🧩 Cognitive Science - 2601 · Scour

The Reasoning Harness: Preserving What's Understood, Not Just What's Said, in Human-AI Collaboration 🧠Symbolic AI

michael124.substack.com·2d·Substack

Gradual Cognitive Externalization: A Framework for Understanding How Ambient Intelligence Externalizes Human Cognition 🔄Systems Thinking

arxiv.org·3d

AI Assistance Reduces Persistence and Hurts Independent Performance 💡Explainable AI

ai-project-website.github.io·1d·Hacker News

Designing life science assessments in the era of generative artificial intelligence 💬Prompt Engineering

journals.plos.org·2d·Hacker News

Large Language Models Align with the Human Brain during Creative Thinking 💬Prompt Engineering

arxiv.org·3d

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection 🪜Recursive Descent

arxiv.org·2d

Contextual Control without Memory Growth in a Context-Switching Task 🐍Mamba SSM

arxiv.org·3d

Beyond Behavior: Why AI Evaluation Needs a Cognitive Revolution 🧠Symbolic AI

arxiv.org·2d

Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not 🌱Minimal ML

arxiv.org·3d

When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't ✨Effect Inference

arxiv.org·1d

Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries 💬Prompt Engineering

arxiv.org·1d

Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents 🧠Symbolic AI

arxiv.org·3d

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning 🧠Symbolic AI

arxiv.org·2d

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals 🪜Recursive Descent

arxiv.org·2d

Don't Blink: Evidence Collapse during Multimodal Reasoning ⚖️Inference Rules

arxiv.org·3d

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability 🧠Symbolic AI

arxiv.org·1d

What Makes Good Multilingual Reasoning? Disentangling Reasoning Traces with Measurable Features 🧠Symbolic AI

arxiv.org·3d

Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework 💬Prompt Engineering

arxiv.org·3d

Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation 🧠Symbolic AI

arxiv.org·3d

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs 🔮Type Inference Visualization

arxiv.org·3d

Loading more...