arXiv AI
Jul 21
Benchmarking Agentic Newswriting via Journalistic Workflows
arXiv:2509. 00446v2 Announce Type: replace Abstract: Recent advances in autonomous digital agents from industry (e.
PACE: Publisher-Adaptive Content Extraction via Agentic Automation
PACE is an agentic framework that learns publisher‑specific extraction configurations from representative web pages and user requirements. During training it employs LLMs to analyze page structure and gather reusable extraction patterns, then creates a deterministic extractor template for inference that eliminates the need for further LLM calls. Experiments on article bodies, metadata, images, and tables show that PACE surpasses scalable non‑manual baselines and approaches the quality of manually engineered publisher‑specific parsers.
Related stories
arXiv AI
Aug 3
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction
arXiv:2607. 29677v1 Announce Type: new Abstract: Enterprise workflows increasingly rely on agents for \emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct output with source evidence as grounding metadata.
arXiv Computation and Language
Aug 31
LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages
LandingAgent is a new framework for generating landing pages that are tailored to a specific target. It uses a reference‑annotated dataset called LandingBench, which abstracts real landing pages into structured elements such as section sequences, layout patterns, tone descriptors, visual emphasis, and CTA structure. The agentic framework operates in three phases—profiling the target, building a reference‑guided wireframe, and refining the page through critique—resulting in pages that are more faithful to the target, concise, readable, aesthetically pleasing, and structurally diverse compared to direct prompting.
arXiv AI
Aug 13
GUIDE: Governed Unified Intelligence for Document-to-Artifact Generation in Enterprise Settings
arXiv:2608. 12133v1 Announce Type: new Abstract: Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images.
arXiv AI
Aug 12
DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
arXiv:2608. 10037v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents.
arXiv AI
Aug 25
FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks
arXiv:2608.22842v1 Announce Type: new Abstract: Financial document parsing requires accuracy, structural consistency, and verifiability that current benchmarks often fail to reflect. We present Finix...
arXiv AI
Jul 20
Behavioral Controllability of Agentic Models for Information Extraction: From Fixed Workflows to Reflective Agents
arXiv:2607. 15715v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for complex information-extraction tasks, yet it remains unclear whether agentic components such as reflection and memory lead to observable and controllable improvements over fixed LLM workflows.
arXiv AI
Sep 15
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
EvoOntology introduces a self‑evolving ontology layer for data agents, encapsulating the ontology as an MCP server with schema, content, and tool layers. It enables agents to query and interact with the ontology at runtime, using a builder agent for autonomous construction and a self‑evolution loop that refines the ontology through attribution‑guided edits validated by backbone‑conditional evaluation. Experiments on three data‑agent benchmarks with four LLM backbones show that EvoOntology consistently outperforms strong baselines and existing semantic‑layer approaches, effectively bridging the agent‑data gap for heterogeneous data.
arXiv AI
Jul 14
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
arXiv:2607. 10079v1 Announce Type: new Abstract: Digital Adoption Platforms (DAPs) are embedded overlays widely used on web systems to guide users through operations inside a page, helping them get started with unfamiliar interfaces quickly.
arXiv Computation and Language
Aug 25
ConvergeWriter: Data-Driven Bottom-Up Article Construction
ConvergeWriter introduces a bottom‑up, data‑driven framework for long‑form document generation that first retrieves exhaustive knowledge from a source corpus and clusters it into distinct knowledge groups. These clusters then guide the creation of a hierarchical outline and the final text, ensuring the output is strictly grounded in the retrieved material and traceable to its sources. Experiments on 14B and 32B LLMs show that this approach matches or surpasses state‑of‑the‑art baselines, especially in scenarios requiring high factual fidelity and structural coherence.
arXiv AI
Jun 6
Benchmark Everything Everywhere All at Once
arXiv:2606. 06462v1 Announce Type: new Abstract: Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance.
arXiv AI
Jun 11
NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track
arXiv:2606. 11199v1 Announce Type: cross Abstract: We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, where it was awarded Best Dynamic Evaluation in the text-to-text track.