The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
cs.AI
Submitted: 2026-07-08
Updated: 2026-10-05
Code: https://github.com/NousResearch/hermes-agent
Terminology
Sources
- Scaling Laws for Neural Language Models
- Training Compute-Optimal Large Language Models
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- RouteLLM: Learning to Route LLMs with Preference Data
- Token-Budget-Aware LLM Reasoning
- Chain of Draft: Thinking Faster by Writing Less
- MemGPT: Towards LLMs as Operating Systems
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
- Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
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