Neuro-Symbolic Dual Memory for Long-Horizon LLM Agents
Discover a neuro-symbolic dual memory framework that improves long-horizon LLM agents by reducing errors and enhancing decision-making accuracy.
DeltaLogic Benchmark Reveals Flaws in AI Belief Revision
DeltaLogic introduces a new benchmark exposing belief-revision failures in AI logical reasoning models, highlighting the need for adaptive reasoning tests.
GrandCode: AI Reaches Grandmaster Level in Coding Contests
Discover how GrandCode uses agentic reinforcement learning to surpass human grandmasters in competitive programming contests.
Designing LLM Agents for Interactive Optimization Success
Explore how LLM agents improve optimization through interactive conversations, outperforming traditional one-shot evaluation methods.
OntoKG: Advanced Ontology-Based Knowledge Graph Construction
Discover OntoKG, an ontology-driven framework using intrinsic-relational routing for scalable, reusable knowledge graph construction and AI applications.