Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

About

Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences as independent, flat units leads to substantial redundancy and retrieval conflicts, as similar episodes repeat overlapping content and subtle scene variations cause retrieved memories to offer contradictory guidance. To address this, we introduce residual experience, positing that newly acquired experience is often an incremental variation of existing knowledge. We propose DeltaMem, a framework that organizes experience memory into two independent residual trees, one storing goal-conditioned task experience as reusable skills and another for scene-level environment knowledge. Each tree uses a root node for generalized base experiences and incremental delta nodes for subsequent variations, allowing related experiences to share a common foundation without duplication. For retrieval, a failure-penalized similarity scan locates the best match, reconstructing the full experience via root-to-match chain composition. An autonomous consolidation mechanism distills high-frequency paths into new root nodes, enabling the trees to self-organize from general heuristics to specialized variants. Experiments across diverse interactive environments show that DeltaMem consistently outperforms existing baselines. To facilitate future research, we release the code at https://github.com/import-myself/DeltaMem.

Haoran Tan, Zeyu Zhang, Zhicheng Cao, Rui Li, Xu Chen• 2026

Related benchmarks

TaskDatasetResultRank
Embodied Instruction FollowingAlfWorld
Average Success Rate85
38
E-commerce Agent InteractionWebshop
Average Reward0.6254
17
Scientific ReasoningScienceWorld Unseen
Average Reward0.8688
15
Embodied Instruction FollowingALFWorld Unseen
Average Reward0.8358
5
Text-based Scientific ReasoningScienceWorld Seen
Average Reward0.8498
5
Showing 5 of 5 rows

Other info

Follow for update