arXiv Machine Learning June 30, 2026 By Kuan Wang

MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation

Read the original on arXiv Machine Learning →

arXiv:2606. 29914v1 Announce Type: cross Abstract: Agent memory systems are increasingly evaluated against RAG and full-context baselines, but reported gains often mix changes in the memory method with changes in the language model, embedding model, or retrieval pipeline, making it unclear what is actually being measured.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

2d ago

MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends

arXiv:2608. 13883v1 Announce Type: new Abstract: Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion.

By Chaoqun Zhan, Qiang Zhou, Guannan Li, Zhenqiang Huang, Qianjin Wang

llms rag agents benchmarks

arXiv AI

Aug 5

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

arXiv:2608. 02613v1 Announce Type: cross Abstract: Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models.

By Jiadong Zhang, Xiaosong Ma

rag agents benchmarks data-engineering

arXiv AI

Jun 29

Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents

arXiv:2606. 27472v1 Announce Type: cross Abstract: Large language model (LLM) agents operate over long, multi-session interactions in which facts change: a user moves, a price updates, a plan is revised.

By Vedant Patel

llms agents reinforcement-learning fine-tuning

arXiv AI

Jul 24

CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents

arXiv:2607. 20458v1 Announce Type: cross Abstract: Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain everything indiscriminately or apply uniform forgetting heuristics that fail to distinguish relevant from irrelevant knowledge.

By Haowen Lai

llms rag agents benchmarks

arXiv AI

5d ago

$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

arXiv:2608. 12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation, discarding search experience after completion.

By Aofan Liu, Shiyuan Song, Yiyan Qi

llms benchmarks

arXiv AI

Jul 14

MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference

arXiv:2607. 10582v1 Announce Type: cross Abstract: Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck.

By Venkatesha Matam, Keon Kim

llms agents efficiency

Related stories

MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends

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

Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents

CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents

$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference