paper-with-me

홈 › Papers

Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection

2026-06-25 · Bo Chen arxiv

LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors, schema mismatches, and heterogeneous page structures. We propose a constrained, verifiable agent framework that shifts LLM output from free-form code to typed JSON collector configurations, combining a six-type collector taxonomy, template and utility-function constraints, static Airflow DAG execution, rule-based quality checking, and structured feedback correction. Experiments on 138 tasks show that the taxonomy supports description-based requirement typing, while confirming that stable instantiation requires completing source, field, and execution constraints beyond the initial description. On 80 independently source-verified tasks, the framework runs with zero execution-stage LLM tokens and the lowest average wall-clock time, trading moderate one-shot quality for a reusable, deterministic, and verifiable execution path suited to repeated scheduled collection. These results position the framework as a reusable, low-cost, and verifiable execution path for repeated open-web data collection.

📄 PDF Abstract BibTeX arXiv:2607.00035

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

2025-05-29 · Chengqi Zheng, Jianda Chen, Yueming Lyu, Wen Zheng Terence Ng 외

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework…

DiversityEfficient Exploration

ConstrainedZero: Chance-Constrained POMDP Planning using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraints

2024-05-01 · Robert J. Moss, Arec Jamgochian, Johannes Fischer, Anthony Corso 외

To plan safely in uncertain environments, agents must balance utility with safety constraints. Safe planning problems can be modeled as a chance-constrained partially observable Markov decision process (CC-POMDP) and sol…

Collision Avoidance

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering

2026-01-30 · Chuanzhe Guo, Jingjing Wu, Sijun He, Yang Chen 외 arxiv

The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments a…

Governance-Constrained Agentic AI: Blockchain-Enforced Human Oversight for Safety-Critical Wildfire Monitoring

2026-04-05 · Ali Akarma, Toqeer Ali Syed, Salman Jan, Hammad Muneer 외 arxiv

The AI-based sensing and autonomous monitoring have become the main components of wildfire early detection, but current systems do not provide adaptive inter-agent coordination, structurally defined human control, and cr…

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning

2026-06-01 · Lichao Wang, Zhaoxing Ren, Tianzhuo Yang, Jiaming Ji 외 arxiv

As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the r…

Reinforcement Learning