Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Payal Fofadiya, Sunil Tiwari

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.

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

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.

Paper Structure

This paper contains 17 sections, 5 equations, 4 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Proposed Methodology
  4. Problem Formulation
  5. Relevance Scoring and Memory Importance
  6. Controlled Forgetting Under Budget Constraint
  7. Adaptive Decay Modeling
  8. Performance–Memory Tradeoff Objective
  9. Mathematical Memory Selection Procedure
  10. Theoretical Stability Analysis
  11. Experimental Setup
  12. Results and Analysis
  13. Memory Budget Sensitivity Analysis
  14. False Memory and Retention Stability Analysis
  15. Ablation Study
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Architecture of the Adaptive Budgeted Forgetting Framework. The system integrates multi-layer memory organization, adaptive relevance-guided control, and budget-constrained selection to maintain long-horizon consistency under fixed memory constraints.
  • Figure 2: Benchmark results across LOCOMO, LOCCO, and MultiWOZ 2.4 highlighting long-horizon reasoning performance, memory decay behavior, and false memory rates.
  • Figure 3: Proposed method across key performance metrics, with solid-line overlay highlighting relative improvement trends.
  • Figure 4: LOCOMO F1, LOCCO retention, MultiWOZ accuracy, and False Memory Rate (FMR) for prior work and the proposed framework.