Related papers: Aryabhata 2: Scaling Reinforcement Learning for Ad…

Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…

Natural Language to SQL (NL2SQL) has emerged as a critical task for enabling seamless interaction with databases. Recent advancements in Large Language Models (LLMs) have demonstrated remarkable performance in this domain. However, existing…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using…

Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with…

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…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Navigating the complexities of physics reasoning has long been a difficult task for Large Language Models (LLMs), requiring a synthesis of profound conceptual understanding and adept problem-solving techniques. In this study, we investigate…

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is…

Large Language Models can develop reasoning capabilities through online fine-tuning with rule-based rewards. However, recent studies reveal a critical constraint: reinforcement learning succeeds only when the base model already assigns…

Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, most existing open-source models are only pre-trained on…

Natural Language to SQL (NL2SQL) enables intuitive interactions with databases by transforming natural language queries into structured SQL statements. Despite recent advancements in enhancing human-computer interaction within database…

The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of existing RL attempts in LLMs usually rely on high-quality…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

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…

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such…

Large language models (LLMs) can face factual limitations when responding to time-sensitive queries about recent events that arise after their knowledge thresholds in the training corpus. Existing search-augmented approaches fall into two…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement…

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…