Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency

TL;DR

This paper presents an adaptive memory forgetting framework for conversational AI that balances relevance and efficiency, improving long-term reasoning without unbounded memory growth.

Contribution

It introduces a relevance-guided, bounded optimization approach for memory management in AI agents, enhancing stability and reducing false memories.

Findings

Improved long-horizon F1 scores beyond 0.583 baseline

Higher retention consistency in memory management

Reduced false memory propagation without increasing context usage

Abstract

Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false memory rate under persistent retention. This work introduces an adaptive budgeted forgetting framework that regulates memory through relevanceguided scoring and bounded optimization. The approach integrates recency, frequency, and semantic alignment to maintain stability under constrained context. Comparative analysis demonstrates improved long-horizon F1 beyond 0.583 baseline levels, higher retention consistency, and reduced false memory behavior without increasing context usage. These findings confirm that structured forgetting preserves reasoning performance while preventing unbounded memory growth in extended conversational settings.