ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

• Computer Science > Computation and Language [Submitted on 4 Feb 2026] Title:ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following View PDF HTML (exper

Research & Labs · February 26, 2026 (updated February 26, 2026) · 2 min · 245 words
Multi-Layer Scheduling for MoE-Based LLM Reasoning

Multi-Layer Scheduling for MoE-Based LLM Reasoning

• Computer Science > Distributed, Parallel, and Cluster Computing [Submitted on 25 Feb 2026] Title:Multi-Layer Scheduling for MoE-Based LLM Reasoning View PDF HTML (experimental)Ab

Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem

Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem

• Computer Science > Artificial Intelligence [Submitted on 25 Feb 2026] Title:Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem V

Research & Labs · February 26, 2026 (updated February 26, 2026) · 2 min · 229 words
Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning

Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning

• Computer Science > Machine Learning [Submitted on 22 Feb 2026] Title:Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning View PDF HTML (experimental)Abstract

Research & Labs · February 25, 2026 (updated February 25, 2026) · 2 min · 246 words
KairosVL: Orchestrating Time Series and Semantics for Unified Reasoning

KairosVL: Orchestrating Time Series and Semantics for Unified Reasoning

• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:KairosVL: Orchestrating Time Series and Semantics for Unified Reasoning View PDF HTML (experimental)Ab

Research & Labs · February 25, 2026 (updated February 25, 2026) · 2 min · 293 words
Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates

Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates

• Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Tar

Symbolic analysis of Grover search algorithm via Chain-of-Thought reasoning and quantum-native tokenization

• Subjects Mathematics and computing Physics Abstract Understanding the high-level conceptual structure of quantum algorithms from their low-level circuit representations is a crit

Quantum Computing · February 24, 2026 (updated February 24, 2026) · 2 min · 257 words
The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics

The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics

• The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics AuthorsGregor Bachmann, Yichen Jiang, Seye

Neurosymbolic Language Reasoning as Satisfiability Modulo Theory

Neurosymbolic Language Reasoning as Satisfiability Modulo Theory

• Computer Science > Artificial Intelligence [Submitted on 20 Feb 2026] Title:Neurosymbolic Language Reasoning as Satisfiability Modulo Theory View PDF HTML (experimental)Abstract:

Research & Labs · February 23, 2026 (updated February 24, 2026) · 2 min · 254 words
The Token Games: Evaluating Language Model Reasoning with Puzzle Duels

The Token Games: Evaluating Language Model Reasoning with Puzzle Duels

• Computer Science > Artificial Intelligence [Submitted on 19 Feb 2026] Title:The Token Games: Evaluating Language Model Reasoning with Puzzle Duels View PDF HTML (experimental)Abs

Research & Labs · February 23, 2026 (updated February 24, 2026) · 2 min · 273 words
Apple Workshop on Reasoning and Planning 2025

Apple Workshop on Reasoning and Planning 2025

• Reasoning and planning are the bedrock of intelligent AI systems, enabling them to plan, interact, adapt, and ultimately, operate independently. • At Apple, understanding and adv

Symbolic analysis of Grover search algorithm via Chain-of-Thought reasoning and quantum-native tokenization

• Subjects Mathematics and computing Physics Abstract Understanding the high-level conceptual structure of quantum algorithms from their low-level circuit representations is a crit

Quantum Computing · February 22, 2026 (updated February 23, 2026) · 2 min · 250 words
LLM-WikiRace: Benchmarking Long-term Planning and Reasoning over Real-World Knowledge Graphs

LLM-WikiRace: Benchmarking Long-term Planning and Reasoning over Real-World Knowledge Graphs

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:LLM-WikiRace: Benchmarking Long-term Planning and Reasoning over Real-World Knowledge Graphs View PDF

Research & Labs · February 20, 2026 (updated February 24, 2026) · 2 min · 301 words
Google's Gemini 3.1 Pro is here, and it just doubled its reasoning score

Google's Gemini 3.1 Pro is here, and it just doubled its reasoning score

• Google’s Gemini 3.1 Pro is here, and it just doubled its reasoning score Follow ZDNET:Add us as a preferred sourceon Google. • ZDNET’s key takeaways Gemini 3.1 Pro is now availab

Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination

Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 253 words
Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination

Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 221 words
Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Tre

Research & Labs · February 19, 2026 (updated February 24, 2026) · 2 min · 256 words
Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Tre

Research · February 19, 2026 (updated February 19, 2026) · 2 min · 241 words
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing L

Research · February 18, 2026 (updated February 19, 2026) · 2 min · 241 words
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing L

Research & Labs · February 18, 2026 (updated February 24, 2026) · 2 min · 241 words
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Mind the (DH) Gap! • A Contrast in Risky Choices Between Reasoning and Conversational LLMs View PDF HT

Research · February 18, 2026 (updated February 19, 2026) · 1 min · 206 words
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

• Computer Science > Artificial Intelligence [Submitted on 16 Feb 2026] Title:Mind the (DH) Gap! • A Contrast in Risky Choices Between Reasoning and Conversational LLMs View PDF HT

Research & Labs · February 18, 2026 (updated February 24, 2026) · 1 min · 206 words
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

• Computer Science > Artificial Intelligence [Submitted on 29 Jan 2026] Title:Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains View PDF HTML (exp

Research & Labs · February 17, 2026 (updated February 24, 2026) · 2 min · 223 words
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

• Computer Science > Artificial Intelligence [Submitted on 29 Jan 2026] Title:Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains View PDF HTML (exp

Research · February 17, 2026 (updated February 19, 2026) · 2 min · 223 words
ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

• Computer Science > Artificial Intelligence [Submitted on 5 Feb 2026] Title:ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs View PDF HTML (e

Research & Labs · February 17, 2026 (updated February 24, 2026) · 2 min · 232 words
ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

• Computer Science > Artificial Intelligence [Submitted on 5 Feb 2026] Title:ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs View PDF HTML (e

Research · February 17, 2026 (updated February 19, 2026) · 2 min · 232 words
Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

• Computer Science > Artificial Intelligence [Submitted on 23 Jan 2026] Title:Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning View PDF HTML (experimental)Abstr

Research · February 17, 2026 (updated February 19, 2026) · 2 min · 243 words
Trace Length is a Simple Uncertainty Signal in Reasoning Models

Trace Length is a Simple Uncertainty Signal in Reasoning Models

• Trace Length is a Simple Uncertainty Signal in Reasoning Models Trace Length is a Simple Uncertainty Signal in Reasoning Models AuthorsSiddhartha Devicâ , Charlotte Pealeâ ¡, Ar

NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

• NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI +56 NVIDIA today releasedCosmos Reason 2, the latest advancement in open, reasoning vision language models for phy

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

• Humans excel at processing vast arrays of visual information, a skill that is crucial for achieving artificial general intelligence (AGI). • Over the decades, AI researchers have

Research · July 20, 2024 (updated February 19, 2026) · 2 min · 248 words