DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

• URL: http://arxiv.org/abs/2606.03083v1
• Date: Tue, 02 Jun 2026 03:13:50 GMT
• Title: DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees
• Abstract summary: We introduce residual experience, positing that newly acquired experience is often an incremental variation of existing knowledge.<n>We propose DeltaMem, a framework that organizes experience memory into two independent residual trees.<n>Experiments across diverse interactive environments show that DeltaMem consistently outperforms existing baselines.
• Score: 15.040112664020503
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning [20.96920050192708]
  Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction.<n>Existing experience learning methods mostly rely on single-agent loops, where the same agent executes tasks, summarizes outcomes, and determines memory content.<n>We propose EDV, an Execute-Distill-Verify framework for reliable experience learning.
  arXiv  Detail & Related papers  (2026-06-23T11:05:05Z)
• Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory [43.487137083499704]
  SkeMex is a post-deployment framework that improves medical agents through a skill-based memory without updating model weights.<n>It distills informative interaction trajectories into structured skills that encode reusable procedural knowledge.<n>It estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance.
  arXiv  Detail & Related papers  (2026-06-08T11:37:01Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline [58.585692088008905]
  MM-Lifelong is a dataset designed for Multimodal Lifelong Understanding.<n>Comprising 181.1 hours of footage, it is structured across Day, Week, and Month scales to capture varying temporal densities.
  arXiv  Detail & Related papers  (2026-03-05T18:52:12Z)
• Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation [22.803751188961865]
  We argue retrieval should move beyond similarity matching and instead operate over latent components.<n>We propose xMemory, which builds a hierarchy of intact units and maintains a searchable high-level node organisation.
  arXiv  Detail & Related papers  (2026-02-02T12:04:58Z)
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution [52.76038908826961]
  We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
  arXiv  Detail & Related papers  (2025-12-11T14:40:01Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory [57.517214479414726]
  ReasoningBank is a memory framework that distills generalizable reasoning strategies from an agent's self-judged successful and failed experiences.<n>At test time, an agent retrieves relevant memories from ReasoningBank to inform its interaction and then integrates new learnings back, enabling it to become more capable over time.<n>We introduce memory-aware test-time scaling (MaTTS), which accelerates and diversifies this learning process by scaling up the agent's interaction experience.
  arXiv  Detail & Related papers  (2025-09-29T17:51:03Z)
• DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation [4.303714963263037]
  Continuous Relation Extraction (CRE) aims to incrementally learn relation knowledge from a non-stationary stream of data. Current replay-based training paradigms prioritize all data uniformly and train memory samples through multiple rounds. We introduce the DecouPled CRE framework that decouples the process of prior information preservation and new knowledge acquisition.
  arXiv  Detail & Related papers  (2024-03-05T07:16:51Z)
• Bootstrapping a DQN Replay Memory with Synthetic Experiences [0.0]
  We present an algorithm that creates synthetic experiences in a nondeterministic discrete environment to assist the learner. The Interpolated Experience Replay is evaluated on the FrozenLake environment and we show that it can support the agent to learn faster and even better than the classic version.
  arXiv  Detail & Related papers  (2020-02-04T15:36:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.