# VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

arXiv: https://arxiv.org/abs/2509.26490 · HTML: https://mlsanity.com/paper/2509.26490/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [UserBench: An Interactive Gym Environment for User-Centric Agents](https://mlsanity.com/paper/2507.22034/) (2025)
- [Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents](https://mlsanity.com/paper/2402.09205/) (2024)
- [LongCat-Flash Technical Report](https://mlsanity.com/paper/2509.01322/) (2025)
- [ToolTalk: Evaluating Tool-Usage in a Conversational Setting](https://mlsanity.com/paper/2311.10775/) (2023)
- [Learning to Ask: When LLM Agents Meet Unclear Instruction](https://mlsanity.com/paper/2409.00557/) (2024)
- [ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists](https://mlsanity.com/paper/2506.01241/) (2025)
- [Introducing LongCat-Flash-Thinking: A Technical Report](https://mlsanity.com/paper/2509.18883/) (2025)
- [Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges](https://mlsanity.com/paper/2505.13328/) (2025)
- [Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?](https://mlsanity.com/paper/2406.12307/) (2024)

## Built on by (most cited first, 30 of 53)

- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [LongCat-Next: Lexicalizing Modalities as Discrete Tokens](https://mlsanity.com/paper/2603.27538/) (2026)
- [LongCat-Flash-Thinking-2601 Technical Report](https://mlsanity.com/paper/2601.16725/) (2026)
- [Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent](https://mlsanity.com/paper/2606.30616/) (2026)
- [ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking](https://mlsanity.com/paper/2601.06487/) (2026)
- [MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate](https://mlsanity.com/paper/2605.01347/) (2026)
- [Scaling Embeddings Outperforms Scaling Experts in Language Models](https://mlsanity.com/paper/2601.21204/) (2026)
- [DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training](https://mlsanity.com/paper/2604.26256/) (2026)
- [EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL](https://mlsanity.com/paper/2605.18703/) (2026)
- [Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text](https://mlsanity.com/paper/2601.10355/) (2026)
- [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://mlsanity.com/paper/2605.27141/) (2026)
- [CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents](https://mlsanity.com/paper/2606.22883/) (2026)
- [CL-bench Life: Can Language Models Learn from Real-Life Context?](https://mlsanity.com/paper/2604.27043/) (2026)
- [Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment](https://mlsanity.com/paper/2602.03100/) (2026)
- [LHAW: Controllable Underspecification for Long-Horizon Tasks](https://mlsanity.com/paper/2602.10525/) (2026)
- [Look Before You Leap: Autonomous Exploration for LLM Agents](https://mlsanity.com/paper/2605.16143/) (2026)
- [Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments](https://mlsanity.com/paper/2605.27209/) (2026)
- [Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale](https://mlsanity.com/paper/2606.15079/) (2026)
- [Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction](https://mlsanity.com/paper/2605.12070/) (2026)
- [STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics](https://mlsanity.com/paper/2605.18548/) (2026)
- [NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness](https://mlsanity.com/paper/2609.08183/) (2026)
- [CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments](https://mlsanity.com/paper/2603.28569/) (2026)
- [interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification](https://mlsanity.com/paper/2602.11202/) (2026)
- [E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios](https://mlsanity.com/paper/2607.23722/) (2026)
- [LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing](https://mlsanity.com/paper/2608.01662/) (2026)
- [EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.06197/) (2026)
- [LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories](https://mlsanity.com/paper/2608.15242/) (2026)
- [SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking](https://mlsanity.com/paper/2609.13141/) (2026)
- [DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios](https://mlsanity.com/paper/2604.25914/) (2026)
- [PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models](https://mlsanity.com/paper/2605.20873/) (2026)

## Abstract (arXiv)

As LLM-based agents are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic user interactions. To address this gap, we introduce VitaBench, a challenging benchmark that evaluates agents on versatile interactive tasks grounded in real-world settings. Drawing from daily applications in food delivery, in-store consumption, and online travel services, VitaBench presents agents with the most complex life-serving simulation environment to date, comprising 66 tools. Through a framework that eliminates domain-specific policies, we enable flexible composition of these scenarios and tools, yielding 100 cross-scenario tasks (main results) and 300 single-scenario tasks. Each task is derived from multiple real user requests and requires agents to reason across temporal and spatial dimensions, utilize complex tool sets, proactively clarify ambiguous instructions, and track shifting user intent throughout multi-turn conversations. Moreover, we propose a rubric-based sliding window evaluator, enabling robust assessment of diverse solution pathways in complex environments and stochastic interactions. Our comprehensive evaluation reveals that even the most advanced models achieve only 30% success rate on cross-scenario tasks, and less than 50% success rate on others. Overall, we believe VitaBench will serve as a valuable resource for advancing the development of AI agents in practical real-world applications. The code, dataset, and leaderboard are available at https://vitabench.github.io/