1 citations · 1 across the 6 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Governed Shared Memory for Multi-Agent LLM Systems
Yanki Margalit, Nurit Cohen-Inger, Erni Avram +2
Multi-agent LLM environments require robust mechanisms for shared knowledge management. This paper formalizes the fleet-memory problem and identifies four foundational failure mode…
cs.AI2026
Agents-as-Peers: Bias-Controlled LLM Evaluation as Multi-Agent Peer Assessment
Yanki Margalit, Erni Avram, Ran Taig +3
Large language model (LLM) evaluation commonly relies on fixed human-authored benchmarks or centralized human/model judges. Fixed benchmarks can age and enter model training corpor…