← All threads

Memory Management for Agents

Methods for managing memory in LLM agents, including consolidation, compression, and learnable memory skills under budget constraints.

37 papers · 3 months

Where this stands

The written synthesis of this thread is for subscribers. Subscribe.

Results across this thread

2 reported results from the papers in this thread.

PaperBenchmarkMetricResultConditionsCode

The table is for subscribers. Subscribe to see every reported number side by side.

How this thread developed

  1. June 2026 · University of Science and Technology of China, Microsoft

    Memory as state management instead of semantic retrieval improves long-horizon agents

    Proposes a memory system based on execution-state tree, outperforming semantic retrieval.

  2. June 2026 · Stanford University, Independent Researcher

    First systematic characterization of agent memory systems across long-horizon tasks

    Provides the first systematic characterization and taxonomy of agent memory systems.

  3. June 2026 · Carnegie Mellon University, University of California, Berkeley

    Shared agent memories boost performance without coordination

    Shared repository for agent-generated trajectories boosts performance without explicit coordination.

  4. June 2026 · Johns Hopkins University, Apple

    Letting language models decide when to compact their context windows

    SelfCompact lets agents dynamically decide when to compact context using summarization and rubrics.

  5. July 2026 · Stanford University

    Treating memory management as a trainable cognitive skill boosts LLM performance 2x–4x in long-horizon tasks

    Memory management as a trainable skill improves long-horizon performance.

  6. July 2026

    Memory consolidation outperforms retention under tight budgets, but retention wins when budgets are loose.

    Formal trade-off between memory consolidation and retention under different budget regimes.

  7. 23 further papers

    Sept 2026 · Zhejiang University, Tencent

    Program repair improves when memories match repository needs and repair stages

    Introduces an adaptive memory-retrieval framework that tailors memory to repository needs and repair stages, advancing memory management for code repair agents.

  8. Sept 2026 · Massachusetts Institute of Technology, Carnegie Mellon University

    Saliency-driven workspace tokens give robots lightweight task memory

    Introduces workspace tokens as a lightweight latent memory mechanism for robots, trained via VLM distillation to capture task-salient historical info.

  9. Sept 2026

    Adaptive memory graphs improve collaboration in multi-agent language-model systems

    Graph-structured memory representation of prerequisites, actions, and outputs for agent systems.

  10. Sept 2026 · National University of Defense Technology

    Self-configured memory views improve retrieval across long conversations

    Introduces self-configured memory views that structure retrieval across long conversations, advancing memory organization techniques.

  11. Sept 2026 · Mem0

    DolphinBench measures agent memory through tasks, cost, and latency

    Benchmarks long-term memory via agent task completion, covering cost, latency, and real-world personas.

  12. Sept 2026 · Zhejiang University, Alibaba Group

    Checkpoint testing reveals hidden weaknesses in self-evolving agent memories

    Introduces checkpoint-based evaluation revealing hidden weaknesses in self-evolving agent memories.

  13. Sept 2026 · NLPR&MAIS, Institute of Automation, Chinese Academy of Sciences

    Bounded visual workspaces improve multimodal agents’ accuracy and efficiency

    Stores visual artifacts in a ledger as an alternative to appending to context, a memory management technique.

  14. Sept 2026 · Huzhou Normal University, Alibaba Group

    C3M preserves multimodal evidence across sessions within fixed memory budgets

    Introduces C3M, a memory architecture that preserves multimodal evidence across sessions under fixed storage and retrieval budgets.

    released code

14 of 37 papers shown