2 papers
cs.MA2026
Origin Attribution for Unsafe Behavior in Self-Evolving Multi-Agent Coding Systems
Hanyi Yu, Jiaming Cui
As language-model-based coding agents evolve their programs and reuse code from one another, safety failures can acquire a history that extends beyond the agent in which they are d…
cs.MA2026
Beyond Tier Labels: Role- and Deployment-Dependent Model Substitution in Multi-Call LLM Workflows
Renxiang Wang, Jiaming Cui
Large multi-call LLM systems pose a scientific problem that query-level routing does not capture: the value of a model depends on where it enters a dependent computation and on the…