Tagged articles
AI Reasoning
41 articles · Page 1 of 1
Tsinghua researchers introduce Algebraic World Model (AWM), a system where AI agents explore environments, form hypotheses as executable code, refine them into algebraic structures, and verify them in Lean 4, achieving 99.9% on ARC-AGI-3 with 43% of human steps and proving impossibility where LLMs hallucinate.
AI ReasoningARC-AGI-3Algebraic World Model
0 likes · 9 min read

This article explains world models as AI systems that simulate physical world rules, contrasting them with LLMs' statistical pattern matching, detailing their capabilities in reasoning, prediction, and cross-domain generalization, while noting high training costs and current limitations in complex scenarios.
AGIAI ReasoningAutonomous Driving
0 likes · 14 min read

GPT-6 Astra achieves near-perfect scores on the ARC-AGI-3 benchmark using a symbolic world model that internalizes reasoning and tool creation, but the $360-per-task compute cost and reliance on external harnesses raise questions about whether this represents genuine AGI progress or expensive brute-force engineering.
AGI benchmarkAI ReasoningARC-AGI-3
0 likes · 11 min read


Geek LabsJun 1, 2026 · Artificial Intelligence
This article introduces four recently popular GitHub open‑source projects—PiD for pixel‑level diffusion image generation, awesome‑architecture for system‑design thinking, ADHD for AI‑driven divergent thinking, and ai‑memory for cross‑agent long‑term memory—detailing their core ideas, usage, and current limitations.
AI ReasoningAI image generationGitHub
0 likes · 15 min read

The paper introduces Native Parallel Reasoner (NPR), a framework that lets language agents generate and maintain multiple reasoning paths using a three‑stage self‑distillation and parallel reinforcement‑learning training paradigm, achieving up to 4.6× speedup and significant accuracy gains across eight reasoning benchmarks.
AI ReasoningNative Parallel Reasonerbenchmark evaluation
0 likes · 18 min read

The General 365 benchmark, built from 365 original seed questions and 1,095 variants across eight reasoning challenges, reveals that most mainstream large language models struggle with everyday logical tasks, achieving at most 62.8% accuracy and requiring far more tokens than on traditional subject‑specific tests.
AI ReasoningGeneral 365LLM Evaluation
0 likes · 9 min read

The article analyzes why traditional Retrieval‑Augmented Generation fails on multi‑hop, vague, or multi‑source queries and explains how Agentic RAG uses an LLM‑driven agent loop to make dynamic retrieval decisions, outlining its architecture, suitable scenarios, and limitations.
AI ReasoningAgentic RAGLLM Agents
0 likes · 7 min read

DeepSeek has released a multimodal model built on a visual‑primitive reasoning paradigm that treats coordinates and bounding boxes as reasoning units, dramatically compresses visual tokens, and achieves state‑of‑the‑art performance on counting, spatial, and topological tasks, while exposing current limits of multimodal inference.
AI ReasoningCompressed Sparse AttentionDeepSeek
0 likes · 12 min read

The article examines whether LLMs can genuinely grasp software requirements, refutes the “stochastic parrot” critique with emergent‑ability research, presents blind‑chess and circuit‑tracing experiments, and showcases GPT‑5.5 engineering case studies that demonstrate deep logical and conceptual comprehension.
AI ReasoningGPT-5.5emergent abilities
0 likes · 11 min read

This article introduces the Tree of Thoughts (ToT) reasoning framework, explains its search‑tree based workflow, demonstrates a full implementation with LangGraph to solve the classic wolf‑goat‑cabbage puzzle, and compares its reliability against a simple Chain‑of‑Thought approach.
AI ReasoningLLMLangGraph
0 likes · 19 min read

A teenage prodigy engineered a "Thinking Claude" prompt that adds a human‑like chain‑of‑thought protocol to Claude 3.5, enabling free O1‑level reasoning and producing impressive outputs such as a functional calculator, sci‑fi story, and playable games, while the article details the prompt’s design process and usage.
AI ReasoningClaude 3.5OpenAI o1
0 likes · 8 min read

The MMKG‑RDS framework introduced by 360 AI Lab creates a complete pipeline—from multimodal document parsing and knowledge‑graph construction to customizable task synthesis and multi‑dimensional quality assessment—enabling the production of high‑quality reasoning data that significantly boosts large‑model performance across diverse domains.
AI ReasoningData Synthesisknowledge graph
0 likes · 7 min read

Google’s Gemini 3.1 Pro jumps to a 77.1% ARC‑AGI‑2 score—a 148% gain over its predecessor—offering stronger reasoning, agentic workflows, SVG generation and multimodal support, while the article compares its performance with Claude, GPT and outlines preview‑stage caveats.
AI ReasoningARC-AGI-2Agentic workflows
0 likes · 15 min read

This article explains how representing multi‑component scientific knowledge as hyperedges, rather than traditional triples, enables large language models to traverse complex material interactions, reduce hallucinations, and generate verifiable experimental designs, demonstrated through a large hypergraph built from thousands of scaffold papers.
AI ReasoningHypergraphLLM
0 likes · 7 min read

