Saved in:
Bibliographic Details
Main Authors: Wang, Prince Zizhuang, Jiang, Shuli
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.07645
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914461054402560
author Wang, Prince Zizhuang
Jiang, Shuli
author_facet Wang, Prince Zizhuang
Jiang, Shuli
contents The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncertain nature of user demands poses a significant challenge; agents must not only invoke tools but also iteratively refine their understanding of user intent through effective communication. While recent advances in reinforcement learning offer a path to more capable tool-use agents, existing approaches require expensive training costs and struggle with turn-level credit assignment across extended interaction horizons. To this end, we introduce PRIME (Proactive Reasoning via Iterative Memory Evolution), a gradient-free learning framework that enables continuous agent evolvement through explicit experience accumulation rather than expensive parameter optimization. PRIME distills multi-turn interaction trajectories into structured, human-readable experiences organized across three semantic zones: successful strategies, failure patterns, and user preferences. These experiences evolve through meta-level operations and guide future agent behavior via retrieval-augmented generation. Our experiments across several diverse user-centric environments demonstrate that PRIME achieves competitive performance with gradient-based methods while offering cost-efficiency and interpretability. Together, PRIME presents a practical paradigm for building proactive, collaborative agents that learn from Human-AI interaction without the computational burden of gradient-based training.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07645
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
Wang, Prince Zizhuang
Jiang, Shuli
Artificial Intelligence
The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncertain nature of user demands poses a significant challenge; agents must not only invoke tools but also iteratively refine their understanding of user intent through effective communication. While recent advances in reinforcement learning offer a path to more capable tool-use agents, existing approaches require expensive training costs and struggle with turn-level credit assignment across extended interaction horizons. To this end, we introduce PRIME (Proactive Reasoning via Iterative Memory Evolution), a gradient-free learning framework that enables continuous agent evolvement through explicit experience accumulation rather than expensive parameter optimization. PRIME distills multi-turn interaction trajectories into structured, human-readable experiences organized across three semantic zones: successful strategies, failure patterns, and user preferences. These experiences evolve through meta-level operations and guide future agent behavior via retrieval-augmented generation. Our experiments across several diverse user-centric environments demonstrate that PRIME achieves competitive performance with gradient-based methods while offering cost-efficiency and interpretability. Together, PRIME presents a practical paradigm for building proactive, collaborative agents that learn from Human-AI interaction without the computational burden of gradient-based training.
title PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
topic Artificial Intelligence
url https://arxiv.org/abs/2604.07645