memory consolidation

The papers

Most central to this idea first, not most recent.

• Big Techcs.AI

  AI agents learn more from human diagnosis than repeated self-review

  Agents that organize their own procedural memory as linked wiki pages, with humans diagnosing failures rather than designing schemas, pass more enterprise tasks than baselines while storing less.

  University of Illinois Urbana-Champaign, Amazon · Nov 2026

• Independentcs.CL

  Cortex folds context benefits into model weights without degrading other skills

  Cortex makes context benefits persist after removal by consolidating them into parametric model updates via prospective queries and low-rank changes.

  Oct 2026

• Academiccs.CV

  Video world model uses test-time training as persistent memory for long-range consistency

  A camera-controlled video world model uses test-time training memory to preserve observed scenes in fixed-size parameters, improving long-horizon revisit consistency.

  Meta Reality Labs, Brown University · Oct 2026

• Research Labcs.AI

  Hippocam enables LLM agents to learn from experience without parameter updates by structuring memory as nested intents and consolidating unused history.

  An LLM agent can consolidate completed intents into abstract summaries, preserve originals in a tree, and recall details on demand, enabling continual learning without parameter updates.

  Institute of Information Engineering, Chinese Academy of Sciences, University of Chinese Academy of Sciences · Oct 2026

• Chinese Techcs.LG

  Adoption-aware memory learning boosts LLM agent NPU kernel synthesis

  SAGE achieves 95.5% execution rate on NPU kernel synthesis by tracking adoption and consolidating reusable rules.

  Fudan University, University of Science and Technology of China · Sept 2026

• Chinese Techcs.AIcode

  C3M preserves multimodal evidence across sessions within fixed memory budgets

  C3M maintains a bounded active index over persistent text-image evidence with relation-aware updates and budgeted routing, improving accuracy on cross-session long-horizon tasks.

  Huzhou Normal University, Alibaba Group · Sept 2026

• Chinese Techcs.CV

  Streaming video memory works better when internalized as evolving latent tokens

  LatentStream converts streaming video memory from store-and-retrieve to retrieve-and-internalize, improving streaming video understanding.

  Nanjing University of Science and Technology, Ant Group · Sept 2026

• Independentcs.AI

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

  When evidence is long relative to the token budget, consolidating memory with Merge or Abstract improves accuracy; under loose budgets, retaining raw records is better.

  July 2026

• Big Techcs.AI

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

  MAGE improves task success rate by 7.8–20.4 percentage points and reduces token consumption by 55.1% on MemoryArena.

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

• Big Techcs.AI

  Governing memory lifecycle, not just retrieval, boosts LLM agent reuse

  Lifecycle-controlled memory improves coding-agent retrieval, bug resolution, and cost by structuring experience, gating detailed recall on struggle, and evicting details after use.

  Amazon, Yale University · Oct 2026

• Big Techcs.CV

  Compact reusable memory improves question answering over hour-long videos

  Video-EMem encodes long videos once into compact time-anchored text and sparse images, then retrieves evidence per query, improving accuracy and cutting latency.

  Zhejiang University, Microsoft Research Asia · Oct 2026

• Big Techcs.AI

  AI agents recall conversations better when memories preserve events and relationships

  A hybrid memory system combining episodic and relational memories with consolidation achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.

  Microsoft · Oct 2026

• Academiccs.CV

  System streams infinite 3D worlds that remember and restore user edits

  WorldStream combines hierarchical planning and persistent tile records to stream unbounded 3D worlds with interactive editing and deterministic revisit.

  University of Science and Technology of China, Joy Future Academy, JD · Oct 2026

• Chinese Techcs.CL

  Event-centric memory with query-aware graph augmentation boosts long-term dialogue reasoning

  QGMem stores long dialogue histories as event-indexed memory units and builds query-specific local graphs, improving retrieval, multi-hop reasoning, and conflict resolution across six benchmarks.

  Chinese Academy of Sciences, University of Chinese Academy of Sciences · Oct 2026

• AI Startupcs.AI

  Self-evolving allocation agent cuts evaluation costs in program evolution

  EvoAlloc learns from search experience to dynamically allocate evaluation resources, reducing required evaluations by 59-82% and improving final performance.

  King Abdullah University of Science and Technology (KAUST), Sakana AI · Oct 2026

• Chinese Techcs.AI

  Memory-guided framework brings differential privacy to million-token LLM inference

  DP-MIND enables private inference on million-token contexts by perturbing chunks, propagating memory, and local denoising.

  Zhejiang University, Ant Group · Oct 2026

• Chinese Techcs.CV

  Adaptive visual memory cuts multimodal reasoning costs without losing accuracy

  Adaptive selection of fine-grained visual tokens during decoding improves multimodal reasoning accuracy and efficiency compared with one-shot compression.

  City University of Hong Kong, Zhejiang University · Oct 2026

• Big Techcs.CV

  Training-free visual memory framework compresses video tokens while preserving event coherence

  KeyRec uses a bounded visual memory with a recent cache and event bank to compress video for VLMs, using 10% of the token budget while improving accuracy.

  University of Virginia, Google · Oct 2026

• Top Universitycs.RO

  Robot memory that runs by clock confuses waiting with working

  Time-sampled memory makes robots mistake idle waiting for task progress, causing early stopping during null events.

  Nanyang Technological University · Nov 2026

• Industrycs.AIcode

  AI agents follow past corrections more reliably when given explicit rules

  Forge Decision Context achieves 95% compliance by injecting behavioral rules at decision points.

