Skip to content

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

Sep 2026 · 2 citations · 30 references
Computer Science

TL;DR

Compared with a full-context baseline using the same DeepSeek-V4-Flash model, FlowState improves the average success rate on MemoryArena and the average pass rate on $\tau^3$-Bench by 4.55 and 13.95 percentage points, respectively, while reducing total token consumption.

Abstract

Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases context costs, while compressing it risks losing details needed later, and the relevance of historical information often becomes apparent as the task progresses. To address these challenges, we propose FlowState, which treats execution state as memory that can be retained and revisited across requests, unifying current decision-making with the reuse of historical information. FlowState preserves semantically typed state nodes, their relations, and references to raw tool observations, separating persistent retention from on-demand access. Within a single execution loop, Incremental State Update (ISU) maintains the current state based on new inputs and feedback, while Progressive State Access (PSA) progressively reveals historical states and supporting evidence as needed during reasoning. Together, these mechanisms enable agents to reassess prior decisions in light of new information and guide subsequent actions. Compared with a full-context baseline using the same DeepSeek-V4-Flash model, FlowState improves the average success rate on MemoryArena and the average pass rate on $\tau^3$-Bench by 4.55 and 13.95 percentage points, respectively, while reducing total token consumption by 43.2% and 40.6%. These results demonstrate the performance and efficiency advantages of FlowState on long-horizon tasks.

View source

Similar papers

StateComp: Learning When to Compress History in Long Horizon Agents

This work proposes State Conditioned Compression (StateComp), a framework that determines when historical interactions can be safely compressed according to the current agent state, and demonstrates that it reduces total agent and summarization tokens while maintaining task performance, and achieves a 12.67-fold speedu...

Ming-Xuan Wang, Hong-Yue Chen, Ying-Long Guo et al. · 3 citations
#artificial intelligence Preprint Oct 2026

MemTrace: State-Consistent Memory for Long-Horizon Coding Agents

MemTrace is a provenance-aware memory system that preserves execution history and aligns its reuse with the evolving task (e.g., iterative cross-file repair) and repository state and retrieves only what the next action requires.

Hong-Ming Xu, Le Zhou, Zhong-He Jin et al. · 0 citations
Preprint Aug 2026

Context as an Environment: Programmatic Context Management for Long-Horizon Agents

LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to preserve before future needs are known. We present Scroll, a context...

Yin Lin, Elaine Ang, E. Zhu et al. · 3 citations

Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability

Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and new data arrives. Each situation represents an independent axis along which an agent may fail. An agent reconciling a long ledger, for example, must repeatedly read its...

Jeffrey Willette, Krishna C. Puvvada, Boris Ginsburg · 0 citations
#artificial intelligence Preprint Sep 2026

ContextRender: From Execution Dependencies to Agent Context

This work develops Tool-Flow Analysis to track how later operations reuse information from earlier tool results, providing a signal called observed reuse, andlations show that observed reuse improves task performance and retention of results reused later.

Savini Kashmira, Jayanaka L. Dantanarayana, Ling-Jia Tang et al. · 0 citations

Continuous Context Management

Results demonstrate that CCM is a viable inference paradigm for agents operating with substantially reduced retained context and that its performance can be improved through reinforcement learning with privileged full-history distillation.

William Hoy, Jing-Xuan Fan, Nurcin Celik et al. · 1 citation · ⚡1

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.