Searcharxiv⌕ Search

arXiv subjects

Qianqian Xie

Publications and source records attributed to Qianqian Xie.

At least 19 recordsLinked to original sources
arXiv2026

GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions

Coding agents can modify and test code across large software projects. Game development is a domain where agents must implement gameplay rules. A game can end in a valid state even after violating its rules during the run. Current game-development benchmarks replay fixed examples, score videos, or ask another model to judge the result. However, no existing benchmark checks game rules throughout execution across varied evaluator-selected scenarios while ensuring exactly reproducible verdicts. We introduce GameLogicBench, a benchmark of 72 gameplay-logic tasks in Godot projects. An automated evaluator checks each game's rules at every simulation tick. Across 403 hand-designed scenarios, seeded parameter variations produce 1,451 test cases. To ensure that the evaluator measures behavior rather than implementation choice, it must accept different correct implementations for each task while rejecting mutants, implementations with one required capability removed. The tasks span isolated mechanics, multi-system interactions, and repository-scale features. Across 20 combinations of language models and scaffolds, the best observed run solves 52.78% of tasks. Under Claude Code, all twelve models solve fewer tasks as task scope expands from isolated mechanics, through interacting systems, to repository-scale features. Agents inspect code more often and make more tool calls on repository-scale tasks than on isolated-mechanic tasks. Most unsuccessful submissions are runnable, but implement some required game behavior incorrectly. We compared versions of our benchmark evaluator built with and without validation using mutants. Without this validation, incorrect agent submissions passed. A separate analysis finds agents copying code from public repositories when network access is open. Reliable evaluation thus depends both on what the tests reject and on what external code agents can access.

cs.SE↗
arXiv2026

TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction

Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone cannot reveal whether correct answers reflect effective integration of the two inputs or instead arise from event polarity, unimodal priors, or superficial cues. Likewise, plausible explanations may rationalize predictions without faithfully reflecting the evidence that drives model behavior. We introduce TimeLitmus, a diagnostic benchmark for cross-modal understanding and explanation faithfulness in event-conditioned time-series prediction. TimeLitmus contains 4,856 evaluation records across Finance and Traffic, combining natural prediction with controlled counterfactual and contrastive interventions, explanation-targeted faithfulness tests, and systematic shortcut controls. Across ten representative LLMs, standard prediction accuracy substantially overstates reliable cross-modal understanding: Hard Paired Contrast (HPC) pair correctness peaks at only 19.2% in Finance and 11.7% in Traffic, and all ten models show lower-than-expected consistency on Finance series-side controls. Models often recognize scenario relations explicitly yet fail to apply them during independent prediction. Explanation faithfulness shows a similar gap: in Traffic, most models cite the manipulated temporal factor in over 90% of cases, while behavioral support remains below 22%. Human annotators outperform LLMs on matched controlled and hard-pair diagnostics, confirming that these distinctions are recoverable from the inputs. Natural-only adaptation yields selective gains in evidence selection and input sensitivity, but not consistent gains in controlled or hard-pair behavior. The benchmark, evaluation suite, and supervised adaptation data will be released publicly.

cs.AI↗
arXiv2026

FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?

Financial scenarios are diverse and complex, spanning varying data conditions, tool configurations, and workflows. Yet existing CUA, Computer-Using Agent, evaluation tasks remain largely manually constructed, limiting scalable coverage of real-world financial scenarios. Then, can agents autonomously construct diverse CUA evaluation tasks for financial scenarios? Evaluating this capability poses three key challenges: scenario coverage of construction requests, fair comparison across construction methods, and reliable assessment of generated task quality. To solve these, we introduce FinCUABuildBench, a benchmark for evaluating financial CUA task construction, featuring: (i) 576 construction requests covering 24 financial workflows and three types of runtime variation; (ii) standardized input, budget, and output specifications; and (iii) a task qualification mechanism based on execution tests and quality checks. We further introduce FinCUABuildAgent, a multi-agent system for automatically constructing dynamic financial CUA evaluation tasks. It consists of three modules that jointly construct tasks, environments, and validators. On FinCUABuildBench, under the same model backbone, existing agent-based construction methods achieve strict qualification rates of only 1.3-8.3%, while FinCUABuildAgent reaches 31.3%. Downstream evaluations further show that the constructed tasks can effectively differentiate CUA task-execution capabilities. These results demonstrate that agents can autonomously construct financial CUA tasks with meaningful evaluation value, offering a practical path toward broader evaluation coverage in financial scenarios. Code: https://github.com/FengxianJi/FinCUABuild

