paper-with-me

홈 › Papers

PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent

2026-04-08 · Prince Zizhuang Wang, Shuli Jiang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.07645

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

PRIME: Policy-Reinforced Iterative Multi-agent Execution for Algorithmic Reasoning in Large Language Models

2026-01-19 · Jiawei Xu, Zhenyu Yu, Ziqian Bi, Minh Duc Pham 외 arxiv

Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforc…

PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing

2024-07-23 · Blazej Manczak, Eliott Zemour, Eric Lin, Vaikkunth Mugunthan

Deploying language models (LMs) necessitates outputs to be both high-quality and compliant with safety guidelines. Although Inference-Time Guardrails (ITG) offer solutions that shift model output distributions towards co…

In-Context LearningInstruction Following

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams

2026-05-26 · Jinzhao Li, Yinuo Chen, Wenxuan Song, Yijia Lei 외 arxiv

Recent multimodal large language models (MLLMs) achieve strong performance on reactive question answering, but real-world streaming assistants require proactive reasoning over continuous visual inputs. Existing benchmark…

Question Answering

A Primer in Post-Training Reasoning Data: What We Know About How It Works

2026-06-01 · Yaoming Li, Guangxiang Zhao, Qilong Shi, Lin Sun 외 arxiv

Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work on post-training reasoning data has grow…

Process Reinforcement through Implicit Rewards

2025-02-03 · Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang 외

Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring complex multi-step reasoni…

MathReinforcement Learning (RL)