RSIV-Harness is a framework that keeps language model weights fixed while recursively improving the surrounding harness based on failure traces, using a four-layer evaluation to ensure stability. It addresses challenges in open-domain conversational text-to-visualization, such as ambiguous user requests, data source discovery, and iterative chart refinement. The introduced ODAC-Vis benchmark evaluates these capabilities across 640 tasks, and experiments show significant gains in executability and chart structure after a single RSIV-Harness iteration.
arXiv:2610.28282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven acr...
Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. While modern MLLMs perform well...
arXiv:2609.26208v1 Announce Type: new Abstract: Data visualization is central to analytical reasoning, but real-world analysis increasingly requires language-driven interactive interfaces rather than...
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
VisInteract introduces a new paradigm for Text-to-Visualization that treats imperfect user queries as a dynamic, interaction-driven problem, requiring the system to recover true intent through multi-turn dialogue. The authors present VisInteract-Bench, the first benchmark for interactive Text-to-Vis, featuring controlled imperfection injection, a realistic user agent, and dual-perspective automated evaluation. They also propose Vis-MCTS, an enhanced Monte Carlo Tree Search algorithm that incorporates progressive widening, cross-rollout information sharing, and dimension-aware reward decomposition, achieving significant performance gains over existing baselines.
arXiv:2608. 02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks.
TopoPilot is an agentic framework designed to automate complex scientific visualization workflows, particularly in topological data analysis and visualization. It uses a two‑agent architecture—a user‑prompt orchestrator and a verifier—to translate natural language into atomic backend actions and ensure semantic consistency before execution. The system incorporates deterministic guardrails and a taxonomy of failure modes, achieving over 95% success in 1,000 simulated multi‑turn conversations and outperforming baseline models and other code generation tools in accuracy, completion time, and token usage.
arXiv:2512. 11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space.
arXiv:2510. 04514v3 Announce Type: replace Abstract: Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts.
arXiv:2609.24094v1 Announce Type: cross Abstract: Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level in...
The paper introduces the Procedural Graph, a framework that structures procedural knowledge into (procedure, relation, procedure) triplets to guide large language model agents in planning and tool usage. At each decision point, a guidance model uses the local subgraph to bias the agent’s next action, while an LLM refiner self‑evolves the graph by editing its topology based on successful versus failed trajectories. Experiments across datasets and LLMs show that Procedural Graphs consistently outperform memory‑based baselines, and the self‑evolution mechanism further improves performance without manual engineering.
arXiv:2605. 12376v2 Announce Type: replace Abstract: Table processing-including cleaning, transformation, augmentation, and matching-is a foundational yet error-prone stage in real-world data pipelines.