Can/Will LLMs Learn to Reason? | Neuro-Symbolic Wednesdays | Centaur AI Institute

💬 Discord: https://discord.gg/h8NVzwnysW 💻 GitHub: https://github.com/centaurinstitute 🤝 LinkedIn: https://www.linkedin.com/company/centaur-ai-institute/ This week, Abu Saparov is presenting: Reasoning—the process of drawing conclusions from prior knowledge—is a hallmark of intelligence. Large language models, and more recently, large reasoning models have demonstrated impressive results on many reasoning-intensive benchmarks. Careful studies over the past few years have revealed that LLMs may exhibit some reasoning behavior, and larger models tend to do better on reasoning tasks. However, even the largest current models still struggle on various kinds of reasoning problems. In this talk, we will try to address the question: Are the observed reasoning limitations of LLMs fundamental in nature? Or will they be resolved by further increasing the size and data of these models, or by better techniques for training them? I will describe recent work to tackle this question from several different angles. Abu's presentation is based on the following papers: https://arxiv.org/abs/2210.01240 https://arxiv.org/abs/2305.15269 https://arxiv.org/abs/2412.04703 https://arxiv.org/abs/2510.22371 https://arxiv.org/abs/2510.25626 0:00 Lobby 1:45 Can/Will LLMs Learn to Reason? 0:54:42 Q&A 1:30:10 Next Week — ​Join us for an interactive session exploring Neuro-Symbolic AI, the emerging paradigm that blends the strengths of neural networks with symbolic reasoning. We will discuss how hybrid approaches can enhance generalization, interpretability, and reasoning, and how these methods are shaping the future of intelligent systems. Whether you’re a researcher, engineer, or simply curious about the cutting edge of AI, you’ll find an engaging space to learn, connect, and exchange ideas. Event Format: 🔍 Reading Group 🎙️ Panel Discussion 🧩 Tutorials/Workshop Series 💬 Research Roundtable 🛠️ Open-Source Project Review 📄 Paper Pitch 🤝 Collaboration Hour 🍵 Networking Mixer #AI #NeuroSymbolic #FutureOfAI