StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents

Wenle Liao; Zhao Wang; Jingchao Zhang; Jiajie Jin; Yimeng Xu; Zhicheng Dou

cs.AISep 28, 2026

StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents

Authors: Wenle Liao, Zhao Wang, Jingchao Zhang, Jiajie Jin, Yimeng Xu, Zhicheng Dou

Organizations: Gaoling School of Artificial Intelligence Renmin University of China

Abstract

LLM-based agents have shown strong capabilities in automated data analysis and are increasingly moving toward long-horizon, multi-stage analytical workflows. However, as the analytical process evolves, constraints, variables, and conclusions remain implicitly embedded in interaction histories, making it difficult for agents to track which analytical artifacts remain valid over increasingly long horizons and changing dependencies. Consequently, stale artifacts may be silently inherited, propagating errors to downstream stages. To address this challenge, we propose StateGuard, an analytical-state validity management framework for long-horizon data agents. StateGuard externalizes evolving analytical progress into a state graph containing constraints, versioned variables, intermediate conclusions, and cross-state relations, treating each state as an executable, verifiable, and traceable object rather than textual memory alone. StateGuard maintains state validity through evidence-grounded verification and hierarchical intervention. To equip StateGuard with these capabilities, we first introduce Manager-Oriented Counterfactual Supervision, which constructs 3K state-centric trajectories through counterfactual runtime synthesis to fine-tune StateGuard for state maintenance, verification, and repair. We then apply Validity-Guided Policy Optimization, using runtime validity evidence to provide fine-grained learning signals for protocol correctness, state grounding, and intervention quality. Experiments on three diverse long-horizon data-analysis benchmarks show that StateGuard consistently improves data-agent performance while reducing dependency-induced downstream error propagation, demonstrating the advantages of explicit analytical-state management for reliable long-horizon data analysis.

Figures & tables

Figure 1: Comparison between our proposed StateGuard and linear reasoning trajectory.

Figure 2: Overview of the StateGuard framework. StateGuard externalizes analytical states during agent execution, performs evidence-grounded validity verification and hierarchical repair, learns from manager-oriented trajectories constructed via relation-based and counterfactual synthesis.

Proprietary General Agents
Method	LongDS								DAComp-DE				DABstep
	Edu.	Comm.	Soc.	Bus.	Geo.	Spo.	Avg.	DCR	Impl.		Evol.	DCR	Hard	Easy
	Edu.	Comm.	Soc.	Bus.	Geo.	Spo.	Avg.	DCR	CFS	CS	CFS	DCR	Hard	Easy
GPT-5.5	63.56	60.30	33.76	38.60	45.40	41.50	47.14	55.34	24.68	62.14	16.10	53.10	36.77	59.72
+ StateGuard	67.74	65.38	40.57	42.79	56.84	45.62	54.12	51.25	28.91	67.32	21.05	49.96	43.65	61.11
Claude Sonnet 5	64.52	57.48	37.13	32.54	40.29	38.76	44.33	60.56	27.64	55.37	19.41	56.20	32.28	77.78

Table 1: Main results on three data-analysis benchmarks. LongDS reports six-domain performance and average accuracy; DAComp-DE covers data implementation and evolution; DABstep reports hard and easy accuracy. DCR measures excess downstream error associated with incorrect upstream. Bold indicates the best result within each group, and — denotes undefined results.

Panel of Figure 3 — Figure 3: Left: ablations on training strategy and analytical-state management. Right: Top: task performance v.s. analytical-state coverage. Bottom: verification engagement across stage difficulty.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Category	Hyperparameter	Value
SFT	Backbone	Qwen3-8B
	Training trajectories	3K
	Epochs	3
	Learning rate	$5\times 10^{-5}$
	Batch size	32
RL	Algorithm	DAPO

Appendix

Table 2: Training configuration and runtime reward settings for StateGuard.

Benchmark	Baseline Worker Budget	+StateGuard Worker Budget	Manager Review
LongDS-Bench	40 / turn	40 / turn	Turn boundary
DABstep	10	15	Every 3 worker steps
DAComp-DE	50	60	Every 5 worker steps

Appendix

Table 3: Worker interaction budgets used for baseline and StateGuard evaluation. Manager actions do not consume worker steps.

Variant	Lifecycle	State	Tools	Repair	Memory	State/Check Policy
ReAct	–	–	–	–	–	–
w/o State Validity	$\times$	$\times$	$\times$	$\times$	$\times$	$\times$
Free-Form Memory	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	Free
StateGuard	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	Structured

Appendix

Table 4: Controlled analytical-state ablations. “Free” denotes an available capability without StateGuard’s prescribed state or verification policy.

Benchmark	Reviews / Task	Manager Calls / Task	Time / Manager Call
LongDS-Bench	33.1	134.5	18.4 s
DABstep	2.3	7.3	15.0 s
DAComp-DE (Impl.)	12.0	30.6	31.5 s
DAComp-DE (Evol.)	12.3	35.1	26.9 s

Appendix

Table 5: Runtime characteristics of StateGuard with DeepSeek-V4-Pro workers. Manager inference is served locally with Qwen3-8B.

Panel of Figure 4 — Figure 4: Internal runtime statistics of StateGuard with DeepSeek-V4-Pro as the worker. Left: state construction statistics, including average states per task, task coverage, and per-state content density. Right: intervention behavior, including the frequency of state hints, error hints, and repairs, as well as tool-usage coverage. Across benchmarks, StateGuard maintains dense structured analytical states while keeping explicit repair interventions sparse and selective.

Figure 5: Representative LongDS case from Global Data on Sustainable Energy . An ambiguity at Turn 3 leads to two downstream paths: the upper path propagates an inconsistent analytical base, whereas StateGuard retrieves the relevant upstream state, prompts localized recomputation, and preserves a consistent state for subsequent ranking.

Explore similar work

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
May 28, 2026Kewei Xu, Xiaoben Lu, Shuofei Qiao +4Long-Horizon Agents Data Science Agents
Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Aug 3, 2026Ziyu Ma, Hailang Huang, Shun Zou +5Long-Horizon Agents Long-Horizon Task Planning
DreamX Team, Alibaba Group
LemonHarness Technical Report
Jun 23, 2026Kailong Ren, Fubo Sun, Jiachen Liu +18Long-Horizon Agents Tool Invocation

May 28, 2026, cs.LGJ/K move · Enter open · S save

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Kewei Xu, Xiaoben Lu, Shuofei Qiao, Zihan Ding+3

Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group

Long-Horizon Agents Data Science Agents Long-Horizon Task Planning

Open paper AskPDF arXiv

Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical context over long horizons untested. We introduce LongDS, a benchmark for long-horizon, multi-turn data analysis where agents must maintain, update, restore, and compose evolving analytical states. LongDS comprises 68 tasks constructed from real-world Kaggle notebooks, spanning 2,225 turns across six domains including Geoscience, Business, and Education. Tasks are designed around state-evolution patterns (e.g., counterfactual perturbation, rollback, multi-state composition), with an average dependency span of 11.3 turns. Evaluating five state-of-the-art models, we find that the best model reaches only 48.45% average accuracy, performance drops nearly 47 points from early to late turns, and long-horizon errors account for 52%--69% of failures. Further analysis shows that additional agent steps do not necessarily improve performance, suggesting that the key bottleneck is maintaining a correct analytical state rather than increasing interaction budget. We release LongDS to support research on reliable long-horizon agentic data analysis. Code and data will be released at https://github.com/zjunlp/DataMind.

Abstract

Explore similar work

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

LemonHarness Technical Report