The article explains how Tree of Thoughts (ToT) lets AI explore multiple solution branches, compares it with Chain of Thought (CoT), details its four core components, outlines pros and cons, shows when to use it, and provides concrete templates and examples—including a login‑system design, novel plot branching, and the newer AoT and GoT variants.
AI ReasoningAOTCoT
0 likes · 13 min read

This article explains how Few‑shot Chain‑of‑Thought (CoT) prompting works, presents a concrete example, and introduces advanced variants such as Contrastive CoT, Complexity‑based Prompting, Active Prompting, Memory‑of‑Thought, and Automatic CoT to improve large language model reasoning accuracy.
AI ReasoningChain-of-Thoughtfew-shot
0 likes · 10 min read

This article explains the core concept of LangChain agents—combining an LLM, a set of tools, and a reasoning‑action loop—to enable dynamic decision‑making, tool invocation, and iterative observation for solving complex, multi‑step tasks.
AI ReasoningAgentsLLM
0 likes · 6 min read

Zero-shot prompting lets large language models perform tasks without examples, and by following principles of clarity and structured instructions, advanced strategies such as emotion prompting, zero-shot chain-of-thought, RE2 re-reading, Rephrase-and-Respond, role-play, and System-2 Attention can significantly improve accuracy and response quality across translation, reasoning, and QA tasks.
AI ReasoningLLMlarge language models
0 likes · 13 min read

DeepSeek R1 replaces traditional supervised fine‑tuning with a pure reinforcement‑learning pipeline, introducing the GRPO algorithm and a four‑stage training regime that dramatically lowers cost, boosts reasoning and code‑generation performance, and raises important ethical, privacy, and societal considerations for large language models.
AI ReasoningDeepSeekGRPO
0 likes · 14 min read

DeepSeek‑R1, the first peer‑reviewed large language model, leveraged a pure reinforcement‑learning framework and the novel GRPO algorithm to achieve breakthrough reasoning performance, low training cost, and widespread acclaim, culminating in a Nature magazine cover story.
AI ReasoningDeepSeekGRPO
0 likes · 14 min read

This article explores how Retrieval‑Augmented Generation (RAG) is transitioning from basic retrieve‑and‑generate pipelines to a unified architecture that incorporates reasoning chains, agent layers, knowledge graphs, Monte‑Carlo Tree Search, reinforcement learning, sophisticated memory management, and multimodal tensor‑based retrieval, while addressing engineering challenges such as storage expansion, re‑ranking, and index dimensionality.
AI ReasoningRAGRetrieval-Augmented Generation
0 likes · 19 min read

The article analyzes GPT‑5’s unified system, advanced reasoning models, and impressive benchmark gains across programming, creative writing, and health domains, highlighting its new router, Verbosity API, and record‑setting performance on tasks such as Aider polyglot, AIME 2025, and HealthBench.
AI ReasoningAI benchmarksGPT-5
0 likes · 7 min read

By rethinking how we interact with large language models—using role‑play, task decomposition, chain‑of‑thought, ReAct, and other advanced prompting strategies—readers can transform generic ChatGPT answers into precise, context‑aware responses, leveraging pattern recognition and context windows for superior AI assistance.
AI ReasoningLLM techniqueschain-of-thought
0 likes · 21 min read

Version 0.9.0 of Ollama introduces a ‘thinking’ control that lets users view and manage the AI model’s reasoning process, with detailed CLI commands, REST API usage, model support list, scripting options, and advanced Modelfile configurations for models like DeepSeek R1 and Qwen 3.
AI ReasoningDeepSeekModelfile
0 likes · 6 min read

This article surveys classic prompt‑engineering methods such as Chain‑of‑Thought, Self‑Consistency, Least‑to‑Most, Boosting of Thoughts, Tree of Thoughts, and AutoGPT, summarizing their core ideas, advantages, limitations, and experimental results to help readers understand how to enhance large language model reasoning without model fine‑tuning.
AI ReasoningSelf-Consistencychain-of-thought
0 likes · 22 min read


21CTOMar 27, 2025 · Artificial Intelligence
Google's Gemini 2.5, billed as its most intelligent AI model, introduces advanced reasoning capabilities that outperform rivals on benchmarks like LMArena and Humanity's Last Exam, excels at web and agent code generation, and is now available to premium users via AI Studio with a 1‑million token context window.
AI ReasoningGoogle Geminibenchmark performance
0 likes · 4 min read

The article examines how chain‑of‑thought (CoT) templates are evolving from short‑term heuristics to long‑range planning in large language models, highlighting recent advances such as OpenAI o1, DeepSeek R1, and Kimi 1.5, and explores template designs that boost reasoning performance, efficiency, and multimodal capabilities.
AI ReasoningEfficiencyLong CoT
0 likes · 7 min read

The paper introduces Critique Fine-Tuning (CFT), a method that replaces simple imitation in supervised fine‑tuning with critique‑based learning, achieving superior reasoning performance on mathematical benchmarks using only 50 K samples, outperforming traditional reinforcement‑learning approaches that require millions of examples.
AI ReasoningCritique Fine-TuningMathematical Benchmarks
0 likes · 7 min read

This tutorial explains how to enhance large language models' logical reasoning by using DeepSeek‑R1's deep‑thinking mode, few‑shot prompting, chain‑of‑thought, and zero‑shot chain‑of‑thought techniques, providing concrete examples, comparisons, and a step‑by‑step template for effective prompt design.
AI ReasoningDeepSeekchain-of-thought
0 likes · 10 min read

This article examines how swapping in DeepSeek‑R1 enhances Retrieval‑Augmented Generation with deeper reasoning, outlines its benefits and pitfalls—including slower inference, higher compute costs, and hallucinations—provides a simple hallucination test, and proposes an Agentic RAG research assistant to balance accuracy and creativity.
AI ReasoningAgenticDeepSeek
0 likes · 10 min read

The article examines whether the latest AI models that claim to perform true reasoning—by breaking problems into steps and using chain‑of‑thought—actually reason like humans, presenting skeptical and supportive expert viewpoints, and offering practical guidance on how to use such models responsibly.
AI ReasoningAI safetyCognitive Modeling
0 likes · 14 min read

Hybrid reasoning lets Claude 3.7 Sonnet dynamically switch between fast, intuition‑like answers and step‑by‑step, deep analysis, improving both speed and accuracy for tasks ranging from simple code snippets to complex algorithm design, and signals a broader shift in large language model capabilities.
AI ReasoningClaude 3.7Hybrid Reasoning
0 likes · 9 min read

The article explains how to use prompt‑engineering techniques on Claude 3.5 Sonnet to mimic DeepSeek‑R1’s transparent reasoning, detailing background, prompt design, iterative optimization, and the broader impact on AI communication and user expression.
AI ReasoningClaudeDeepSeek
0 likes · 25 min read

The article dissects the s1 paper that claims a sub‑$50 cloud budget can produce a reasoning model rivaling DeepSeek R1 and OpenAI o1, detailing the curated s1K dataset, the budget‑forcing inference technique, the 26‑minute fine‑tuning on Qwen2.5‑32B, performance gaps on AIME and MATH benchmarks, and the misconceptions surrounding cost and "distillation".
AI ReasoningOpen Source LLMQwen2.5-32B
0 likes · 12 min read

In a December 2024 online event titled “o1 Reasoning and the Future of Mathematics,” UCLA professor Terence Tao, OpenAI senior vice president Mark Chen, and policy lead James Donovan discuss how advanced AI reasoning models could transform mathematical research, problem solving, collaboration, and education.
AI ReasoningEducationartificial intelligence
0 likes · 41 min read

This article breaks down the replication of OpenAI’s o1 model into four phases—assessment, journey‑learning foundation, component implementation, and training—while highlighting key challenges such as building scalable long‑thought data, reward models, and policy reasoning trees, and discusses the broader impact of o1’s reasoning abilities.
AI ReasoningLLM replicationOpenAI o1
0 likes · 18 min read

OpenAI’s newly released o1 series introduces a reinforcement‑learning‑trained LLM that generates long chain‑of‑thought reasoning, achieving top‑50% scores on IOI contests, high rankings on Codeforces and AIME, and dramatically outperforming GPT‑4o across scientific and mathematical tasks.
AI ReasoningOpenAIartificial intelligence
0 likes · 8 min read

The article examines why leading large language models such as GPT‑4o, Gemini Advanced, and Claude 3.5 incorrectly claim that 9.11 is larger than 9.9, analyzes tokenization and prompting strategies that cause the error, and discusses recent research and OpenAI model updates.
AI ReasoningNumerical Comparisonlarge language models
0 likes · 7 min read

The article explains how ChatGPT’s surprising step‑by‑step reasoning, known as Chain of Thought, emerged as a technical breakthrough, links it to model scaling, cognitive System 1/2 theory, and the influence of code data in training large language models.
AI ReasoningChatGPTEmergence
0 likes · 10 min read


ArchitectFeb 18, 2023 · Artificial Intelligence
The article reviews the evolution of large language models, highlighting two major paradigm shifts after GPT‑3, the role of scaling laws, knowledge acquisition, prompting techniques, reasoning abilities, and outlines future research priorities for building more capable and efficient AI systems.
AI ReasoningModel ScalingSparse Transformers
0 likes · 71 min read

The Hulu AI team’s ICLR‑2020 paper introduces a consciousness‑prior‑driven graph neural network that dynamically prunes message‑passing subgraphs, achieving state‑of‑the‑art results on large‑scale knowledge‑graph completion tasks while improving interpretability and computational efficiency.
AI ReasoningGraph Neural Networkconsciousness prior
0 likes · 7 min read
