WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents
On the map: LLM agents and tool use → Software engineering coding agents
also in 1 more
Abstract (arXiv)
Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substantial run-to-run variability. Fixing failures via environment-specific training or manual patching is costly and hard to scale. To enable self-evolving agents in user-facing service environments, we propose WISE-Flow, a workflow-centric framework that converts historical service interactions into reusable procedural experience by inducing workflows with prerequisite-augmented action blocks. At deployment, WISE-Flow aligns the agent's execution trajectory to retrieved workflows and performs prerequisite-aware feasibility reasoning to achieve state-grounded next actions. Experiments on ToolSandbox and τ2-bench show consistent improvement across base models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 32 references that are in the map. First posted on arXiv 13 Jan 2026.
Builds on
19 of 32 references.
References · 19
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
- 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
- 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
- 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
- 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
7 more
- 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
- 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
- 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 84
- 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agentscited by 69
- 2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learningcited by 52
- 2025Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agentscited by 5
- 2025JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptationcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators
- 2026It Takes Workflows to Evolve Better Workflows
- 2025(P)rior(D)yna(F)low: A Priori Dynamic Workflow Construction via Multi-Agent Collaboration
- 2026FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
- 2025Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
- 2025OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
- 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
- 2026Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language