DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards

Dashboards are powerful visualization tools for data-driven decision-making, integrating multiple interactive views that allow users to explore, filter, and navigate data. Unlike static charts, dashboards support rich interactivity, which is essential for uncovering insights in real-world analytical workflows. However, existing question-answering benchmarks for data visualizations largely overlook this interactivity, focusing instead on static charts. This limitation severely constrains their ability to evaluate the capabilities of modern multimodal agents designed for GUI-based reasoning. To address this gap, we introduce DashboardQA, the first benchmark explicitly designed to assess how vision-language GUI agents comprehend and interact with real-world dashboards. The benchmark includes 112 interactive dashboards from Tableau Public and 405 question-answer pairs with interactive dashboards spanning five categories: multiple-choice, factoid, hypothetical, multi-dashboard, and conversational. By assessing a variety of leading closed- and open-source GUI agents, our analysis reveals their key limitations, particularly in grounding dashboard elements, planning interaction trajectories, and performing reasoning. Our findings indicate that interactive dashboard reasoning is a challenging task overall for all the VLMs evaluated. Even the top-performing agents struggle; for instance, the best agent based on Gemini-Pro-2.5 achieves only 38.69% accuracy, while the OpenAI CUA agent reaches just 22.69%, demonstrating the benchmark's significant difficulty. We release DashboardQA at https://github.com/vis-nlp/DashboardQA

The Emergence of Abstract Thought in Large Language Models Beyond Any Language

As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts. This has led to the widespread assumption that LLMs may "think" in English. However, more recent results showing strong multilingual performance, even surpassing English performance on specific tasks in other languages, challenge this view. In this work, we find that LLMs progressively develop a core language-agnostic parameter space-a remarkably small subset of parameters whose deactivation results in significant performance degradation across all languages. This compact yet critical set of parameters underlies the model's ability to generalize beyond individual languages, supporting the emergence of abstract thought that is not tied to any specific linguistic system. Specifically, we identify language-related neurons-those are consistently activated during the processing of particular languages, and categorize them as either shared (active across multiple languages) or exclusive (specific to one). As LLMs undergo continued development over time, we observe a marked increase in both the proportion and functional importance of shared neurons, while exclusive neurons progressively diminish in influence. These shared neurons constitute the backbone of the core language-agnostic parameter space, supporting the emergence of abstract thought. Motivated by these insights, we propose neuron-specific training strategies tailored to LLMs' language-agnostic levels at different development stages. Experiments across diverse LLM families support our approach.

What Makes a Good Natural Language Prompt?

As large language models (LLMs) have progressed towards more human-like and human--AI communications have become prevalent, prompting has emerged as a decisive component. However, there is limited conceptual consensus on what exactly quantifies natural language prompts. We attempt to address this question by conducting a meta-analysis surveying more than 150 prompting-related papers from leading NLP and AI conferences from 2022 to 2025 and blogs. We propose a property- and human-centric framework for evaluating prompt quality, encompassing 21 properties categorized into six dimensions. We then examine how existing studies assess their impact on LLMs, revealing their imbalanced support across models and tasks, and substantial research gaps. Further, we analyze correlations among properties in high-quality natural language prompts, deriving prompting recommendations. We then empirically explore multi-property prompt enhancements in reasoning tasks, observing that single-property enhancements often have the greatest impact. Finally, we discover that instruction-tuning on property-enhanced prompts can result in better reasoning models. Our findings establish a foundation for property-centric prompt evaluation and optimization, bridging the gaps between human--AI communication and opening new prompting research directions.

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

Reinforcement learning (RL) has become the dominant paradigm for endowing language models with advanced reasoning capabilities. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a granular understanding of their advantages is still lacking. To address this gap, we introduce a fine-grained analytic framework to dissect the impact of RL on reasoning. Our framework specifically investigates key elements that have been hypothesized to benefit from RL training: (1) plan-following and execution, (2) problem decomposition, and (3) improved reasoning and knowledge utilization. Using this framework, we gain insights beyond mere accuracy. For instance, providing models with explicit step-by-step plans surprisingly degrades performance on the most challenging benchmarks, yet RL-tuned models exhibit greater robustness, experiencing markedly smaller performance drops than their base counterparts. This suggests that RL may not primarily enhance the execution of external plans but rather empower models to formulate and follow internal strategies better suited to their reasoning processes. Conversely, we observe that RL enhances the model's capacity to integrate provided knowledge into its reasoning process, leading to performance improvements across diverse tasks. We also study difficulty, showing improved training by developing new ways to exploit hard problems. Our findings lay a foundation for more principled training and evaluation of reasoning models.

MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision

Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles and communication protocols. These manual designs often fail to align with the underlying LLMs' strengths and struggle to adapt to novel tasks. Recent automatic MAS approaches attempt to mitigate these limitations but typically necessitate a validation set for tuning and yield static MAS designs lacking adaptability during inference. We introduce MAS-ZERO, the first self-evolved, inference-time framework for automatic MAS design. MAS-ZERO employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance, without requiring a validation set. Critically, it enables dynamic agent composition and problem decomposition through meta-feedback on solvability and completeness. Experiments across math, graduate-level QA, and software engineering benchmarks, using both closed-source and open-source LLM backbones of varying sizes, demonstrate that MAS-ZERO outperforms both manual and automatic MAS baselines, achieving a 7.44% average accuracy improvement over the next strongest baseline while maintaining cost-efficiency. These findings underscore the promise of meta-level self-evolved design for creating effective and adaptive MAS.

