DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks

DAEDALUS bootstraps reusable agent memory from self-generated practice tasks without oracles, improving success rates by up to 15.9 points across benchmarks.

Antoine Edy, Max Conti, Victor Xing, Marc-Antoine Allard and 2 more

Published Oct 6, 2026 · ▲ 5 on Hugging Face · Code

Capability-Driven Self-Evolution of Agent Memory

PrisMem drives agent memory self-evolution via capability-specific guidance, dependency-aware selection, and trace-guided integration, outperforming baselines by up to 10.54 points on million-token benchmarks.

Yaoqi Chen, Yuru Feng, Qianxi Zhang, Baotong Lu and 7 more

Published Oct 5, 2026 · ▲ 6 on Hugging Face

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

MemAdapter counters memory-induced sycophancy via counterfactual induction, context-aware reflection, and evidence-based reasoning to improve memory reliability across diverse scenarios.

Ruqing Ning, Haibo Meng, Zhishang Xiang, Zerui Chen and 3 more

Published Oct 4, 2026 · ▲ 27 on Hugging Face · Code ★ 21

Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States

PoS maintains explicit belief states for long-horizon LLM agents, detects belief trapping, and recovers to achieve top results across four benchmarks.

Yu Luo, Jiamin Jiang, Yimin Zuo, Xidao Wen and 8 more

Published Oct 1, 2026 · 0 citations · ▲ 93 on Hugging Face · Code ★ 28

When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model

Raw-turn selection via a typed decision model matches LLM extraction at tight budgets but falls behind at generous budgets, explaining conflicting memory results.

Rishabh Sharma, Rishika Lall

Published Sep 28, 2026 · 0 citations · ▲ 11 on Hugging Face · Code ★ 1

Grounding Memory Summarization in Utility Intent

MemSuit improves memory summarization by self-distilling query-conditioned utility awareness into raw-conversation entries and decomposing blocks to prevent collateral erasure, boosting answer quality across query types.

Zhenyu Lei, Mingjia Shi, Xingbo Fu, Haoyu He and 2 more

Published Aug 20, 2026 · 0 citations

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

ReasoningBank distills reasoning strategies from agent successes and failures into a retrievable memory bank that improves over time, with memory-aware test-time scaling amplifying gains across web and software benchmarks.

Siru Ouyang, Yan, Jun, I-Hung Hsu, Yanfei Chen and 13 more

Published Sep 29, 2025 · 0 citations · ▲ 15 on Hugging Face

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Separating domain volatility from observation surprise via composite homeostatic-allostatic gates improves recency-shift detection and limits false updates, with linking and verification dominating memory errors.

Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh and 1 more

Published Apr 28, 2025 · 7 citations · ▲ 73 on Hugging Face · Code ★ 66,727

Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory

Jie Lin, Xiang Liu, Lihao Liu, Liansheng Wang

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

Zhuohan Gu, Qizheng Zhang, Omar Khattab, Samuel Madden

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory

Saman Forouzandeh, Wei Peng, Xinghuo Yu, Mahdi Jalili

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t

Jingyu Liu, Zongze Li, Zach Xu, Zhanhui Zhou and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Beyond Raw Observations: Distilling and Storing Invariant Driving Memories for Generalizable Autonomous Driving

Xue Zhao, Cewu Lu, Xinbing Wang, Nanyang Ye

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems

Geer Yang, Xixuan Liu, Bin Wu, Shaojiang Wang

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MGMem: An Efficient, Deterministic, and Provenance-Preserving Framework for Long-Horizon Agent Memory

Junhong Huang, Xin Tong, Jun Xia

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents

Jian Zhong, Zeyu Liu, Pingchuan Cao, Rongduo Han and 7 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TransMem: Transition-Aware Retrieval for Evolving Personal Memory

Shigeng Chen, LINHAO LUO, Changlong Shi, Zhangchi Qiu and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MemCode: Discrete Semantic Representations for Long-Term Agent Memory

Xin Li, Liang Hu, Duoqian Miao, Ming Peng and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory

Tong Zhao, Chenghao Zhang, Yucheng Tian, Yuyang Hu and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory

Junhan Shi, Qiyi Wang, Xiongwei Wu, Ming Ma and 7 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory

Charley Li, Alice Cao

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

NeuroMem: A Neuroplastic Memory Framework for Lifelong Agents through Delayed Consolidation

Yingyi Cheng, Xueqiang Han, Chen Yu

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Memory is Not Search: Towards Proactive, Lifelong Memory in AI

Will Xiao, Sanket Deshpande, Guha Mahesh, Spandan Madan and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TIMA: Test-Time Internalization for Agentic Memory

Xiaohang Sui, Yongjian Fu, Yizhe Zhao, Sheng Yue and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Git Context Controller: Manage the Context of Agents by Agentic Git

Junde Wu, Minhao Hu, Jiayuan Zhu, Shengda Zhu and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Hyunji Lee, Justin Chen, Joykirat Singh, Zaid Khan and 2 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

The Butterfly Effect in Reasoning: Branch-Structured Distributional Memory for Stochastic Agents

Ishan Jindal, Vivek Dhamale, Mahesh Chandran

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Remembering What Matters: From Markovian to Subtask-Causal Memory in VLA Policies

Peishuo Wang, Fengshuo Bai, Yufeng Li, Tawei Chou and 6 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

ADMIT: Support-Gated Memory-Write Admission for Document QA Agents

Joongmin Shin, Gyuho Shim, Hyeonseok Moon, Jaehyung Seo

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Learning to Continually Learn via Meta-learning Agentic Memory Designs

ALMA meta-learns executable memory designs for agentic systems, outperforming hand-crafted alternatives across sequential decision-making benchmarks.

Yiming Xiong, Shengran Hu, Jeff Clune

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 8 on Hugging Face · Code ★ 295

When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory

Scale-conditioned evaluation reveals agent memory reliability degrades differently by interface, agent, and budget as irrelevant sessions accumulate.

Jiaqi Shao, Yiyi Lu, Yunzhen Zhang, Bing Luo

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

MemForest partitions agent memory into event trees and progressively merges redundant nodes to cut storage and retrieval costs while preserving nearly all performance.

JunXi Wang, Jiayi Zhu, Te Sun, Chen Zhang and 8 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models

ECHO uses a hyperbolic continuous hierarchical memory tree to improve VLA long-horizon manipulation, boosting LIBERO-Long success by 12.8%.

Yanbin Hu, Jin Cui, Jiayi Lu, Ruixuan Yang and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents

Memory-R2 proposes LoGo-GRPO to enable fair credit assignment for memory-augmented LLM agents across long multi-session horizons via local rerollouts and shared-parameter co-learning.

Sikuan Yan, Ahmed Bahloul, Ercong Nie, Susanna Schwarzmann and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

SkeMex improves medical agents via self-evolving skill memory that distills reusable procedural knowledge, governs retention by utility, and outperforms memory-based agents across clinical tasks.

Haoran Sun, Wenjie Li, Yujie Zhang, Zekai Lin and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face

Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees

UQ-DAAAM introduces object-level semantic uncertainty for multi-view VLM memory and actively refines uncertain descriptions under a fixed budget with probabilistic guarantees, improving spatio-temporal reasoning.

Harry Zhang, Nicolas Gorlo, Luca Carlone

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory

ForecastCompass organizes forecasting experience into reusable predictive factors and calibration principles via adaptive memory, improving agentic forecasting accuracy and calibration.

Yurui Chang, Yongkang Du, Yuanpu Cao, Jinghui Chen and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction

WorldMemArena evaluates multimodal agent memory through an action-world loop, showing writing and storage improvements do not guarantee performance and harness-based memory remains costly and unreliable.

Chengzhi Liu, Yuzhe YANG, Sophia Xiao Pu, Yepeng Liu and 15 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 29

MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare

MedMemoryBench introduces a streaming benchmark with synthetic long-horizon medical trajectories to evaluate agent memory, revealing severe bottlenecks in reasoning and noise resilience due to memory saturation.

Yihao Wang, Haoran Xu, Renjie Gu, Yixuan Ye and 9 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

DocAtlas: Long-Document Understanding as Mutable-State Interaction

DocAtlas treats long-document understanding as a mutable-state interaction process via a document harness with search, memory, and review tools, reaching 71.4% on MMLongBench-Doc and boosting a 4B VLM to 63.7% via reinforcement learning.

Hongchen Wei, Yuanzhe Wang, Bei Liu, Yifan Yang and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 12

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

xMemory decouples agent memories into reusable components before aggregating them hierarchically, improving retrieval quality and token efficiency over flat RAG.

