When Is Smaller Greener? Right-Sizing Language Models for Agentic AI
cs.AI, cs.MA
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AutoMix: Automatically Mixing Language Models
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Small Language Models are the Future of Agentic AI
- The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
- Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
- Measuring the environmental impact of delivering AI at Google Scale
- RouterBench: A Benchmark for Multi-LLM Routing System
- How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference
- HugSelect: An Explainable Multi-Criteria Decision-Support Framework for foundation-model selection
- AI Agents That Matter
- Measuring AI Ability to Complete Long Software Tasks
- ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
- How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making
- Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
- GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization
- The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
- Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
- $\tau$-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
- Agents' Last Exam
- 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