Meta-Design Matters: A Self-Design Multi-Agent System

Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles and communication protocols. These manual designs often fail to align with the underlying LLMs' strengths and struggle to adapt to novel tasks. Recent automatic MAS approaches attempt to mitigate these limitations but typically necessitate a validation-set for tuning and yield static MAS designs lacking adaptability during inference. We introduce SELF-MAS, the first self-supervised, inference-time only framework for automatic MAS design. SELF-MAS employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance, without requiring a validation set. Critically, it enables dynamic agent composition and problem decomposition through meta-feedback on solvability and completeness. Experiments across math, graduate-level QA, and software engineering benchmarks, using both closed-source and open-source LLM back-bones of varying sizes, demonstrate that SELF-MAS outperforms both manual and automatic MAS baselines, achieving a 7.44% average accuracy improvement over the next strongest baseline while maintaining cost-efficiency. These findings underscore the promise of meta-level self-supervised design for creating effective and adaptive MAS.

J4R: Learning to Judge with Equivalent Initial State Group Relative Preference Optimization

To keep pace with the increasing pace of large language models (LLM) development, model output evaluation has transitioned away from time-consuming human evaluation to automatic evaluation, where LLMs themselves are tasked with assessing and critiquing other model outputs. LLM-as-judge models are a class of generative evaluators that excel in evaluating relatively simple domains, like chat quality, but struggle in reasoning intensive domains where model responses contain more substantive and challenging content. To remedy existing judge shortcomings, we explore training judges with reinforcement learning (RL). We make three key contributions: (1) We propose the Equivalent Initial State Group Relative Policy Optimization (EIS-GRPO) algorithm, which allows us to train our judge to be robust to positional biases that arise in more complex evaluation settings. (2) We introduce ReasoningJudgeBench, a benchmark that evaluates judges in diverse reasoning settings not covered by prior work. (3) We train Judge for Reasoning (J4R), a 7B judge trained with EIS-GRPO that outperforms GPT-4o and the next best small judge by 6.7% and 9%, matching or exceeding the performance of larger GRPO-trained judges on both JudgeBench and ReasoningJudgeBench.

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation

Hallucination, the generation of factually incorrect information, remains a significant challenge for large language models (LLMs), especially in open-domain long-form generation. Existing approaches for detecting hallucination in long-form tasks either focus on limited domains or rely heavily on external fact-checking tools, which may not always be available. In this work, we systematically investigate reference-free hallucination detection in open-domain long-form responses. Our findings reveal that internal states (e.g., model's output probability and entropy) alone are insufficient for reliably (i.e., better than random guessing) distinguishing between factual and hallucinated content. To enhance detection, we explore various existing approaches, including prompting-based methods, probing, and fine-tuning, with fine-tuning proving the most effective. To further improve the accuracy, we introduce a new paradigm, named RATE-FT, that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection. With extensive experiments and analysis using a variety of model families & datasets, we demonstrate the effectiveness and generalizability of our method, e.g., +3% over general fine-tuning methods on LongFact.

Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?

Charts are ubiquitous as they help people understand and reason with data. Recently, various downstream tasks, such as chart question answering, chart2text, and fact-checking, have emerged. Large Vision-Language Models (LVLMs) show promise in tackling these tasks, but their evaluation is costly and time-consuming, limiting real-world deployment. While using LVLMs as judges to assess the chart comprehension capabilities of other LVLMs could streamline evaluation processes, challenges like proprietary datasets, restricted access to powerful models, and evaluation costs hinder their adoption in industrial settings. To this end, we present a comprehensive evaluation of 13 open-source LVLMs as judges for diverse chart comprehension and reasoning tasks. We design both pairwise and pointwise evaluation tasks covering criteria like factual correctness, informativeness, and relevancy. Additionally, we analyze LVLM judges based on format adherence, positional consistency, length bias, and instruction-following. We focus on cost-effective LVLMs (<10B parameters) suitable for both research and commercial use, following a standardized evaluation protocol and rubric to measure the LVLM judge's accuracy. Experimental results reveal notable variability: while some open LVLM judges achieve GPT-4-level evaluation performance (about 80% agreement with GPT-4 judgments), others struggle (below ~10% agreement). Our findings highlight that state-of-the-art open-source LVLMs can serve as cost-effective automatic evaluators for chart-related tasks, though biases such as positional preference and length bias persist.

SweRank: Software Issue Localization with Code Ranking

Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e.g., bug report, feature request), is a critical yet time-consuming aspect of software development. While recent LLM-based agentic approaches demonstrate promise, they often incur significant latency and cost due to complex multi-step reasoning and relying on closed-source LLMs. Alternatively, traditional code ranking models, typically optimized for query-to-code or code-to-code retrieval, struggle with the verbose and failure-descriptive nature of issue localization queries. To bridge this gap, we introduce SweRank, an efficient and effective retrieve-and-rerank framework for software issue localization. To facilitate training, we construct SweLoc, a large-scale dataset curated from public GitHub repositories, featuring real-world issue descriptions paired with corresponding code modifications. Empirical results on SWE-Bench-Lite and LocBench show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems using closed-source LLMs like Claude-3.5. Further, we demonstrate SweLoc's utility in enhancing various existing retriever and reranker models for issue localization, establishing the dataset as a valuable resource for the community.