# Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents

arXiv: https://arxiv.org/abs/2605.25971 · HTML: https://mlsanity.com/paper/2605.25971/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 18 of 18)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://mlsanity.com/paper/2410.12361/) (2024)
- [MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents](https://mlsanity.com/paper/2506.21605/) (2025)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [General Agentic Memory Via Deep Research](https://mlsanity.com/paper/2511.18423/) (2025)
- [Sleep-time Compute: Beyond Inference Scaling at Test-time](https://mlsanity.com/paper/2504.13171/) (2025)
- [MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants](https://mlsanity.com/paper/2409.20163/) (2024)
- [MetaReflection: Learning Instructions for Language Agents using Past Reflections](https://mlsanity.com/paper/2405.13009/) (2024)
- [Lightweight LLM Agent Memory with Small Language Models](https://mlsanity.com/paper/2604.07798/) (2026)
- [ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models](https://mlsanity.com/paper/2603.19466/) (2026)

## Built on by (most cited first, 4 of 4)

- [Studying Without a Syllabus: Task-Agnostic Environment Preprocessing](https://mlsanity.com/paper/2609.10824/) (2026)
- [How Strongly Should Task State Influence an LLM Agent?](https://mlsanity.com/paper/2609.25686/) (2026)
- [Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym](https://mlsanity.com/paper/2609.37267/) (2026)
- [Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents](https://mlsanity.com/paper/2610.05266/) (2026)

## Abstract (arXiv)

While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between interactions is largely wasted, leaving agents unable to prepare for future user needs. To bridge this gap, we introduce ProAct, a proactive agent architecture that leverages idle-time compute to anticipate and fulfill likely upcoming user needs. By analyzing evolving dialogue history together with persistent memory, ProAct predicts upcoming needs and iteratively acquires information, allowing the agent to resolve knowledge gaps and prepare evidence before the user initiates a query. To rigorously evaluate proactive capabilities, we also introduce ProActEval, a comprehensive benchmark comprising 200 scenarios across 40 domains, featuring predictable need chains and diverse user cognitive profiles. Empirical results demonstrate significant advantages over reactive baselines. ProAct accelerates task completion by reducing required turns by 14.8%, decreases user effort by 11.7%, and cuts hallucination rates by 28.1% on ProActEval. Furthermore, MemBench evaluations confirm that ProAct achieves state-of-the-art reflective accuracy, underscoring its sustained and robust performance.