Can agents learn inside of their own dreams?
Agentic AI gets lost
On the failure of AI to develop world models
Memory Models: Towards Agents That Learn
Agents that truly learn from experience will be powered by memory models: models that create and curate token-space memory across model generations, trained with memory-native RL.
[Keynote 04] AgentSociety: Exploring Large Language Model Agents for Piloting Social Experiments
Letta
Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.
EMERGENCE WORLD: A Laboratory for Evaluating Long-horizon Agent Autonomy — Emergence AI
Most evaluations of AI agents look like exams: a discrete task, a clean environment, a score in minutes or hours. Emergence World is built for the opposite question—what happens when you let agents run continuously, in a shared environment with real-world signals, for weeks. It is a research platfor
On AI as model organism for human learning
I've a pretty taste for paradox
The Self-Evidencing Agent: Mind, Existence, and Predictive Processing
How the concept of self-evidencing offers a philosophical principle for understanding mind and behavior, consciousness, value, wisdom, and meaning.What is
Introducing LM Studio Bionic: the AI agent for open models
The AI agent made for open models, built to get things done.
pguso/ai-agents-from-scratch
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.
Equipping agents for the real world with Agent Skills
Discover how Anthropic builds AI agents with practical capabilities through modular skills, enabling them to handle complex real-world tasks more effectively and reliably.
[Keynote 01] A Theory of Appropriateness: Social Norms for Humans and AIs
Training AI Agents with RL | Unsloth Documentation
Learn how to train AI agents for real-world tasks using Reinforcement Learning (RL).
Look-ahead Reasoning with a Learned Model in Imperfect Information Games
Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios....
