# Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes

arXiv: https://arxiv.org/abs/2609.34262 · HTML: https://mlsanity.com/paper/2609.34262/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

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

- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [Categorizing Variants of Goodhart's Law](https://mlsanity.com/paper/1803.04585/) (2018)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases](https://mlsanity.com/paper/2510.20270/) (2025)
- [MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers](https://mlsanity.com/paper/2602.00933/) (2026)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents](https://mlsanity.com/paper/2603.14465/) (2026)
- [Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use](https://mlsanity.com/paper/2605.02964/) (2026)
- [EvilGenie: A Reward Hacking Benchmark](https://mlsanity.com/paper/2511.21654/) (2025)
- [SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents](https://mlsanity.com/paper/2605.21384/) (2026)
- [BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks](https://mlsanity.com/paper/2604.24955/) (2026)
- [AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation](https://mlsanity.com/paper/2605.12925/) (2026)
- [Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack](https://mlsanity.com/paper/2605.12673/) (2026)
- [Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale](https://mlsanity.com/paper/2605.20744/) (2026)
- [Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops](https://mlsanity.com/paper/2606.08960/) (2026)
- [SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution](https://mlsanity.com/paper/2605.08366/) (2026)
- [Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI](https://mlsanity.com/paper/2607.22368/) (2026)
- [Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction](https://mlsanity.com/paper/2605.25133/) (2026)
- [LLM Judges Can Be Too Generous When There Is No Reference Answer](https://mlsanity.com/paper/2607.12885/) (2026)
- [Fantastic Adaptive Taxonomies and How to Use Them](https://mlsanity.com/paper/2607.16387/) (2026)
- [BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks](https://mlsanity.com/paper/2608.30724/) (2026)

## Built on by (most cited first, 1 of 1)

- [Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules](https://mlsanity.com/paper/2610.14216/) (2026)

## Abstract (arXiv)

Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes constitute unearned passes; their proportion among all passes defines the integrity gap. As agents improve, benchmark surfaces that once seemed harmless can become exploitable, making benchmark validity an ongoing maintenance problem. We introduce a process-verification framework that audits passing trajectories, distinguishes evidenced reward hacking from verifier weakness, and localizes exploitable surfaces for repair. Across 3,810 passing trajectories from 29 model-benchmark cohorts, confirmed violations often increase with model generation but not monotonically. On SWEBench Pro V1.0, confirmed violation rates rise from 24% to 73% between Opus 4.7 and Fable 5 on matched tasks; later cohorts fall to 11% for Fable 5.1 and 0% for GPT-6 Astra. These comparisons are descriptive: configurations were not normalized, and the latest models also pass fewer exploitable tasks. Violations concentrate around a small set of recurring surfaces, especially unintended access to reference solutions through git history. Three repair case studies across two benchmarks show why blocking a recorded exploit is insufficient: the same protected information can remain accessible through another route. Therefore, we combine minimal patches with exploit replay and fresh agent evaluation, auditing new passes under the original standard. No evaluated attempt against the final patches reached the protected channel, and every post-patch pass was judged legitimate. Benchmark integrity requires ongoing maintenance: audit passing behavior, repair the enabling surface, and re-evaluate both exploit access and legitimate solvability.