Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

TL;DR

This paper presents H-EPM, a hybrid episodic-procedural memory approach that enables multi-turn tool-use agents to adaptively reuse past experiences, improving inference and reinforcement learning performance in dynamic environments.

Contribution

It introduces a novel hybrid memory strategy combining episodic and procedural knowledge, with a tool graph for better experience reuse and exploration in multi-turn agent tasks.

Findings

Up to 50% inference-time performance improvement.

Up to 40% gains in reinforcement learning on OOD tasks.

Effective experience reuse enhances policy generalization.

Abstract

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too context-specific to transfer, while tool-level reuse ignores the surrounding context and environment. In this paper, we introduce a hybrid episodic-procedural memory strategy (H-EPM) that enables experience-induced self-evolution of multi-turn tool-use policies by adaptively reusing partially overlapping successful experiences during both inference and training. Inspired by human episodic-procedural integration, we construct a tool graph from accumulated trajectories, where recurring tool-to-tool dependencies capture procedural routines and each edge is augmented with compact episodic summaries of relevant context. At inference time, the agent dynamically balances episodic recall for contextual reasoning with procedural execution for routine steps. Beyond inference, H-EPM introduces a memory-guided reinforcement learning paradigm that directly addresses a core challenge in multi-turn agent reinforcement learning, namely ineffective exploration over long trajectories. By biasing exploration toward historically successful tool transitions, H-EPM learns a stronger policy that generalizes at inference time without relying on domain-specific experience collection. Experiments show that H-EPM consistently delivers substantial inference-time gains over strong baselines across multi-turn tool-use benchmarks, reaching improvements of up to fifty percent. It also improves reinforcement learning policy performance, achieving gains of up to forty percent on out-of-distribution tasks.