Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
The article discusses a new technique called Causal Memory Intervention (CMI) designed for long-horizon LLM agents. CMI aims to improve memory selection by focusing on the causal usefulness of memories rather than their relevance. The proposed method shows better performance in maintaining answer quality and robustness against misleading memories compared to existing memory systems.
- ▪Causal Memory Intervention (CMI) estimates how candidate memories affect model answers under controlled interventions.
- ▪CMI selects memories that enhance task performance while suppressing irrelevant or harmful ones.
- ▪The study introduces Causal-LoCoMo, a benchmark for evaluating memory selection in long conversational data.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.17641 (cs) [Submitted on 17 May 2026] Title:Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents Authors:Saksham Sahai Srivastava View a PDF of the paper titled Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents, by Saksham Sahai Srivastava View PDF HTML (experimental) Abstract: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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
