WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents

• URL: http://arxiv.org/abs/2601.08158v1
• Date: Tue, 13 Jan 2026 02:43:41 GMT
• Title: WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents
• Abstract summary: Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks.<n>We propose WISE-Flow, a feasibility-centric framework that converts historical service interactions into reusable procedural experience.
• Score: 12.014029662322152
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $τ^2$-bench show consistent improvement across base models.

Related papers

• ContextFlow: In-Context Flow Matching for Robot Manipulation [91.60992853468242]
  We introduce ContextFlow, a conditional flow-matching model that learns continuous action distributions for in-context imitation learning.<n>On LIBERO, ContextFlow outperforms ICRT by 35 percentage points in average success rate on unseen task configurations.<n>On real robots, it generalizes to unseen configurations of both single-arm and bimanual tasks, achieving 40% success on a new pen-uncapping configuration.
  arXiv  Detail & Related papers  (2026-09-06T21:53:58Z)
• From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators [17.263246226058474]
  Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment.<n>We present MetaFlow, which casts workflow generation as a meta-learning problem.<n>It trains in two stages: supervised fine-tuning on synthetic workflow data, followed by reinforcement learning with verifiable rewards.<n>The resulting model produces effective for trained tasks and exhibits strong generalization to untrained tasks and novel operator sets.
  arXiv  Detail & Related papers  (2026-06-29T14:17:09Z)
• From Specification to Execution: AI Assisted Scientific Workflow Management [0.7507031378170735]
  We present an AI-assisted approach to scientific workflow management.<n>The method introduces a structured specification phase that separates workflow intent, design, and implementation, allowing validation prior to code generation.<n>We evaluate the approach using a federated learning workflow for medical imaging, chosen for its parallel, iterative, and dependency-intensive structure.
  arXiv  Detail & Related papers  (2026-06-16T19:21:09Z)
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [67.92316850084575]
  We introduce Claw-Eval-Live, a live benchmark for workflow agents.<n>Each release is constructed from public workflow-demand signals.<n>Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts.
  arXiv  Detail & Related papers  (2026-04-30T17:23:19Z)
• WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience [2.259603972734445]
  Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and workflow orchestration.<n>Traditional methods generate from scratch for every query, leading to high cost, slow response, and poor robustness.<n>We propose an adaptive, trajectory-driven framework for automatic workflow generation that reduces token usage and improves efficiency and success rate.
  arXiv  Detail & Related papers  (2026-03-22T16:49:58Z)
• MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks [95.86122998005612]
  MiroFlow is an open-source agent framework for large language models (LLMs)<n>It incorporates an agent graph for flexible orchestration, an optional deep reasoning mode to enhance performance, and a robust execution to ensure stable and reproducible performance.<n>It consistently achieves state-of-the-art performance across multiple agent benchmarks, including GAIA, BrowseComp-EN/ZH, HLE, xBench-DeepSearch, and FutureX.
  arXiv  Detail & Related papers  (2026-02-26T09:45:04Z)
• FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning [5.153212048436295]
  LLMs can solve complex tasks through reasoning and tool use, but accurately translating these solutions into structured remains challenging.<n>We model as sequences of tool use and reformulate the problem as designing a mechanism that can both solve tasks and reliably construct them.<n>We propose an Execute-Summarize(ES) framework that decouples task execution from workflow construction.
  arXiv  Detail & Related papers  (2026-02-12T10:04:42Z)
• ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Intrinsic Adaptation [60.25542764389203]
  Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks.<n>Existing approaches, relying on manual orchestration or runtime-based patches, often struggle with poor generalization and fragmented optimization.<n>We propose ToolSelf, a novel paradigm enabling tool-driven self-readjustment.
  arXiv  Detail & Related papers  (2026-02-08T09:27:18Z)
• FlowSteer: Interactive Agentic Workflow Orchestration via End-to-End Reinforcement Learning [49.369614288007334]
  FlowSteer is an end-to-end reinforcement learning framework that takes a lightweight policy model as the agent and an executable canvas environment.<n>We show that FlowSteer significantly outperforms baselines across various tasks.
  arXiv  Detail & Related papers  (2026-02-02T05:30:42Z)
• DyFlow: Dynamic Workflow Framework for Agentic Reasoning [79.19799197382478]
  DyFlow is a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback.<n>We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation.<n>Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains.
  arXiv  Detail & Related papers  (2025-09-30T10:36:23Z)
• Agent WARPP: Workflow Adherence via Runtime Parallel Personalization [0.0]
  Large language models (LLMs) are increasingly applied in task-oriented dialogue (TOD) systems.<n>We present Adherence via Parallel Personalization, or WARPP, a training-free, modular framework that combines multi-agent runtime with orchestration.<n>By dynamically pruning conditional branches based on user attributes, the framework reduces reasoning overhead and narrows tool selection at runtime.
  arXiv  Detail & Related papers  (2025-07-23T23:27:49Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• Action Engine: Automatic Workflow Generation in FaaS [1.4185188982404757]
  Action Engine makes use of toolaugmented large language models (LLMs) at its kernel to interpret human language queries.<n>Action Engine seamlessly manages the data dependency between them, ensuring the developer's query is processed and resolved.
  arXiv  Detail & Related papers  (2024-11-29T05:54:41Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.