🧩 Cognitive Architecture - tomasz · Scour

Position: AI as Part of Self -- Extending the Mind Requires Cognitive Co-Regulation 🎭Anthropic Claude

Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs 🧠LLM Reasoning

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP 🧠LLM Reasoning

Self-supervised Hierarchical Visual Reasoning with World Model 🧠LLM Reasoning

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory 🧠LLM Reasoning

CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning 🧠LLM Reasoning

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road 🧠LLM Reasoning

Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning 🧠LLM Reasoning

Leveraging Latent Visual Reasoning in Silence 🧠LLM Reasoning

Video Models Can Reason with Verifiable Rewards 🧠LLM Reasoning

Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification 🧠LLM Reasoning

SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents 🔄Cybernetic Economics

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions 👥Crowdsourcing

Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers 💬Prompt Engineering

MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models 🧠LLM Reasoning

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning 🧠LLM Reasoning

Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR 💬Prompt Engineering

The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning 🧠LLM Reasoning

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs 🤖AI Agents

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning 🧠LLM Reasoning

Log in to enable infinite scrolling