# π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

arXiv: https://arxiv.org/abs/2605.14678 · HTML: https://mlsanity.com/paper/2605.14678/

## Key facts

- Cited by 6 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 36 of its 50 references that are in the map.
- First posted on arXiv 14 May 2026.

## 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, 30 of 36)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks](https://mlsanity.com/paper/2602.16313/) (2026)
- [SkillX: Automatically Constructing Skill Knowledge Bases for Agents](https://mlsanity.com/paper/2604.04804/) (2026)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces](https://mlsanity.com/paper/2604.05172/) (2026)
- [ClawBench: Can AI Agents Complete Everyday Online Tasks?](https://mlsanity.com/paper/2604.08523/) (2026)
- [APEX-Agents](https://mlsanity.com/paper/2601.14242/) (2026)
- [Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents](https://mlsanity.com/paper/2601.19935/) (2026)
- [KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation](https://mlsanity.com/paper/2604.08455/) (2026)
- [MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments](https://mlsanity.com/paper/2602.06075/) (2026)
- [MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization](https://mlsanity.com/paper/2603.25973/) (2026)
- [PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records](https://mlsanity.com/paper/2601.09636/) (2026)
- [EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings](https://mlsanity.com/paper/2603.13594/) (2026)
- [Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants](https://mlsanity.com/paper/2604.00842/) (2026)
- [Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History](https://mlsanity.com/paper/2602.17003/) (2026)
- [PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments](https://mlsanity.com/paper/2603.23231/) (2026)
- [Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation](https://mlsanity.com/paper/2512.06710/) (2025)
- [ClawArena: Benchmarking AI Agents in Evolving Information Environments](https://mlsanity.com/paper/2604.04202/) (2026)

## Built on by (most cited first, 6 of 6)

- [Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents](https://mlsanity.com/paper/2605.28108/) (2026)
- [JarvisBench: Always-on Intelligence Between Humans and Agents](https://mlsanity.com/paper/2608.14870/) (2026)
- [PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks](https://mlsanity.com/paper/2608.21381/) (2026)
- [Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym](https://mlsanity.com/paper/2609.37267/) (2026)
- [What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents](https://mlsanity.com/paper/2610.06406/) (2026)
- [Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training](https://mlsanity.com/paper/2610.10740/) (2026)

## Abstract (arXiv)

The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often begin with underspecified requests and leave important needs, constraints, or preferences unstated. However, existing benchmarks rarely evaluate whether agents can identify and act on such hidden intents before they are explicitly stated, especially in sustained multi-turn interactions where user needs emerge gradually. To address this gap, we introduce π-Bench, a benchmark for proactive assistance comprising 100 multi-turn tasks across 5 domain-specific user personas. By incorporating hidden user intents, inter-task dependencies, and cross-session continuity, π-Bench evaluates agents' ability to anticipate and address user needs over extended interactions, jointly measuring proactivity and task completion in long-horizon trajectories that better reflect real-world use. Experiments show (1) proactive assistance remains challenging, (2) a clear distinction between task completion and proactivity, and (3) the value of prior interaction for proactive intent resolution in later tasks.