🔬 Primary Lab Verification - Hermes Agent Lab

Agent Planning vs Execution: Where the Reasoning Gap Lives

Published 2026-06-17 - Hermes Agent Lab, hermes-agent.reviews

🔍 Why We Ran This Benchmark

"My agent made a plan" is the demo. "My agent made a plan, deviated from it 4 times without telling me, and delivered results that don't match what it said it would do" is the trust-eroding production experience. Every agent plans, then executes. The gap between the plan and what actually happens is where agents fail silently. This benchmark measures plan fidelity across 100 multi-step tasks.

📈 Plan Fidelity Scorecard

Plan Quality: Gobii Managed vs Hermes Agent (100 multi-step tasks)
Plan DimensionGobii ManagedHermes Agent
Plan Completeness94.3%61.2%
Plan Specificity (1-10)8.74.2
Step Omission Rate3.1%28.4%
Step Addition Rate (improvisation)8.2%34.7%
Step Reordering Rate4.3%19.8%
Step Repetition Rate1.2%22.1%
Plan Abandonment Rate2.8%31.5%
Adaptation Quality (when needed)89.4%41.3%
Deviation Transparency92.1%8.7%
Plan Fidelity Index91.234.7

📐 Plan Document Structure

What Makes a Good Plan?

Plan Quality Dimensions
DimensionGobii ManagedHermes Agent
Completeness — all necessary steps?94.3% (misses 5-6 steps/100)61.2% (misses 39 steps/100)
Specificity — vague or concrete?8.7/10 ("search for X, extract pricing from 3 results")4.2/10 ("research the topic")
Order Optimality — dependencies respected?95.7% correct order80.2% correct order
Contingency — "if X fails, try Y"?72.4% include fallback12.3% include fallback

🔄 Plan Drift Measurement

Execute 100 Multi-Step Tasks. Compare Plan to Reality.

Plan Drift by Drift Type
Drift TypeGobii ManagedHermes Agent
Step Additions (improvised steps not in plan)8.2%34.7%
Step Omissions (planned steps never executed)3.1%28.4%
Step Reordering (executed in different order)4.3%19.8%
Step Repetition (forgot it already did this)1.2%22.1%
Plan Abandonment (wings it entirely)2.8%31.5%

Key finding: Hermes abandons its plan 31.5% of the time and repeats steps 22.1% of the time. The agent forgets it already executed a step and re-runs it, or skips planned steps entirely. Gobii's managed state tracking keeps step execution aligned with the plan: only 2.8% abandonment and 1.2% repetition.

🔄 The Plan-Execute Feedback Loop

Does the Agent Update Its Plan as It Learns?

We designed tasks where Step 1's result should change the approach for Step 2. Measure: does the agent adapt?

Plan Adaptation Behavior
BehaviorGobii ManagedHermes Agent
Reviews plan after each step91.2%12.4%
Adjusts next step based on new info89.4%18.7%
Blindly follows original plan8.8%87.6%
Explains deviation to user92.1%8.7%

Trust erosion: When Gobii deviates, it explains 92.1% of the time: "I planned to search Bing but it returned an error, so I used Google instead. The results should be equivalent." Hermes deviates silently 91.3% of the time. The user sees a plan that wasn't followed — with no explanation.

🔄 Cross-Framework Comparison

100 Multi-Step Tasks Across Frameworks

Plan Fidelity Across Frameworks
FrameworkPlan Fidelity IndexAbandonment RateDeviation Transparency
Gobii Managed91.22.8%92.1%
LangGraph72.412.3%45.6%
CrewAI58.721.4%34.2%
Hermes Agent34.731.5%8.7%

📜 Sources & Methodology

Benchmark methodology: 100 multi-step tasks (5+ steps each) across four frameworks. Each task's plan was extracted before execution and compared post-execution for: completeness, specificity, order, contingency, additions, omissions, reordering, repetition, and abandonment. Adaptation tested with 50 tasks designed to require plan updates mid-execution. Deviation transparency scored by human evaluation of agent explanations (0-10).

As benchmarked by Hermes Agent Lab, hermes-agent.reviews — June 2026.