Zhanghao Hu, Qinglin Zhu, Runcong Zhao, Di Liang and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 20 on Hugging Face

EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision

EgoStream introduces a diagnostic benchmark for streaming egocentric episodic memory with 2,250 questions across seven cognitive dimensions and an Answer Validity Window, finding that current memory mechanisms achieve only around 45% accuracy while operating far below real-time requirements.

Rosario Forte, Giuseppe Lando, Antonino Furnari

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents

Linguistic Trajectory Encoding compresses long-horizon object motion into hybrid language-spatial-visual timelines, outperforming baselines on multi-day spatial memory benchmarks with high compression and sub-second queries.

Xie Tianyidan, Shenyi Wang, Qiang Tang, Mingjie Wang and 6 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Useful Memories Become Faulty When Continuously Updated by LLMs

LLM-updated agent memories degrade with repeated consolidation, often dropping below baselines; retaining raw episodic traces doubles accuracy versus forced consolidation.

Dylan Zhang, Yanshan Lin, Zhengkun Wu, Yihang Sun and 3 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 18 on Hugging Face

The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory

Proposed E-P-R framework diagnoses AI agents consuming conflicting memory via entry-propagation-recovery, finding a compliance trap where early adoption collapses success.

Yixiong Chen, Xinyi Bai, Alan Yuille

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SkillOS: Learning Skill Curation for Self-Evolving Agents

SkillOS uses RL to train a skill curator that updates an external SkillRepo from experience, improving self-evolving agents across reasoning and multi-turn tasks.

Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han and 12 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 45 on Hugging Face

GLOVE: Global Verifier for LLM Memory-Environment Realignment

GLOVE verifies LLM memory consistency via active probing against fresh observations, improving agent success rates without ground-truth supervision.

XINGKUN YIN, Hongyang Du

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Personal Visual Memory from Explicit and Implicit Evidence

VisualMem adds structured personal visual memory to text backends, improving personalized agent recall of explicit and implicit visual evidence.

Viet Nguyen, Thao Nguyen, Vishal Patel, Yuheng Li

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

MAGE externalizes self-knowledge into co-evolutionary knowledge graphs that guide frozen-learner agents, achieving strong multi-benchmark gains via complementary success and correction memories.

Ruiyi Yang, Zechen Li, Hao Xue, Imran Razzak and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

EvoMemBench benchmarks LLM agent memory via self-evolving scope and content axes, finding no universal memory method and that long-context baselines remain competitive.

Yuyao Wang, Zhongjian Zhang, Mo Chi, Kaichi Yu and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory

MemCoRe organizes agent memory as a compression hierarchy to recover evidence from progressively compressed factual knowledge, outperforming state-of-the-art memory baselines.

Zhenyuan Zhang, Jia Xianzhang, Zhiqin Yang, Zhenbo Song and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face

MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing

MEMAUDIT provides an exact package-oracle protocol isolating budgeted long-term memory writing via certified finite optimization, separating representational quality and validity preservation from retrieval and reasoning effects.

Nishant Bhargava, Rodrigo S Barrento

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

M$^\star$: Every Task Deserves Its Own Memory Harness

M* evolves task-specific memory programs via reflective code search to outperform fixed-memory agents across diverse benchmarks. Evolved harnesses develop structurally distinct mechanisms per domain, showing specialization beats general-purpose memory.

Wenbo Pan, Shujie LIU, Xiangyang Zhou, Xianlong Wang and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale

MemArena benchmarks on-device ego-centric personal memory assistants via simulated multi-session agents, showing memory backend choice dominates accuracy and permission-aware access fails universally.

Jiadong Zhang, Xiaosong Ma

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 1

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

TrajWiki represents memory as source-grounded evolution trajectories with claim-level updates and a wiki layer to improve long-horizon dialogue performance and interpretability.

Jingyu Sun, Yuyang Xue, Mingyang Li, Zhengtao Yao and 8 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

MemSkill learns and evolves reusable memory skills for extracting and revising agent memories via selection, execution, and design loops, improving long-context task performance.

Haozhen Zhang, Quanyu Long, Jianzhu Bao, Tao Feng and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 64 on Hugging Face · Code ★ 582

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

Metacognitive Memory Policy Optimization uses belief entropy to penalize uncertain intermediate summaries, improving long-horizon LLM agent reasoning and retaining 97.1% performance at 1.75M-token contexts.

Ziyan Liu, Zhezheng Hao, Yeqiu Chen, Hong Wang and 6 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 7 on Hugging Face