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

arXiv: https://arxiv.org/abs/2604.02280 · HTML: https://mlsanity.com/paper/2604.02280/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method](https://mlsanity.com/paper/2412.09082/) (2024)
- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation](https://mlsanity.com/paper/2509.09754/) (2025)
- [Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models](https://mlsanity.com/paper/2409.19315/) (2024)

## Built on by (most cited first, 2 of 2)

- [Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents](https://mlsanity.com/paper/2606.10616/) (2026)
- [MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare](https://mlsanity.com/paper/2605.11814/) (2026)

## Abstract (arXiv)

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.