paper-with-me

Papers

XFlow: An Executable Protocol Programming System for Reliable Multi-Agent Workflows

2026-06-11 · Hanqi Li, Jing Peng, Zijian Wang, Lu Chen, Kai Yu arxiv

LLM-based multi-agent systems increasingly coordinate planning, reasoning, tool use, and human interaction, yet their reliability remains limited. A central source of this limitation is the underspecified prompt--harness boundary. Current systems lack a principled way to decide which workflow commitments should remain in prompts and which should become harness structure. We present \textbf{XFlow}, an executable protocol programming system for reliable multi-agent workflows, and \textbf{XPF} (XFlow Protocol Format), its domain-specific protocol programming language. XFlow occupies a middle position between prompt-only orchestration and markup-like workflow descriptions. XPF remains readable as a literate protocol, but it is compiled and executed as a program. Its design keeps informal semantic work inside actors while moving selected commitments into harness structure that can be checked, preserved, and enforced. At runtime, XFlow stages uncertainty through lifecycle-governed symbols, which are typed state cells with validation and commit states. Actor outputs are mediated before they become shared state, instead of spreading through prompts, transcripts, or implicit memory. Our experiments cover Constrained Interaction, Long-Context Reasoning, and Agentic Software Engineering. They show that XFlow improves reliability by making constraints, evidence handling, and process requirements explicit and enforceable.

📄 PDF Abstract BibTeX arXiv:2606.14790

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MixFlows: principled variational inference via mixed flows

2022-05-16 · Zuheng Xu, Naitong Chen, Trevor Campbell

This work presents mixed variational flows (MixFlows), a new variational family that consists of a mixture of repeated applications of a map to an initial reference distribution. First, we provide efficient algorithms fo…

Variational Inference

VisCoder2: Building Multi-Language Visualization Coding Agents

2025-10-24 · Yuansheng Ni, Songcheng Cai, Xiangchao Chen, Jiarong Liang 외 arxiv

Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language cover…

Parametric Maxflows for Structured Sparse Learning with Convex Relaxations of Submodular Functions

2015-09-14 · Yoshinobu Kawahara, Yutaro Yamaguchi

The proximal problem for structured penalties obtained via convex relaxations of submodular functions is known to be equivalent to minimizing separable convex functions over the corresponding submodular polyhedra. In thi…

Sparse Learning

ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching

2025-12-04 · Guanbo Huang, Jingjia Mao, Fanding Huang, Fengkai Liu 외 arxiv

Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, includi…

Can We Generate Visual Programs Without Prompting LLMs?

2024-12-11 · Michal Shlapentokh-Rothman, Yu-Xiong Wang, Derek Hoiem

Visual programming prompts LLMs (large language mod-els) to generate executable code for visual tasks like visual question answering (VQA). Prompt-based methods are difficult to improve while also being unreliable and co…

Data AugmentationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)