# CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation

arXiv: https://arxiv.org/abs/2606.01815 · HTML: https://mlsanity.com/paper/2606.01815/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 12 of 12)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [UserBench: An Interactive Gym Environment for User-Centric Agents](https://mlsanity.com/paper/2507.22034/) (2025)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [Mind the Sim2Real Gap in User Simulation for Agentic Tasks](https://mlsanity.com/paper/2603.11245/) (2026)
- [BaxBench: Can LLMs Generate Correct and Secure Backends?](https://mlsanity.com/paper/2502.11844/) (2025)
- [Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations](https://mlsanity.com/paper/2601.17087/) (2026)
- [τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge](https://mlsanity.com/paper/2603.04370/) (2026)

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

- [Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent](https://mlsanity.com/paper/2609.38604/) (2026)

## Abstract (arXiv)

Evaluating LLM agents in realistic service scenarios requires complex task dependencies, imperfect user behavior, and an evaluation that accommodates multiple valid solutions. We introduce CRAB-Bench (Constraint-based Realistic Agent Benchmark) and RUSE (Realistic User Simulation Engine) to address this gap. CRAB-Bench generates tasks via a constraint graph over multiple interdependent entities with structured distractors, requiring agents to reason carefully over thousands of misleading candidates where only a tiny fraction of solutions are valid. RUSE replaces cooperative, template-like simulators with realistic users grounded in human behavioral studies, instantiated across diverse personas and four behavioral dimensions. Experiments on four frontier LLM agents show that the best model achieves only 61% pass@1 on CRAB-Bench, and switching to RUSE causes further drops of up to 57%, concentrated in task-solving ability rather than conversational quality. Information Disclosure is the most damaging behavioral dimension, and agents interacting with RUSE are less likely to admit mistakes, instead masking errors through implicit corrections.