arXiv AI October 9, 2026 By Minghao Li, Bangyan Li, Zifan Wang, Yulong Li, Hu Xu, Gan Zhang, Jingtong Wu, Wenqiang Xu

FlowState: Execution State as Memory for Long-Horizon LLM Agents

FlowState introduces a method for long-horizon LLM agents to treat execution state as a reusable memory, preserving semantically typed state nodes and their relations while separating persistent retention from on-demand access. The system uses Incremental State Update to maintain current state and Progressive State Access to reveal historical states during reasoning, allowing agents to reassess past decisions with new information. Experiments show FlowState improves success rates on MemoryArena and pass rates on τ³‑Bench by 4.55 and 13.95 percentage points, respectively, while cutting token consumption by over 40%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 4

LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference

arXiv:2608. 02515v1 Announce Type: cross Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context.

By Zhichen Liu, Ruihan Sun, Hengjie Yang, Zipeng Wu, Zhaohan Chen, Xiaofan Zhang, Yang Xu

llms agents nlp

arXiv AI

Aug 21

Can Agent Memory Systems Track Evolving State?

arXiv:2608. 19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps.

By Xinyi Fan, Miri Liu, Ruozhen Yang, Siru Ouyang, Jiawei Han

llms rag agents benchmarks

arXiv AI

Jul 13

Shared Selective Persistent Memory for Agentic LLM Systems

arXiv:2607. 09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive.

By Sanjana Pedada, Aditya Dhavala, Neelraj Patil

llms agents data-engineering

arXiv AI

Aug 5

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.

By Yuxin Liao, Le Wu, Min Hou, Hao Liu, Han Wu, Zishu Wang

llms agents nlp

arXiv AI

Sep 10

When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents

The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.

By Shweta Mishra, Shashank Mishra

llms rag agents nlp benchmarks

arXiv Computation and Language

4d ago

LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation

arXiv:2608.12990v2 Announce Type: replace Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager c...

By Dongfang Li, Zixuan Liu, Junmai Wang, Jiahe Huang, Fuhao Li, Lin Zhang, Bonian Jia, Baotian Hu, Min Zhang

llms agents nlp benchmarks

One email a morning, machine-written

Related stories

LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference

Can Agent Memory Systems Track Evolving State?

Shared Selective Persistent Memory for Agentic LLM Systems

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents

LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation