# Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering

arXiv: https://arxiv.org/abs/2609.12039 · HTML: https://mlsanity.com/paper/2609.12039/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 123 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 25 of 25)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition](https://mlsanity.com/paper/2504.21801/) (2025)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Preserving Statistical Validity in Adaptive Data Analysis](https://mlsanity.com/paper/1411.2664/) (2014)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [Feedback Loops With Language Models Drive In-Context Reward Hacking](https://mlsanity.com/paper/2402.06627/) (2024)
- [The Ladder: A Reliable Leaderboard for Machine Learning Competitions](https://mlsanity.com/paper/1502.04585/) (2015)
- [We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs](https://mlsanity.com/paper/2406.10279/) (2024)
- [Incomplete Contracting and AI Alignment](https://mlsanity.com/paper/1804.04268/) (2018)
- [The Art, Science, and Engineering of Fuzzing: A Survey](https://mlsanity.com/paper/1812.00140/) (2018)
- [Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study](https://mlsanity.com/paper/2503.15223/) (2025)
- [Chaos Engineering](https://mlsanity.com/paper/1702.05843/) (2017)
- [Specifications: The missing link to making the development of LLM systems an engineering discipline](https://mlsanity.com/paper/2412.05299/) (2024)
- [Engineering Trustworthy Self-Adaptive Software with Dynamic Assurance Cases](https://mlsanity.com/paper/1703.06350/) (2017)
- [Perpetual Assurances for Self-Adaptive Systems](https://mlsanity.com/paper/1903.04771/) (2019)
- [Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems](https://mlsanity.com/paper/2605.23109/) (2026)

## Abstract (arXiv)

Software development follows an implementation-verification loop in which developers or agents iteratively revise an implementation until an evaluator, such as a test suite, accepts it. The evaluator checks the implementation against a set of requirements under a model of the deployment environment. Yet even a formal proof that the implementation satisfies the requirements under the model cannot guarantee acceptable behavior after deployment. Requirements only approximate stakeholder intent, and the model only approximates the real deployment environment. We call these together - requirement gap and model gap - the two-gap framework, which unifies the main failure modes of agentic software engineer-ing: reward hacking exploits omissions in the requirements or model, while hallucination widens the gaps by fabricating requirements or environment assumptions. Because neither gap can generally be certified closed in an open, changing world, the goal shifts from closing them to continuously narrowing them. We therefore propose an assurance-revision loop that uses deployment evidence to revise the requirements, model, or evaluator when stakeholders reject the resulting behavior. We then cast assured agentic development as a resource-allocation problem over human judgment, agent capability, and compute. The two principal bottlenecks mirror the two gaps: human judgment for the requirement gap and faithful, costly evaluation for the model gap. Reality remains the final verifier: acceptable behavior under actual deployment conditions is the ultimate test, while predeployment evaluations remain proxies for it.