Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows

arXiv:2609.23790 · cs.AI, cs.MA, cs.PF · Submitted 2026-09-20 · Read on arXiv

cs.AI, cs.MA, cs.PF

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: 8 pages, 3 figures, 6 tables. Code, data, and evaluation harness in github: https://github.com/vsingh45/tca-compiler

Code: https://github.com/vsingh45/tca-compiler

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 20× in this paper · explained in 1 episode
• Benchmark — 19× in this paper · explained in 2 episodes
• Total Cost of Agency — 7× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Multi-Agent System — 3× in this paper · explained in 6 episodes
• Topological Order — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Agent Memory — 2× in this paper · explained in 1 episode
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Text-to-SQL — 1× in this paper · explained in 3 episodes

Sources

• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• RouterBench: A Benchmark for Multi-LLM Routing System
• MemGPT: Towards LLMs as Operating Systems
• $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection