🧩 Cognitive Architecture - tomasz · Scour

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition 🧠LLM Reasoning

Agents Are Not Algorithms: The Tradeoffs of Decision-Time Reasoning in AI Trading 🧠LLM Reasoning

mlquants.substack.com

·13h·Substack

Anthropic Named Their Models After Poetic Forms. I Think They Accidentally Mapped the Human Brain. 🎭Anthropic Claude

github.com·1d·DEV

Agentic Embedding Systems Theory: A New Cognitive Architecture for the Problem of “AI Knowing What… 🤖AI Agents

·5d

Towards AGI: Making LLMs Better at Reasoning (1/2) 🧠LLM Reasoning

mlops.community·5d

The Geometry of Reasoning and Learning in the Age of AI [video] 💬Prompt Engineering

youtube.com·6d·Hacker News

Development of non-spatial grid-like neural codes tracks inference and intelligence 🔲Cellular Automata

Distilling a strategic-reasoning framework into 7B weights 🧠LLM Reasoning

lerugray.github.io·6d·Hacker News

Reasoning Models Don't Just Think Longer, They Move Differently 🧠LLM Reasoning

The 3 Levels Of Thinking And How To Design For Them 🔄Systems Thinking

elearninginfographics.com·4d

Mechanism-aware personalized learning intervention for short- and long-term academic outcome modeling 🔁Spaced Repetition

frontiersin.org·4d

Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models 🧠LLM Reasoning

GIM: Evaluating models via tasks that integrate multiple cognitive domains 🧠LLM Reasoning

Architecting the AI Agent Platform: A Definitive Guide 🤖AI Agents

mlops.community·5d

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models 🧠LLM Reasoning

stell2026/Anima: Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core. 🧠LLM Reasoning

github.com·3d·DEV

Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning 🧠LLM Reasoning

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics 🧠LLM Reasoning

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails 🧠LLM Reasoning

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning 🧠LLM Reasoning

Log in to enable infinite scrolling