains language models to solve hard problems by first breaking them into smaller parts and then solving those parts, instead of only thinking in one long chain.

#divide-and-conquer reasoning#chain-of-thought#reinforcement learning

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

MiMo-V2-Flash Technical Report

Intermediate

Xiaomi LLM-Core Team, : et al.Jan 6arXiv

MiMo-V2-Flash is a giant but efficient language model that uses a team-of-experts design to think well while staying fast.

#Mixture-of-Experts#Sliding Window Attention#Global Attention

Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling

Beginner

Falcon LLM Team, Iheb Chaabane et al.Jan 5arXiv

Falcon-H1R is a small (7B) AI model that thinks really well without needing giant computers.

#Falcon-H1R#Hybrid Transformer-Mamba#Chain-of-Thought

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

Intermediate

Peter Chen, Xiaopeng Li et al.Dec 18arXiv

The paper studies why two opposite-sounding tricks in RL for reasoning—adding random (spurious) rewards and reducing randomness (entropy)—can both seem to help large language models think better.

#RLVR#Group Relative Policy Optimization#ratio clipping