Bridging intent and execution in agentic systems

Bridging intent and execution in agentic systems - Amazon Science

Research areas

Our scientific contributions

Publications Research from our scientists and collaborators.

Conferences Our experts present and discuss cutting-edge research at scientific meetings globally.

Research areas

Our scientific contributions

Publications Research from our scientists and collaborators.

Conferences Our experts present and discuss cutting-edge research at scientific meetings globally.

News & blog

The latest from Amazon researchers

Amazon Science Blog Technical deep-dives and perspectives from our scientists.

News Research milestones and recent achievements.

The latest from Amazon researchers

Amazon Science Blog Technical deep-dives and perspectives from our scientists.

News Research milestones and recent achievements.

Amazon Research Awards

Amazon Nova AI Challenge

Research collaborations

Amazon Research Awards

Amazon Nova AI Challenge

Research collaborations

Resources

AGI Labs Meet the team building useful AI agents.

Amazon Nova Try Amazon’s frontier foundation models.

AGI Labs Meet the team building useful AI agents.

Amazon Nova Try Amazon’s frontier foundation models.

Careers Explore our open roles.

Amazon Scholars Faculty research opportunities on industry-scale technical challenges.

Postdoctoral Science Program Early-career research opportunities alongside experienced industry scientists.

Careers Explore our open roles.

Amazon Scholars Faculty research opportunities on industry-scale technical challenges.

Postdoctoral Science Program Early-career research opportunities alongside experienced industry scientists.

Bridging intent and execution in agentic systems

The harnesses that mediate between models and tools in agentic systems are becoming their own performance bottleneck, but a few simple design principles can fix what ails them.

By Gaurav Gupta, Vatshank Chaturvedi

June 8, 2026

18 min read

Share

Share

分享到微信

x

Overview by Amazon Nova

• Amazon researchers introduce Simple Strands Agent (SSA), a customizable single-agent harness designed to minimize the intent-execution gap, achieving consistent performance gains across multiple models and benchmarks.
• Key design principles include improving tool interfaces, providing feedback through diff files, and balancing internal reasoning with external interactions to enhance agent performance.
• The research highlights model-specific preferences in tool usage and the importance of adapting harnesses to align with these preferences for optimal performance.
• All elements of the SSA harness, including agent logic, tools, prompts, and model configurations, are open-sourced for reproducibility.

Was this answer helpful?

AI agent performance is not just a modeling problem; it is fundamentally a systems problem. A modern agent combines an LLM with a harness, software that mediates the LLM’s interaction with tools and manages the cycle of reasoning and feedback: you can think of the harness as the operating system around the model. As models improve, the performance bottleneck shifts from the model’s ability to reason to the harness’s ability to translate model intent into actions and reflect execution outcomes back to the model.

We formalize this bottleneck as the intent-execution gap: the mismatch between what the model intends and what the harness executes, and vice versa. For example, in trying to revise code, a model may intend to edit a single instance of a function, while the harness accidentally modifies multiple instances.

We show that minimizing this bidirectional gap — without any task-specific tuning — is sufficient to achieve state-of-the-art performance across diverse agentic benchmarks, including datasets that test real-world repository patching (SWE-Pro, SWE-Verified) and interactive terminal environments (Terminal-Bench2).

While the most visible components of the harness — such as the execution graph, which controls iterations over the thought-action-observation process, and tools — are natural candidates for improvement, we highlight that seemingly trivial implementation details lead to nontrivial fluctuations in performance. Factors such as environment interaction timeouts, infrastructure stability, and resource constraints also materially affect performance. Thus, benchmaxing, or reporting higher numbers on benchmarks, may not necessarily quantify underlying model/harness capability, as it is additionally influenced by the basic infrastructure parameters used during evaluations.

We also introduce Simple Strands Agent (SSA), a lightweight and customizable single-agent harness designed to close the gap between the performance reported in agent documentation and the performance seen in open-source implementations. SSA achieves consistent gains in performance across multiple models and benchmarks.

Finally, we show that effective agent design is not entirely model agnostic. While many principles generalize, different model families exhibit distinct preferences in tool usage, feedback interpretation, and context sensitivity, making model-harness codesign a critical factor in achieving optimal performance.

Motivations

It is well established that problem-specific customizations such as tuned prompts, tailored tools, and specialized execution graphs can improve AI models’ performance in a controlled setting (fixing all other factors, such as evaluation infrastructure). However, we observed that many such optimizations fail to transfer between models. Improvements that work for one model or version often degrade, disappear, or even regress with newer models.

This lack of transferability exposes a deeper issue: many optimizations implicitly overfit the behavior of a specific model. As models improve, these behaviors change, making such gains brittle and noncompounding.

In the context of agents, this suggests a shift in focus: rather than optimizing for current model behavior, we should identify invariant components — design principles that remain effective across model upgrades, benchmarks, and environments. To identify such invariants, we focus on the model-harness interface — the boundary where model outputs are interpreted and executed and where execution outcomes are communicated back to the model. This interface is the primary locus of failure when agent performance degrades across settings. From this perspective, two fundamental questions emerge:

1. Does the harness…