4 papers · 1 filter
Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
Theo Rusu, Sourena Khanzadeh, Manar Alalfi
Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption that representing conversations…
Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI
Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1
Modern AI systems bring societal risks such as mass surveillance, extreme concentrations of power, and loss of user autonomy---calling into question a model where third-parties col…
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
Sourena Khanzadeh
As Large Language Model (LLM) agents are increasingly tasked with high-stakes autonomous decision-making, the transparency of their reasoning processes has become a critical safety…
Breadth-First Search vs. Restarting Random Walks for Escaping Uninformed Heuristic Regions
Daniel Platnick, Dawson Tomasz, Eamon Earl +2
Greedy search methods like Greedy Best-First Search (GBFS) and Enforced Hill-Climbing (EHC) often struggle when faced with Uninformed Heuristic Regions (UHRs) like heuristic local…