collaborators
Showing cs.MAShow all

5 papers · 1 filter

cs.MA2026

When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizations

Jose Manuel de la Chica Rodriguez, Jairo Rodriguez Arias, Spyridon Chouliaras

Standard automation ROI misses four categories of systemic risk -- tacit knowledge erosion, resilience reduction, regulatory exposure, and socio-institutional capital degradation -…

cs.MA2026

When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems

Jose Manuel de la Chica, Juan Manuel Vera, Jairo Rodríguez

Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evalu…

cs.MA2026

Selection as Power: Constrained Reinforcement for Bounded Decision Authority

Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz

Selection as Power argued that upstream selection authority, rather than internal objective misalignment, constitutes a primary source of risk in high-stakes agentic systems. Howev…

cs.MA2026

Towards Selection as Power: Bounding Decision Authority in Autonomous Agents

Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz

Autonomous agentic systems are increasingly deployed in regulated, high-stakes domains where decisions may be irreversible and institutionally constrained. Existing safety approach…

cs.MA2026

Self-Evolving Coordination Protocol in Multi-Agent AI Systems: An Exploratory Systems Feasibility Study

Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz

Contemporary multi-agent systems increasingly rely on internal coordination mechanisms to combine, arbitrate, or constrain the outputs of heterogeneous components. In safety-critic…