3 papers
cs.MA2026
At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent
David Dylan, Aoife Brennan, Cian Murphy +3
Multi-agent LLM pipelines, such as Planner-Executor-Critic teams, often report gains over single agents, but these gains usually come with higher inference cost because the team ma…
cs.LG2026
Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result
Liam Byrne, David Dylan, Orla Fitzgerald +4
Personalizing a frozen large language model (LLM) to individual users is often framed as a meta-learning problem in prompt space: each user is a task, and one seeks a shared natura…
cs.AI2026
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
Darragh Quinn, David Dylan, Roisin Healy +3
Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expens…