Related papers: P1: Mastering Physics Olympiads with Reinforcement…

Large language models (LLMs) have rapidly advanced and are increasingly capable of tackling complex scientific problems, including those in physics. Despite this progress, current LLMs often fail to emulate the concise, principle-based…

Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we…

Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…

Small Language Models (SLMs) offer privacy and efficiency for educational deployment, yet their utility depends on reliable multistep reasoning. Existing benchmarks often prioritize final answer accuracy, obscuring 'right answer, wrong…

While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evaluation benchmarks. Specifically, existing benchmarks often…

Proprietary AI systems have recently demonstrated impressive capabilities on complex proof-based problems, with gold-level performance reported at the 2025 International Mathematical Olympiad (IMO). However, the training pipelines behind…

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains…

Physics problem-solving is a challenging domain for AI models, requiring integration of conceptual understanding, mathematical reasoning, and interpretation of physical diagrams. Existing evaluations fail to capture the full breadth and…

While reinforcement learning has advanced the reasoning abilities of Large Language Models (LLMs), these gains are largely confined to English, creating a significant performance disparity across languages. To address this, we introduce…

Physics provides fundamental laws that describe and predict the natural world. AI systems aspiring toward more general, real-world intelligence must therefore demonstrate strong physics problem-solving abilities: to formulate and apply…

[Abridged abstract] Large Language Models (LLMs) can solve some undergraduate-level to graduate-level physics textbook problems and are proficient at coding. Combining these two capabilities could one day enable AI systems to simulate and…

We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuning (SFT) followed by reinforcement learning (RL). A central…

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on…

Although Large Language Models (LLMs) have demonstrated remarkable progress, their proficiency in graph-related tasks remains notably limited, hindering the development of truly general-purpose models. Previous attempts, including…

With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with…

Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily learn to pattern-match toward correct answers? We study this question by training a 1.5B-parameter…

In recent years, general-purpose large language models (LLMs) such as GPT, Gemini, Claude, and DeepSeek have advanced at an unprecedented pace. Despite these achievements, their application to finance remains challenging, due to fragmented…

Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general…

Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics…