Tag

reasoning

0 views collected around this technical thread.

DataFunTalk
DataFunTalk
Jun 3, 2025 · Artificial Intelligence

Meta‑Capability Alignment: Psychologically Inspired Training to Endow Large Language Models with Stable Reasoning

Researchers from NUS, Tsinghua and Salesforce AI Research introduce a meta‑capability alignment framework that integrates deductive, inductive and abductive reasoning via a psychology‑based triple, automatically generates and validates training data, and demonstrates over 10% accuracy gains on math, coding and scientific benchmarks for 7B and 32B models.

Artificial IntelligenceLarge Language ModelsMeta‑Capability Alignment
0 likes · 8 min read
Meta‑Capability Alignment: Psychologically Inspired Training to Endow Large Language Models with Stable Reasoning
Model Perspective
Model Perspective
May 19, 2025 · Fundamentals

Master Logical Reasoning: Methods, Fallacies, and Persuasive Argument Frameworks

This guide systematically explores deductive, inductive, analogical, and causal reasoning, outlines common logical fallacies, presents argument structures and evaluation criteria, and introduces the Toulmin model, offering readers practical tools to strengthen critical thinking and construct persuasive, well‑grounded arguments.

argumentationcritical thinkingdeductive reasoning
0 likes · 6 min read
Master Logical Reasoning: Methods, Fallacies, and Persuasive Argument Frameworks
DevOps
DevOps
May 18, 2025 · Artificial Intelligence

Why the Focus Has Shifted from AI Agents to Agentic Workflows

Although large language models have enabled AI agents that mimic human digital interactions, their commercial accuracy remains far below production standards, prompting the industry to pivot toward agentic workflows and data synthesis, which promise more reliable task automation, reasoning, and observable, auditable processes for knowledge work.

AI agentsagentic workflowsdata synthesis
0 likes · 6 min read
Why the Focus Has Shifted from AI Agents to Agentic Workflows
Java Tech Enthusiast
Java Tech Enthusiast
May 12, 2025 · Artificial Intelligence

Chain‑of‑Recursive‑Thoughts (CoRT): Boosting LLM Reasoning with Recursive Self‑Critique

The article introduces Chain‑of‑Recursive‑Thoughts (CoRT), explains how recursive self‑evaluation enhances large language model reasoning, outlines its workflow, shares GitHub resources, compares it with existing CoT methods, and reports experimental results using Mistral 3.1 24B.

AIChain-of-Recursive-ThoughtsCoRT
0 likes · 6 min read
Chain‑of‑Recursive‑Thoughts (CoRT): Boosting LLM Reasoning with Recursive Self‑Critique
DataFunTalk
DataFunTalk
Apr 25, 2025 · Artificial Intelligence

Does Reinforcement Learning Really Expand Reasoning Capacity in Large Language Models? Insights from Recent Empirical Study

Recent empirical research by Tsinghua’s LeapLab and Shanghai Jiao Tong University reveals that reinforcement‑learning‑based fine‑tuning (RLVR) improves sampling efficiency but does not extend the fundamental reasoning abilities of large language models beyond their base capabilities, as demonstrated across mathematics, code, and visual reasoning benchmarks.

AI researchLarge Language ModelsRLVR
0 likes · 12 min read
Does Reinforcement Learning Really Expand Reasoning Capacity in Large Language Models? Insights from Recent Empirical Study
AntTech
AntTech
Apr 10, 2025 · Artificial Intelligence

Ant Group Presents Four AI Research Papers at ICLR 2025 Live Showcase

At the ICLR 2025 live session in Singapore, Ant Group showcased four cutting‑edge papers—CodePlan, Animate‑X, Group Position Embedding, and OmniKV—demonstrating advances in large‑language‑model reasoning, universal character animation, layout‑aware document understanding, and efficient long‑context inference.

AI researchDocument UnderstandingLarge Language Models
0 likes · 6 min read
Ant Group Presents Four AI Research Papers at ICLR 2025 Live Showcase
AntTech
AntTech
Mar 27, 2025 · Artificial Intelligence

LMM‑R1: A Two‑Stage Reinforcement Learning Framework for Enhancing Multimodal Model Reasoning

Researchers from Ant Group, Southeast University and others introduced the open‑source LMM‑R1 framework, a two‑stage reinforcement‑learning approach that first strengthens textual reasoning and then generalizes it to multimodal tasks, achieving significant performance gains on benchmarks such as football, Sokoban, and geometry reasoning with modest GPU costs.

AILarge Language Modelsmultimodal
0 likes · 8 min read
LMM‑R1: A Two‑Stage Reinforcement Learning Framework for Enhancing Multimodal Model Reasoning
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Mar 24, 2025 · Artificial Intelligence

AI SDK 4.2 Release: New Reasoning, MCP Client, useChat Message Components, Image Generation, URL Sources, and Provider Updates

The AI SDK 4.2 release introduces powerful new features such as step‑by‑step reasoning support, a Model Context Protocol (MCP) client for tool integration, useChat message components, multimodal image generation, standardized URL sources, OpenAI Responses API support, Svelte 5 compatibility, and numerous middleware and provider enhancements, all illustrated with practical JavaScript/TypeScript examples.

AI SDKJavaScriptMCP
0 likes · 19 min read
AI SDK 4.2 Release: New Reasoning, MCP Client, useChat Message Components, Image Generation, URL Sources, and Provider Updates
Model Perspective
Model Perspective
Mar 21, 2025 · Artificial Intelligence

How DeepSeek’s Tree‑Based Reasoning Transforms AI Interaction

DeepSeek’s R1 inference mode replaces linear chain‑of‑thought with a transparent, multi‑path tree reasoning system, offering layered analysis, intent understanding, memory management, emotion detection, and hallucination mitigation, illustrated through a practical example of buying authentic cigarettes and detailed technical breakdowns.

Artificial IntelligenceLarge Language Modelshallucination
0 likes · 16 min read
How DeepSeek’s Tree‑Based Reasoning Transforms AI Interaction
AntTech
AntTech
Mar 6, 2025 · Artificial Intelligence

CodePlan: Unlocking Reasoning Potential in Large Language Models via Code‑Form Planning

The article introduces CodePlan, a novel framework that injects code‑form planning into large language model reasoning, addressing the limitations of natural‑language‑only approaches and demonstrating significant performance gains across diverse benchmark tasks.

Artificial IntelligenceCodePlanLarge Language Models
0 likes · 10 min read
CodePlan: Unlocking Reasoning Potential in Large Language Models via Code‑Form Planning
Java Tech Enthusiast
Java Tech Enthusiast
Feb 19, 2025 · Artificial Intelligence

xAI's Grok 3 Model: Benchmarks, Reasoning, and Industry Reactions

Elon Musk’s xAI introduced the Grok 3 family—trained on roughly 200,000 GPUs and offered in standard, mini and Reasoning versions—that claims top‑slot performance on math, science and coding benchmarks, outpacing Google Gemini, DeepSeek V3, Claude and OpenAI GPT‑4o, while pricing starts at $30 per month and drawing both praise for its speed and criticism for lingering hallucinations and ethical sensitivities.

AIDeepSearchGrok3
0 likes · 16 min read
xAI's Grok 3 Model: Benchmarks, Reasoning, and Industry Reactions
Cognitive Technology Team
Cognitive Technology Team
Feb 3, 2025 · Artificial Intelligence

DeepSeek R1 Introduces Group‑Related Policy Optimization for Advanced Reasoning in Large Language Models

DeepSeek AI’s new open‑source model DeepSeek‑R1 leverages a novel Group‑Related Policy Optimization (GRPO) reinforcement‑learning framework and multi‑stage training to dramatically boost complex reasoning performance, achieving AIME 2024 Pass@1 scores comparable to OpenAI’s o1 model.

AIDeepSeekGRPO
0 likes · 4 min read
DeepSeek R1 Introduces Group‑Related Policy Optimization for Advanced Reasoning in Large Language Models
DataFunTalk
DataFunTalk
Jan 27, 2025 · Artificial Intelligence

Improving AI Agent Planning and Reasoning: Challenges and Practical Solutions

The article examines current limitations of AI agents in planning and complex reasoning, critiques existing methods like COT/TOT and ReAct, and proposes practical strategies—including combined COT‑Reflection approaches, structured memory algorithms, and white‑box interaction designs—to enhance agent performance within the DataFun knowledge map framework.

AI AgentCoTData Modeling
0 likes · 3 min read
Improving AI Agent Planning and Reasoning: Challenges and Practical Solutions
Cognitive Technology Team
Cognitive Technology Team
Oct 16, 2024 · Artificial Intelligence

Large Language Models Lack Formal Reasoning Ability: Five Pieces of Evidence from the GSM‑Symbolic Benchmark

Recent research by Apple’s Iman Mirzadeh team introduces the GSM‑Symbolic benchmark, revealing that large language models, despite high scores on GSM8K, exhibit significant performance drops when problem numbers, names, or extra clauses change, indicating a lack of true formal reasoning ability.

AI safetyGSM‑SymbolicLarge Language Models
0 likes · 9 min read
Large Language Models Lack Formal Reasoning Ability: Five Pieces of Evidence from the GSM‑Symbolic Benchmark
DataFunSummit
DataFunSummit
Jul 16, 2024 · Artificial Intelligence

Knowledge Graph Construction, Reasoning, and QA for Intelligent Hypertension Diagnosis

This article presents a comprehensive exploration of knowledge‑graph‑based modeling, neural‑symbolic multi‑hop reasoning, and large‑model‑driven question answering applied to precise medication decision‑making in hypertension, detailing system architecture, experimental evaluations, real‑world deployments, and future research directions.

Medical AIhypertensionknowledge graph
0 likes · 26 min read
Knowledge Graph Construction, Reasoning, and QA for Intelligent Hypertension Diagnosis
Model Perspective
Model Perspective
Apr 16, 2024 · Fundamentals

10 Everyday Logic Patterns That Boost Decision‑Making and Communication

This article explains ten common types of logical reasoning used in daily life, describing each concept, practical scenarios, and visual examples to help readers analyze information, make better decisions, and communicate more persuasively.

Visualizationcritical thinkingdecision making
0 likes · 8 min read
10 Everyday Logic Patterns That Boost Decision‑Making and Communication
DataFunTalk
DataFunTalk
Nov 2, 2023 · Artificial Intelligence

Enhancing Language and Vision Models with External Knowledge and Tools: OREO‑LM, REVEAL, and AVIS

This article reviews recent research on augmenting language and multimodal models with external knowledge sources and tool‑calling mechanisms, covering three systems—OREO‑LM for knowledge‑graph reasoning, REVEAL for multi‑source visual‑language pretraining, and AVIS for dynamic tool selection—and their experimental results and implications.

Tool Integrationknowledge graphlanguage model
0 likes · 28 min read
Enhancing Language and Vision Models with External Knowledge and Tools: OREO‑LM, REVEAL, and AVIS
DataFunSummit
DataFunSummit
Oct 17, 2023 · Artificial Intelligence

Enhancing Vision and Language Models with External Knowledge Graphs and Tool Integration

This article reviews recent research on augmenting language and vision models by incorporating external knowledge sources such as knowledge graphs, multi‑source retrieval, and dynamic tool‑calling frameworks, presenting three systems—OREO‑LM, REVEAL, and AVIS—and their experimental results.

AI researchTool Integrationknowledge graph
0 likes · 27 min read
Enhancing Vision and Language Models with External Knowledge Graphs and Tool Integration
Baidu Geek Talk
Baidu Geek Talk
May 8, 2023 · Artificial Intelligence

Augmented Language Models: Reasoning and External Tool Utilization

The survey shows that once language models exceed roughly ten billion parameters they spontaneously acquire two complementary abilities—step‑by‑step reasoning, often elicited by chain‑of‑thought prompts or scratch‑pad training, and the capacity to invoke external tools such as search engines, calculators, or robots—enabling them to retrieve up‑to‑date information, perform complex computations, and act in the world, thereby advancing toward general artificial intelligence.

AILarge Language Modelsprompt engineering
0 likes · 20 min read
Augmented Language Models: Reasoning and External Tool Utilization