cs.AI↗
arXiv2026

Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation

However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question. To address this question, we propose SciStyleBench, a unified three-component benchmark for diagnosing and mitigating stylistic bias in LLM-based idea evaluation: (i) First, SciStyleStage, a three-stage evaluation environment that applies controlled stylistic perturbations to fixed scientific content across three settings no context, fixed-domain context, and open-domain retrieval context, covering 600 scientific ideas and 15 style variants, with 9,000 evaluation instances per setting; (ii) Second, SciStyleMetrics, a set of quantitative measures, including Style Bias Index (SBI), Substance Recognition Rate (SRR), and Adversarial Win Rate (AWR), to characterize how stylistic variation affects scoring stability, substance discrimination, and ranking robustness; (iii) Third, SciStyleExtractor, a plug-and-play evaluation module that separates presentation style from scientific content by predicting style type and deviation before style-conditioned evaluation, enabling us to assess whether style awareness reduces stylistic bias. Experiments on SciStyleBench show that direct LLM judges remain sensitive to writing style and struggle to distinguish scientific substance. In contrast, SciStyleExtractor reduces SBI from 0.566 to 0.501 while increasing SRR and AWR from 0.504 and 0.554 to 0.759 and 0.899, respectively. These results suggest that robust idea evaluation requires invariance to stylistic variation without sacrificing sensitivity to scientific substance. Overall, SciStyleBench provides a systematic framework for identifying, quantifying, and mitigating stylistic bias in scientific idea evaluation.

cs.CL↗
arXiv2026

MiraMind: Benchmarking Reliable Mental Health Reasoning beyond Answer Accuracy

Mental-health reasoning with large language models (LLMs) is an evidence-constrained judgment problem: models must transform limited, subjective, and often ambiguous evidence into interpretations, decisions, or claims whose specificity, certainty, severity, and actionability remain warranted. Existing benchmarks mainly evaluate specific clinical roles or final answers, leaving the reliability of explicit reasoning trajectories under-specified. We introduce MiraMind, a unified benchmark spanning six task families and 13 datasets across appraisal, diagnosis, intervention, abstraction, and verification. MiraMind evaluates both task outcomes and the trajectories connecting evidence to judgment through usability, logical structure, and informational contribution. Evaluating 20 LLMs reveals a restraint gap, in which the specificity or certainty of model judgments exceeds what limited evidence supports. We further train Mindora, an 8B model that targets evidence-to-judgment transitions through hard-case supervision, structured trajectory rewriting, and consistency-aware optimization. Mindora achieves the best average rank on MiraMind, improves over its backbone across all six task families, and produces more balanced reasoning trajectories. These results show that MiraMind can expose shared restraint failures and evaluate whether targeted post-training improves evidence-constrained mental-health reasoning.

