Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs
cs.AI, cs.DC
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- Small Language Models are the Future of Agentic AI
- Octopus v2: On-device language model for super agent
- LLM-assisted Agentic Edge Intelligence Framework
- TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
- CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration
- AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems
- Scaling Laws for Neural Language Models
- Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
- When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
- PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
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