[2502.19402] General Reasoning Requires Learning to Reason from the Get-go

Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly – the hallmarks of artificial ge…

General Reasoning Requires Learning to Reason from the Get-go Seungwook Han Jyothish Pari Samuel J. Gershman Pulkit Agrawal Abstract Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly – the hallmarks of artificial general intelligence (AGI) – remains fragile. While LLMs seemingly succeed in commonsense reasoning, programming, and mathematics, they struggle to generalize algorithmic understanding across novel contexts. Our experiments with algorithmic tasks in e

related reading

• DeepSeek-R1arxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• [2506.19733] Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?arxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• State of RL for reasoning LLMs | A. Weersaweers.de
• Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Modelsarxiv.org
• Reasoning Models Reason Well, Until They Don'tarxiv.org
• [2602.19362] LLMs Can Learn to Reason Via Off-Policy RLarxiv.org
• [2504.13837] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?arxiv.org
• Self-Adapting Language Modelsarxiv.org