# XYEval: Agents say yes to bad advice

arXiv: https://arxiv.org/abs/2609.23939 · HTML: https://mlsanity.com/paper/2609.23939/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 46 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 30 of 37)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers](https://mlsanity.com/paper/2402.19255/) (2024)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [Dissecting Adversarial Robustness of Multimodal LM Agents](https://mlsanity.com/paper/2406.12814/) (2024)
- [SycEval: Evaluating LLM Sycophancy](https://mlsanity.com/paper/2502.08177/) (2025)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [CREPE: Open-Domain Question Answering with False Presuppositions](https://mlsanity.com/paper/2211.17257/) (2022)
- [QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?](https://mlsanity.com/paper/2503.22674/) (2025)
- [MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers](https://mlsanity.com/paper/2602.00933/) (2026)
- [(QA)2: Question Answering with Questionable Assumptions](https://mlsanity.com/paper/2212.10003/) (2022)
- [Interactive Code Generation via Test-Driven User-Intent Formalization](https://mlsanity.com/paper/2208.05950/) (2022)
- [On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback](https://mlsanity.com/paper/2411.02306/) (2024)
- [Learning to Ask: When LLM Agents Meet Unclear Instruction](https://mlsanity.com/paper/2409.00557/) (2024)
- [Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering](https://mlsanity.com/paper/2502.13069/) (2025)
- [Task Ambiguity in Humans and Language Models](https://mlsanity.com/paper/2212.10711/) (2022)
- [BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs](https://mlsanity.com/paper/2510.04721/) (2025)
- [HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?](https://mlsanity.com/paper/2604.09408/) (2026)
- [Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty](https://mlsanity.com/paper/2412.06771/) (2024)
- [Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs](https://mlsanity.com/paper/2506.07180/) (2025)
- [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://mlsanity.com/paper/2603.26233/) (2026)

## Abstract (arXiv)

Effective communication between users and AI agents is essential for human-AI collaboration. The XY problem is a well-known communication pitfall where a person asks about their attempted solution rather than their actual problem. We extend prior sycophancy evaluation to the XY problem in agentic settings, evaluating whether agents can resist plausible but misleading suggestions from users and communicate their reasoning. We introduce XYEval, a meta-evaluation framework that can transform an existing benchmark into an XY problem evaluation. We evaluate five models across six diverse benchmark suites. Agents suffer large XY drops under XY mutation across benchmarks, with relative drops reaching up to 46.7%. With τ2-bench, we further show that agent performance drops more when encountering a pedantic user who requires detailed explanations before approving a better solution. Our findings suggest that current agents lack the ability to effectively reason and communicate when facing misleading suggestions. A simple system instruction baseline that encourages awareness of XY problems only offers partial mitigation. Extensive trace analyses provide behavioral insights into how and why these XY drops occur across execution trajectories. Our results show that mitigating the XY problem remains challenging, requiring agents to both recognize user misdirection and clearly communicate the underlying problem.