  PwC, Georgian AI Lab · Nov 2026

• Big Techcs.LG

  Two-memory approach lets AI agents learn new tasks without forgetting old ones

  Separating value functions into permanent parametric and transient non-parametric features balances stability and plasticity in continual reinforcement learning.

  McGill University, Mila · Nov 2026

• Industrycode

  Memory benchmarks can hide how agents preserve and revise facts

  Aggregate accuracy hides how agent memory systems update, preserve, attribute, and temporally organize facts; four cognitive paradigms expose distinct stability-plasticity profiles.

  UNC-Chapel Hill · Sept 2026

• Top Universitycs.CL

  Self-programmed memory adapts retrieval depth to each agent query

  MemCodex improves task success by 10.1% with 3.4x fewer tokens and 2.1x faster inference.

  Université de Montréal, Mila – Quebec AI Institute · Oct 2026

• Chinese Techcs.AI

  Delayed recommendation feedback can guide useful evolution of agent memory

  Delayed recommendation feedback evolves agent memory via three-stage credit assignment, achieving +7.75% MEG.

  Harbin Institute of Technology, Alibaba Group · Sept 2026

• Chinese Techcs.AI

  Contrasting multiple trajectories sharpens skill learning for LLMs

  SkillCome improves skill evolution for language models by contrasting multiple successful and failed trajectories and using dual memory to derive reusable skills.

  Fudan University, Ant Group · Sept 2026

• Academiccs.AIcode

  Memory lets traffic-simulation agents build reusable skills without retraining

  SimSkill, a self-evolving LLM agent with episodic, procedural, and semantic memory, improves verified success on SUMO benchmarks by up to 25 percentage points.

  Jilin University · Sept 2026

• Chinese Techcs.CV

  AI video generators learn which past frames to remember for longer clips

  Long videos generated frame by frame stay coherent when the model learns which past frames to keep in memory instead of following fixed cache rules.

  Tsinghua University, ByteDance Seed · Nov 2026

• Big Techcs.AI

  Shared scheduler enables realistic training of continual-learning agents

  SCLATE enables continual-learning agent evaluation and training by coordinating benchmark and agent events on a shared simulated clock.

  Apple · Oct 2026

• Academiccs.AI

  Self-configured memory views improve retrieval across long conversations

  AutoViewMem improves conversational memory retrieval by discovering and using low-overlap semantic views to structure memories at write time.

  National University of Defense Technology · Sept 2026

• Big Techcs.AI

  Memory guidelines help language-model agents succeed consistently across repeated runs

  LLM agents averaging 77% per-run success on AppWorld pass all five runs on only 53% of tasks; self-evolving consistency guidelines raise this by 16 points same-task and 13 similar-task.

  IBM Software Innovation Lab, IBM Research · Sept 2026

• Big Techcs.AI

  Post-training can replace prompt-time schema injection for enterprise coding agents

  CRAFT uses two-stage post-training to embed schema knowledge into coding agents, improving analytics performance while reducing prompt token costs by 9x.

  Amazon Advertising Foundations, Amazon Web Services Agentic AI · June 2026

• Chinese Techcs.CL

  Tool graph memory rarely improves multi-turn agents by itself

  Tool graph memory rarely improves multi-turn tool use, and apparent gains come from extra computation rather than the stored guidance.

  Hanyang University, Hunyuan, Tencent · Oct 2026

• Chinese Techcs.LG

  Language models can learn new tasks while forgetting less

  Output entropy can replace reference-model KL as a real-time forgetting signal, and dynamic replay weighting reduces catastrophic forgetting in LLM fine-tuning.

  Beijing Jiaotong University, The Hong Kong Polytechnic University · Oct 2026

• Big Techcs.CLcode

  Persistent context graphs cut agent memory costs without extra model calls

  Storing attention-derived importance and dependency links in a lightweight persistent context graph reduces memory compaction latency by approximately 95%.

  University of California, Santa Barbara, Microsoft · Oct 2026

• Chinese Techcs.AI

  Routing Across Memory Types Makes LLM Agents More Accurate and Efficient

  A routing agent that selects among heterogeneous memory providers improves LLM agent accuracy by 10%.

  Tsinghua University, Tencent · Sept 2026

• Top Universitycs.CLcode

  Runtime research preserves details that prebuilt agent memories can lose

  Just-In-Time Agent Memory constructs query-relevant context at runtime, outperforming Ahead-of-Time systems and prior trained memory.

  Beijing Academy of Artificial Intelligence, Peking University · Sept 2026

• Academiccs.AI

  Kernel-managed memory personalizes multiple AI agents with shorter prompts

  Kernel-managed shared memory matches full-context personalization quality at a fraction of latency and token cost.

  Rutgers University · Sept 2026

• Independentcs.AI

  Smarter merging and packing improve LLM memory under tight budgets

  An online clustering method achieves 83% of full-context quality using only 32% of the tokens at a 4k budget.

  Sept 2026

• Chinese Techcs.CL

  Building LLM memory at test time beats offline memory systems for long histories

  Deferring memory construction to inference and building it progressively during reasoning improves long-context question answering with lower overhead.

  Northeastern University, Tsinghua University · Oct 2026

• Top Universitycs.AI

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

  Construction, not generation, is the dominant cost in agent memory workloads.

  Stanford University, Independent Researcher · June 2026