cs.CL↗
arXiv2026

Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications

Large Language Models (LLMs) have demonstrated significant potential in medicine, with many studies adapting them through continued pre-training or fine-tuning on medical data to enhance domain-specific accuracy and safety. However, a key open question remains: to what extent do LLMs memorize medical training data. Memorization can be beneficial when it enables LLMs to retain valuable medical knowledge during domain adaptation. Yet, it also raises concerns. LLMs may inadvertently reproduce sensitive clinical content (e.g., patient-specific details), and excessive memorization may reduce model generalizability, increasing risks of misdiagnosis and making unwarranted recommendations. These risks are further amplified by the generative nature of LLMs, which can not only surface memorized content but also produce overconfident, misleading outputs that may hinder clinical adoption. In this work, we present a study on memorization of LLMs in medicine, assessing its prevalence (how frequently it occurs), characteristics (what is memorized), volume (how much content is memorized), and potential downstream impacts (how memorization may affect medical applications). We systematically analyze common adaptation scenarios: (1) continued pretraining on medical corpora, (2) fine-tuning on standard medical benchmarks, and (3) fine-tuning on real-world clinical data, including over 13,000 unique inpatient records from Yale New Haven Health System. The results demonstrate that memorization is prevalent across all adaptation scenarios and significantly higher than that reported in the general domain. Moreover, memorization has distinct characteristics during continued pre-training and fine-tuning, and it is persistent: up to 87% of content memorized during continued pre-training remains after fine-tuning on new medical tasks.

cs.CL↗
arXiv2026

ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors

Conversational investment advisors influence not only what users know, but also how they make subsequent decisions as market conditions evolve. Existing evaluations primarily assess response quality or observed outcomes, leaving the long-horizon pathway from advisor language to investor behavior difficult to audit. We introduce ShiJianBench, an offline framework for evaluating conversational investment advisors through matched investor trajectories under fixed historical market feedback. At its core is a multi-agent investor simulator with explicit evolving state variables, motive-driven deliberation, long-term memory, and dialogue-grounded updates. The simulator is calibrated against aggregate behavioral patterns from 7,199 real users, and advisor policies are evaluated using separate investor-side, service-side, and content-side metrics under a hard compliance gate. Experiments on Chinese fund-market traces from 2021 to 2026 identify a stable leading group of LLM advisors that combines substantially stronger personalized content with competitive investor-side trajectory outcomes. These results reveal a systematic distinction between producing a high-quality response and delivering an effective long-horizon intervention, motivating trajectory-aware evaluation of conversational advisors.

cs.CL↗
arXiv2026

LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents

Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory environments remains challenging. Current safety approaches often overlook the intermediate step of transforming laboratory natural language, including safety rules, manuals, protocols, and standard operating procedures, into machine-checkable runtime constraints. We introduce LabGuard (Laboratory Guard), a language-to-execution safety suite that grounds natural-language laboratory rules into executable specifications and deploys them as runtime guards. LabGuard includes three core components: LabGuard-IR, which defines a typed executable representation; LabGuard-Bench, which provides 812 supervised annotations expanded from 203 seed laboratory rules; and LabGuard-Grounder, which maps natural-language laboratory rules into LabGuard-IR. The resulting IR instances are handled by the LabGuard Pipeline, which compiles them into runtime monitors and applies them at the controller boundary. Experiments show that LabGuard generalizes to unseen laboratory-rule sources, achieves 79.4 task-scope F1, and reduces unsafe events from 39.5% to 23.8% after monitor compilation. In LabUtopia, its runtime monitors integrate with ACT, keeping interventions below 0.5% while preserving task success.

cs.AI↗
arXiv2026

AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities

While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visual signals, and editing one modality often requires coordinated changes in the other. Existing benchmarks primarily evaluate visual transformations on silent clips or isolated audio editing, leaving complex audio-visual editing and cross-modal consistency underexplored. We introduce AVE-Compass, a comprehensive benchmark with 145 curated source videos, 196 audio-visually coupled editing instructions, and 2,688 fine-grained checklist items. It evaluates Instruction Following, Fidelity Preserving, Realism, and Editing Intent through checklist-based MLLM judging and a dedicated realism rubric, complemented by automated cross-modal, video, and audio metrics. Extensive evaluation shows that state-of-the-art models still struggle to execute cross-modal instructions while preserving non-target content. We further propose AVE-Agent, a modular agent framework that decomposes complex instructions into dependent subtasks and iteratively improves editing results through self-reflection and evaluator feedback. AVE-Agent improves instruction execution, Fidelity Preserving, and audio-visual alignment in joint editing while maintaining competitive perceptual quality.

cs.MM↗
arXiv2026

Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems

When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branching Entropy (CBE), a pre-execution difficulty signal computed entirely from local inference, which predicts high inflation with AUROC 0.887; and (3) selects models by maximizing a Semantic Exchange Rate (SER) that divides expected accuracy by predicted true cost, with a fresh-escalation policy that discards failed chains before routing to a stronger model. On GSM8K under a fixed budget, InflationAgent achieves 94.7\% accuracy versus 91.0\% for FrugalGPT while using 31\% fewer tokens, and we show that forwarding a failed reasoning chain to GPT-4o reduces its accuracy by up to 34.8 percentage points, validating the fresh-escalation design.

cs.CL↗
arXiv2026

TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation

Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text-Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation.

cs.CL↗
arXiv2026

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents. We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through LLM-assisted expert review. From these annotations, we build TELBench, a 1,000-instance benchmark for identifying error spans among normal exploration, failed searches, tentative hypotheses, and harmless noise. We further propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path. Experiments across model families and auditing frameworks show that DRIFT improves span-level error localization and first-error accuracy by up to 30 percentage points. Our work provides a process-level view of reliability in deep-research agents.

cs.AI↗
arXiv2026

Overview of the ClinicalSkillQA 2026 Shared Task on Continuous Perception and Procedural Reasoning in Clinical Skill Assessment

This paper presents an overview of the ClinicalSkillQA 2026 shared task, which was organized with the BioNLP Workshop at ACL 2026. The goal of this shared task is to evaluate continuous perception and procedural reasoning in clinical skill assessment by requiring systems to reconstruct the correct temporal order of shuffled clinical key frames and generate rationales grounded in clinical workflow knowledge. The benchmark contains 200 test-only instances sampled from clinical skill videos, covering three emergency-care procedures. Each instance is annotated with the ground-truth temporal order and an expert-verified rationale. A total of seven teams participated in the task, collectively making 90 submissions, with four teams providing system description papers. Systems are evaluated using Task Accuracy, Pairwise Accuracy, and BERTScore, which measure exact sequence reconstruction, local temporal consistency, and rationale quality, respectively. In this paper, we describe the task setup, dataset construction, and evaluation criteria. We further summarize the methodologies adopted by participating teams and present a comprehensive analysis of the submitted systems. The official results suggest that current models still struggle with continuous perception and procedural reasoning, especially when they must integrate visual evidence, temporal structure, and clinical workflow knowledge.

cs.HC↗
arXiv2026

FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information

Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Reporting Language) provides a standard for tagging financial figures, mapping thousands of facts to over 10k US GAAP concepts remains costly and error prone. Existing benchmarks oversimplify this task as flat, single step classification over small subsets of concepts, ignoring the hierarchical semantics of the taxonomy and the structured nature of financial documents. Consequently, these benchmarks fail to evaluate Large Language Models (LLMs) under realistic reporting conditions. To bridge this gap, we introduce FinTagging, the first comprehensive benchmark for structure aware and full scope XBRL tagging. We decompose the complex tagging process into two subtasks: (1) FinNI (Financial Numeric Identification), which extracts entities and types from heterogeneous contexts including text and tables; and (2) FinCL (Financial Concept Linking), which maps extracted entities to the full US GAAP taxonomy. This two stage formulation enables a fair assessment of LLMs' capabilities in numerical reasoning and taxonomy alignment. Evaluating diverse LLMs in zero shot settings reveals that while models generalize well in extraction, they struggle significantly with fine grained concept linking, highlighting critical limitations in domain specific structure aware reasoning.

