Reasoning
DeepSeek-Prover-V2: Bridging the Gap Between Informal and Formal Mathematical Reasoning
While DeepSeek-R1 has significantly advanced AI’s capabilities in informal reasoning, formal mathematical reasoning has remained a challenging task for AI. This is primarily because producing verifiable mathematical proof requires both deep conceptual understanding and the ability to construct precise, step-by-step logical arguments. Recently, however, significant advancement is made in this direction as researchers at DeepSeek-AI…
LLMs Can Now Reason in Parallel: UC Berkeley and UCSF Researchers Introduce Adaptive Parallel Reasoning to Scale Inference Efficiently Without Exceeding Context Windows
Large language models (LLMs) have made significant strides in reasoning capabilities, exemplified by breakthrough systems like OpenAI o1 and DeepSeekR1, which utilize test-time compute for search and reinforcement learning to optimize performance. Despite this progress, current methodologies face critical challenges that impede their effectiveness. Serialized chain-of-thought approaches generate excessively long output sequences, increasing latency and…
Now it’s TikTok parent ByteDance’s turn for a reasoning AI: enter Seed-Thinking-v1.5!
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More It started with the announcement of OpenAI’s o1 model in Sept. 2024, but really took off with the DeepSeek R1 release in Jan. 2025. Now, it seems that most major AI model providers and trainers are…
TxAgent: An AI Agent that Delivers Evidence-Grounded Treatment Recommendations by Combining Multi-Step Reasoning with Real-Time Biomedical Tool Integration
Precision therapy has emerged as a critical approach in healthcare, tailoring treatments to individual patient profiles to optimise outcomes while reducing risks. However, determining the appropriate medication involves a complex analysis of numerous factors: patient characteristics, comorbidities, potential drug interactions, contraindications, current clinical guidelines, drug mechanisms, and disease biology. While Large Language Models (LLMs) have…
This AI Paper Introduces R1-Onevision: A Cross-Modal Formalization Model for Advancing Multimodal Reasoning and Structured Visual Interpretation
Multimodal reasoning is an evolving field that integrates visual and textual data to enhance machine intelligence. Traditional artificial intelligence models excel at processing either text or images but often struggle when required to reason across both formats. Analyzing charts, graphs, mathematical symbols, and complex visual patterns alongside textual descriptions is crucial for applications in education,…
This AI Paper from Menlo Research Introduces AlphaMaze: A Two-Stage Training Framework for Enhancing Spatial Reasoning in Large Language Models
Artificial intelligence continues to advance in natural language processing but still faces challenges in spatial reasoning tasks. Visual-spatial reasoning is fundamental for robotics, autonomous navigation, and interactive problem-solving applications. AI systems must effectively interpret structured environments and execute sequential decisions to function in these domains. While traditional maze-solving algorithms, such as depth-first search and A*,…
Reinforcement Learning Meets Chain-of-Thought: Transforming LLMs into Autonomous Reasoning Agents
Large Language Models (LLMs) have significantly advanced natural language processing (NLP), excelling at text generation, translation, and summarization tasks. However, their ability to engage in logical reasoning remains a challenge. Traditional LLMs, designed to predict the next word, rely on statistical pattern recognition rather than structured reasoning. This limits their ability to solve complex problems…
Together AI’s $305M bet: Reasoning models like DeepSeek-R1 are increasing, not decreasing, GPU demand
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More When DeepSeek-R1 first emerged, the prevailing fear that shook the industry was that advanced reasoning could be achieved with less infrastructure. As it turns out, that’s not necessarily the case. At least, according to Together AI,…
This AI Paper from UC Berkeley Introduces a Data-Efficient Approach to Long Chain-of-Thought Reasoning for Large Language Models
Large language models (LLMs) process extensive datasets to generate coherent outputs, focusing on refining chain-of-thought (CoT) reasoning. This methodology enables models to break down intricate problems into sequential steps, closely emulating human-like logical reasoning. Generating structured reasoning responses has been a major challenge, often requiring extensive computational resources and large-scale datasets to achieve optimal performance….
This AI Paper Explores Long Chain-of-Thought Reasoning: Enhancing Large Language Models with Reinforcement Learning and Supervised Fine-Tuning
Large language models (LLMs) have demonstrated proficiency in solving complex problems across mathematics, scientific research, and software engineering. Chain-of-thought (CoT) prompting is pivotal in guiding models through intermediate reasoning steps before reaching conclusions. Reinforcement learning (RL) is another essential component that enables structured reasoning, allowing models to recognize and correct errors efficiently. Despite these advancements,…
- 1
- 2