# Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents

arXiv: https://arxiv.org/abs/2605.17641 · HTML: https://mlsanity.com/paper/2605.17641/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 17 May 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval](https://mlsanity.com/paper/2512.16962/) (2025)

## Built on by (most cited first, 6 of 6)

- [Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents](https://mlsanity.com/paper/2606.08151/) (2026)
- [From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL](https://mlsanity.com/paper/2608.07213/) (2026)
- [Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol](https://mlsanity.com/paper/2608.20729/) (2026)
- [CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents](https://mlsanity.com/paper/2608.22577/) (2026)
- [Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval](https://mlsanity.com/paper/2610.02070/) (2026)
- [What to Admit and How to Present: Governing Persistent Memory in LLM Agents](https://mlsanity.com/paper/2610.11188/) (2026)

## Abstract (arXiv)

Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad history inclusion, treating retrieved memories as uniformly useful. This assumption is fragile because memories may be topically related while remaining irrelevant, stale, or misleading. We propose Causal Memory Intervention (CMI), a causal memory-selection technique that estimates how candidate memories affect the model's answer under controlled interventions, selecting memories that improve task performance while suppressing unstable, irrelevant, or harmful ones. To evaluate this setting, we introduce Causal-LoCoMo, a causally annotated benchmark derived from long conversational data, where each example contains a user request, a structured memory bank, useful memories, irrelevant distractors, and synthetic harmful memories. We compare CMI against vector, graph, reflection, summary, full-history, and no-memory baselines. Results show that CMI achieves a stronger balance between answer quality and robustness to misleading memory, suggesting that reliable long-term memory requires selecting context based on causal usefulness rather than relevance alone. The full framework, benchmark construction code, and experimental pipeline are available at https://github.com/Saksham4796/causal-memory-intervention.