cs.CL↗
arXiv2026

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice

While Large Language Models (LLMs) excel in various general domains, they exhibit notable gaps in the highly specialized, knowledge-intensive, and legally regulated Chinese tax domain. Consequently, while tax-related benchmarks are gaining attention, many focus on isolated NLP tasks, neglecting real-world practical capabilities. To address this issue, we introduce TaxPraBen, the first dedicated benchmark for Chinese taxation practice. It combines 10 traditional application tasks, along with 3 pioneering real-world scenarios: tax risk prevention, tax inspection analysis, and tax strategy planning, sourced from 14 datasets totaling 7.3K instances. TaxPraBen features a scalable structured evaluation paradigm designed through process of "structured parsing-field alignment extraction-numerical and textual matching", enabling end-to-end tax practice assessment while being extensible to other domains. We evaluate 19 LLMs based on Bloom's taxonomy. The results indicate significant performance disparities: all closed-source large-parameter LLMs excel, and Chinese LLMs like Qwen2.5 generally exceed multilingual LLMs, while the YaYi2 LLM, fine-tuned with some tax data, shows only limited improvement. TaxPraBen serves as a vital resource for advancing evaluations of LLMs in practical applications.

cs.CL↗
arXiv2026

DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation

Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and ambiguous task definitions. We propose DR$^{3}$-Eval, a realistic and reproducible benchmark for evaluating deep research agents on multimodal, multi-file report generation. DR$^{3}$-Eval is constructed from authentic user-provided materials and paired with a per-task static research sandbox corpus that simulates open-web complexity while remaining fully verifiable, containing supportive documents, distractors, and noise. Moreover, we introduce a multi-dimensional evaluation framework measuring Information Recall, Factual Accuracy, Citation Coverage, Instruction Following, and Depth Quality, and validate its alignment with human judgments. Experiments with our developed multi-agent system DR$^{3}$-Agent based on multiple state-of-the-art language models demonstrate that DR$^{3}$-Eval is highly challenging and reveals critical failure modes in retrieval robustness and hallucination control. Our code and data are publicly available.

cs.AI↗
arXiv2026

SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos

Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing interactions update the procedural state and thereby determine the correctness of later actions. We introduce SiMing-Bench, the first benchmark for evaluating this capability from full-length clinical skill videos. It targets rubric-grounded process-level judgment of whether interaction-driven state updates preserve procedural correctness across an entire workflow. SiMing-Bench is instantiated with SiMing-Score, a physician-annotated dataset of real clinical skill examination videos spanning cardiopulmonary resuscitation, automated external defibrillator operation, and bag-mask ventilation, each paired with a standardized step-wise rubric and dual-expert labels. Across diverse open- and closed-source MLLMs, we observe consistently weak agreement with physician judgments. Moreover, weak performance on rubric-defined intermediate steps persists even when overall procedure-level correlation appears acceptable, suggesting that coarse global assessment substantially overestimates current models' procedural judgment ability. Additional analyses with binary step judgment and step-aligned clips indicate that the bottleneck is not merely fine-grained scoring or temporal localization, but modeling how continuous interactions update procedural state over time.

cs.CV↗
arXiv2026

Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images

Recent advances in vision-language models (VLMs) have improved image captioning for cultural heritage. However, inferring structured cultural metadata (e.g., creator, origin, period) from visual input remains underexplored. We introduce a multi-category, cross-cultural benchmark for this task and evaluate VLMs using an LLM-as-Judge framework that measures semantic alignment with reference annotations. To assess cultural reasoning, we report exact-match, partial-match, and attribute-level accuracy across cultural regions. Results show that models capture fragmented signals and exhibit substantial performance variation across cultures and metadata types, leading to inconsistent and weakly grounded predictions. These findings highlight the limitations of current VLMs in structured cultural metadata inference beyond visual perception.

cs.CV↗