AI Research articles

8 articles about AI Research, newest first.

• Wiki Foundation Model: Solving RAG Bottlenecks with Neural Graphs — Learn how the Wiki Foundation Model (WFM) evolves RAG by replacing sparse knowledge graphs with trainable neural graphs to enable complex multi-hop reasoning.
• Beyond GraphRAG: Exploring Runtime Graph Repair and Agentic RAG — Discover the next evolution of RAG with 'Cognition on Graph,' a research breakthrough focusing on runtime graph repair and bidirectional synergy.
• ECDYSIS: Solving Runtime Harness Failures in LLM Agents — Learn how the ECDYSIS method helps LLM agents distinguish between their own logic errors and runtime harness failures to prevent overfitting.
• Procedural Graphs: Giving AI a Blueprint for Complex Tasks — Discover how Procedural Graphs act as a self-evolving control layer, allowing LLM agents to plan and execute complex workflows with precision.
• Stop Testing Everything: How 'Task-Coevolve' Fast-Tracks AI Reasoning — Explore how adaptive validation and harness optimization allow AI to evolve faster by ignoring redundant evaluations and focusing on growth.
• The Death of Monolithic AI: The Scaffold & Harness Paradigm — Explore the shift from giant, single-model AI to modular 'Agentic' frameworks that use scaffolds and harnesses to self-evolve and solve complex problems.
• The Math of Empathy: How Harvard and MIT are Giving AI a 'Theory of Mind' — Explore how Theory of Mind (ToM) allows AI to switch between social and non-social learning to become more socially intelligent.
• MANTA: The AI Agents That Can Rewire Their Own Brains — Discover MANTA, a breakthrough in multi-agent systems that allows AI agents to dynamically change their communication network during inference.