AI
Applying Anthropic Primitives at Large Enterprises: Harness Paradigm for Knowledge Work
Researchers propose an architecture for large enterprises to use the 'harness paradigm' as a way to ...
AI
SAGE: A Unified Algebra and Self-Adaptive Execution for AI Functions in SQL
Researchers have developed SAGE, a unified framework for integrating AI functions into SQL systems. ...
AI
Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents
Researchers have developed a new hierarchical memory system called Weighted Memory Tree (WMT) to hel...
AI
Beyond Effectiveness: A Multi-Criteria Framework for Comparing Practical Socio-Technical Interventions
Researchers have proposed many interventions to address issues like content moderation and misinform...
AI
Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance
Researchers have developed an auditable framework for trustworthy large language...
AI
DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents
A new benchmark called DreamBench-SWE has been developed to test the memory hygi...
AI
Why2Speak: Faithful Reasoning for Abstaining Action Policies
Researchers have developed a method to study how artificial intelligence systems...
AI
CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery
A new AI approach called Certification-Driven Reinforcement Learning (CDRL) has ...