https://youtu.be/dW0gb6PV0EM\n
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\nThe following papers were recommended by the Semantic Scholar API
\n- \n
- Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning (2025) \n
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models (2025) \n
- How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study (2025) \n
- Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 (2025) \n
- SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild (2025) \n
- Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning (2025) \n
- Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Papers
arxiv:2505.10554
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Abstract
Explicit alignment of large reasoning models with deduction, induction, and abduction through a three-stage pipeline improves scalability and reliability in reasoning tasks.
AI-generated summary
Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as self-correction, backtracking, and verification phenomena often referred to as the model's "aha moment". However, the timing and consistency of these emergent behaviors remain unpredictable and uncontrollable, limiting the scalability and reliability of LRMs' reasoning capabilities. To address these limitations, we move beyond reliance on prompts and coincidental "aha moments". Instead, we explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks. Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosting performance by over 10\% relative to instruction-tuned baselines. Furthermore, domain-specific RL from the aligned checkpoint yields an additional 2\% average gain in the performance ceiling across math, coding, and science benchmarks, demonstrating that explicit meta-ability alignment offers a scalable and dependable foundation for reasoning. Code is available at: https://github.com/zhiyuanhubj/Meta-Ability-Alignment
Community
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning (2025)
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models (2025)
- How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study (2025)
- Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 (2025)
- SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild (2025)
- Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning (2025)
- Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2505.10554 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2505.10554 in a Space README.md to link it from this page.