The reviewed record of science sign in
Pith

arxiv: 2403.11322 · v5 · pith:ZXIKT7LT · submitted 2024-03-17 · cs.CL · cs.AI

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ZXIKT7LTrecord.jsonopen to challenge →

classification cs.CL cs.AI
keywords statestateflowtask-solvingactionsllmscomplexdynamicenhancing
0
0 comments X
read the original abstract

It is a notable trend to use Large Language Models (LLMs) to tackle complex tasks, e.g., tasks that require a sequence of actions and dynamic interaction with tools and external environments. In this paper, we propose StateFlow, a novel LLM-based task-solving paradigm that conceptualizes complex task-solving processes as state machines. In StateFlow, we distinguish between "process grounding" (via state and state transitions) and "sub-task solving" (through actions within a state), enhancing control and interpretability of the task-solving procedure. A state represents the status of a running process. The transitions between states are controlled by heuristic rules or decisions made by the LLM, allowing for a dynamic and adaptive progression. Upon entering a state, a series of actions is executed, involving not only calling LLMs guided by different prompts, but also the utilization of external tools as needed. Our results show that StateFlow significantly enhances LLMs' efficiency. For instance, StateFlow achieves 13% and 28% higher success rates compared to ReAct in InterCode SQL and ALFWorld benchmark, with 5x and 3x less cost respectively. We also show that StateFlow can be combined with iterative refining methods like Reflexion to further improve performance.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

    cs.CR 2025-07 unverdicted novelty 8.0

    ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.

  2. LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle

    cs.SE 2026-07 conditional novelty 7.0

    LogicHunter combines specification-driven test generation with a ReAct-based agentic oracle to discover 40 previously unknown bugs in LangChain, LlamaIndex, and CrewAI, achieving 91.17% oracle precision.

  3. GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving

    cs.LG 2026-05 unverdicted novelty 7.0

    GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.

  4. Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents

    cs.CL 2026-06 unverdicted novelty 6.0

    Autopilot enforces verifiable termination via a gated FSM scheduler and hard floor, proving that termination implies goal achievement under gate soundness, floor enforcement, and plan coverage, while cutting fabricati...

  5. SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch

    cs.AI 2026-04 unverdicted novelty 4.0

    SDOF combines an RLHF-trained intent router with a state-aware dispatcher using finite automata to constrain multi-agent orchestration, reporting 80.9% routing accuracy and 86.5% task completion on a recruitment platf...

  6. ClinQueryAgent: A Conversational Agent for Population Health Management

    cs.IR 2026-04 unverdicted novelty 4.0

    The paper introduces ClinQueryAgent, a conversational agent that converts natural language queries into database queries for population health management while keeping patient data secure, and reports its use by 128 s...

  7. From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI

    cs.CR 2026-05 unverdicted novelty 3.0

    The paper analyzes evolving security and safety threats in generative AI from content generation to agentic actions, noting that attack surfaces expand faster than defenses and that many safeguards require institution...