Search arXiv⌕ Search

arXiv subjects

Qingsong Wen

Publications and source records attributed to Qingsong Wen.

At least 19 recordsLinked to original sources
arXiv2026

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role composition: a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce $χ$-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document managed-care operations handbook skill. Across 30 agent harness/models configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.

cs.CL↗
arXiv2026

DrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modeling

Real-world time series contain evolving underlying dynamics with irregular variations that lack stable temporal patterns and are often referred to as noise. Existing methods address this mixture by filtering frequencies or suppressing noisy observations. They either miss temporal evolution or risk suppressing useful dynamics. We propose DrafTS, a model-agnostic framework that aims to reduce noise while preserving evolving dynamics through time-aware Decomposition with ResiduAl correction For Time Series. DrafTS uses features derived from instantaneous amplitude and frequency to guide decomposition into a primary component intended to capture underlying dynamics. A task-specific backbone models the primary component, while a lightweight correction module uses residual information to correct the backbone output. Across four time series modeling tasks, DrafTS improves six diverse backbones, demonstrating its effectiveness. Code is at https://github.com/Autumn61q/DrafTS

cs.AI↗
arXiv2026

REAT: A Reflective Experience-Augmented Tutoring Framework for Multi-turn Mathematical Instruction

Current Large Language Models (LLMs) excel at solving complex mathematical problems, yet this proficiency does not inherently translate into effective tutoring. While advanced LLM tutors may leverage multi-agent frameworks or fine-tuning, most still lack a mechanism to systematically accumulate and reuse pedagogical experience over time, limiting their adaptability to diverse student needs during fluid, multi-turn interactions. To bridge this gap, we propose the Reflective Experience-Augmented Tutoring (REAT) framework, which couples experience distillation from historical dialogues with real-time adaptive retrieval. Driven by a multi-agent Observer-Critic-Mentor (OCM) distillation pipeline, REAT reviews past conversational trajectories and distills raw interactions into structured, problem-agnostic pedagogical experiences. During live tutoring, a state-aware retrieval module injects these curated experiences to provide adaptive scaffolding based on the student's cognitive state. Experiments demonstrate that the proposed framework significantly outperforms both prompt-only and supervised fine-tuning (SFT) baselines, particularly in improving complex, low-scoring tutoring scenarios. Crucially, the distilled experiences exhibit robust generalization across diverse model architectures and mathematical datasets.

cs.MA↗
arXiv2026

RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent

Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, existing benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving realistic tool orchestration for recommendation underexplored. To bridge this gap, we propose RecToolBench, a Model Context Protocol (MCP)-based benchmark for evaluating tool-using recommender agents under fuzzy user instructions. RecToolBench contains more than 1,200 executable tasks across three recommendation domains, 13 MCP servers, and 32 tools, spanning single-tool calls, parallel tool calls, sequential tool chains, and hybrid tool orchestration. We construct RecToolBench with a scalable synthesize--fuzzify--judge pipeline that generates executable fuzzy recommendation tasks, and evaluates agent trajectories using rule-based execution checks and rubric-based LLM evaluation. Experiments on representative LLMs show that syntactically valid tool calls do not guarantee successful recommendations. Models struggle with semantic parameter grounding, multi-step evidence integration, and grounded final recommendations, especially as orchestration complexity increases. Our results identify tool orchestration under fuzzy user intent as a major bottleneck for agentic recommender systems. Our data and code are available at https://github.com/ShawnChenn/RecToolBench.

cs.IR↗
arXiv2026

HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit

Internal-state probes enable truthfulness prediction before a large language model generates an answer. When detectors change both the layers they read and the rules used to combine them, the source of improved prediction becomes difficult to identify. We separate these choices and find that retaining more layers improves prediction even under fixed equal weighting. An exact Fisher-ratio decomposition explains why the additional benefit of linear reweighting is limited on these probe scores: information inlayer-wise differences largely overlaps with that captured by the depth mean. Estimating additional weights can then offset this small benefit when the data used to fit them are limited. These findings motivate our proposed method HalluTracer, which averages layer-wise probe logits to predict truthfulness before decoding. Across six models and four benchmarks, including TruthfulQA, HalluTracer achieves the highest area under the receiver operating characteristic curve (AUROC) in 23 of 24 model--benchmark pairs among the compared methods. The results support using evidence from across the network without requiring a correspondingly more flexible aggregation rule, clarifying the distinct roles of layer selection and weighting in pre-decoding detection.

cs.CL↗
arXiv2026

Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning

Asset retrieval (finding similar assets in a financial universe) is central to quantitative investment decision-making. Existing approaches define similarity through historical price patterns or sector classifications, but such backward-looking criteria provide no guarantee about future behavior. We argue that effective asset retrieval should be future-aligned: the retrieved assets should be those most likely to exhibit correlated future returns. To this end, we propose Future-Aligned Soft Contrastive Learning (FASCL), a representation learning framework whose soft contrastive loss uses pairwise future return correlations as continuous supervision targets. We further introduce an evaluation protocol designed to directly assess whether retrieved assets share similar future trajectories. Experiments on 5,631 US-listed securities against 14 baselines show that FASCL attains the best future return correlation at every retrieval depth and the best rank information coefficient at every depth and horizon, leads on trend consistency in 13 of 16 cells, and gives the highest gross Sharpe ratio in a spread trading backtest at every basket size. Code is available at https://github.com/HyeongminLEE/fascl .

cs.CE↗
arXiv2026

Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers

Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additional iterations can reduce support for a reference answer, leaving unclear whether an update's direction is locally unhelpful or its full displacement moves too far. We study this distinction by analysing reference utility, which measures this support, along the model's own update direction, varying the fraction of the proposed displacement supplied to the readout. This reveals finite-step failures in which a locally improving direction produces a harmful full update. A pathwise curvature decomposition characterises how initial progress is lost, while a local quadratic model predicts full-step gains and useful step scales. Bounds based on accumulated curvature variation characterise the approximation error of these predictions. Experiments across two model families reveal this separation on mathematical and commonsense tasks. A fixed quarter step produces positive gains in reference utility for 72.2--83.2% of selected failures across four settings. These findings identify a mismatch between update direction and step scale as a mechanism of lost progress, explaining how some harmful updates retain useful computation.

cs.LG↗
arXiv2026

From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process Mining

Process mining has long turned event logs into process knowledge: discovered models, conformance evidence, bottleneck diagnoses, and runtime predictions. Agentic AI changes the target. Process-aware agents will not only ask what happened. They will ask whether a proposed action should be taken, given the available evidence, privacy budget, organizational authority, and downstream risk. This BlueSky paper proposes event-to-action process mining: a process-mining agenda for transforming heterogeneous operational event data into governed action. The goal is not another dashboard, a generic enterprise simulator, or a language interface over logs. We argue that the community needs four mineable artifacts: event-object representations, action evidence packages, governance contracts, and benchmarks where act, defer, ask, and refuse are all valid outputs. This agenda is timely because agentic business process management (BPM), LLM-assisted process mining, object-centric event standards, causal process monitoring, and privacy-preserving learning are maturing separately. Bringing them together defines a data-mining target inside process mining: mining logged organizational behavior for accountable action, not only retrospective insight.

cs.AI↗
arXiv2026

An Interactive Agent for Requirement-Driven Candidate Sourcing

Finding people from a natural-language description (``ML engineers transitioning to research roles in biotech'') is increasingly delegated to LLM agents and framed as information retrieval. We argue that it is fundamentally a requirements engineering task: such a request is an under-determined requirement with implicit constraints, many valid answers, and no acceptance criterion, so useful answers require eliciting, validating, and verifying the requirement before search can matter. We present \sys{}, to our knowledge the first interactive, requirements-driven candidate-sourcing agent (it elicits, validates, retrieves, and verifies a vague people-request into a justified slate through bounded elicitation, workflow templates, a two-stage commit protocol, and bidirectional termination guards) and \bench{}, a benchmark that runs the requirements lifecycle (criteria-anchored validation, multi-model evidence-grounded oracle construction, and cost-aware verification). Across $21$ systems and all $691$ requirements, \sys{} dominates breadth ($100%$ coverage at $2.5\times$ the yield) and is \emph{near-orthogonal} to the field, with $90%$ of the people it returns are surfaced by \emph{none} of $20$ strong LLM-plus-web baselines combined. Beyond breadth, an evidence-grounded judging of every system shows \sys{} \emph{recalls} the most relevant real people: $0.241$ of the union pool, $1.9\times$ the next system, with a bootstrap $95%$ interval disjoint from every baseline. \sys{} is thus the strongest \emph{sourcing} engine (the deepest real, reachable candidate pool), while precision-ranking LLMs serve as~complementary verifiers.

cs.SE↗
arXiv2026

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining long-horizon research whose conclusions remain auditable. We present Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence. Mint-Agent is built upon three pillars: data, harness, and algorithm. Our data engine constructs clean, specialized tasks for atomic financial capabilities and long-horizon agentic execution from real-world financial sources. MintHarness enables stable interaction with open-ended environments and maintains auditable evidence trails across extended research trajectories. Our training recipe combines SFT, critical-step OPD, and RLVR to develop separate financial reasoning and agentic execution experts, which are then unified through model merging and multi-teacher on-policy distillation into compact, general-purpose financial agents. This pipeline yields two flagship models, Mint-Cu (9B) and Mint-Ag (27B). Across professional financial benchmarks, our models demonstrate two defining strengths: (1) Reliability: Mint-Ag achieves 98.33% on RFC-Bench, surpassing GPT-5.6-Sol and Claude-Opus-4.8 by 3.66 and 3.00 points; and (2) Executability: Mint-Cu reaches 69.86% on FinSearchComp T2, outperforming Agents-A1-35B and Nex-N2-mini by 22.83 and 12.78 points, while Mint-Ag achieves 76.00% and 60.49% on FinanceAgentBench v1.1 and v2, respectively. These results establish a path toward trustworthy financial intelligence in which domain expertise, long-horizon execution, and auditable evidence are jointly engineered as a unified foundation for frontier agentic models.

cs.CL↗
arXiv2026

Forecast Collapse in Time-Series Foundation Models

When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-sectional correlation. We call this forecast collapse. Surprisingly, the phenomenon largely disappears when forecasting trading volume under the same setting. We investigate forecast collapse across time-series foundation models (TSFMs), twelve deep-learning forecasting models, and 97 public benchmark configurations, and find that it is closely tied to target predictability. We identify two distinct reasons behind it: low predictability limits the amplitude of calibrated point forecasts, while per-series objectives leave cross-series structure unidentified. These findings reveal a calibration-ranking tradeoff: optimizing squared error leads to flat predictions, whereas directly optimizing cross-sectional correlation improves ranking but can inflate forecast amplitude by more than an order of magnitude. To address this tradeoff, we introduce CalibRank, a simple objective that balances calibration and ranking. On Finance1K, CalibRank nearly triples cross-sectional correlation while keeping amplitude close to the target, and improves correlation on all tested models. Our results reveal a blind spot in conventional time-series evaluation: per-series metrics can hide failures in cross-series structure needed by downstream decisions.

cs.LG↗
arXiv2026

TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments

Time series analysis in high-stakes domains relies on recurring data releases, where new observations can alter the evidence base and the validity of later conclusions. Existing time series QA benchmarks mostly rely on fixed snapshots, leaving temporal validity and cutoff-aware evidence use unevaluated. We introduce TimeSage-EV, a live benchmark for agentic time series analysis in evolving environments. It tracks 60 real institutional scenarios across 6 domains, comprising 1,485 scenario-period QA pairs from Feb 2023 to May 2026 and spanning monthly, weekly, daily, and irregular release cadences. At each period, large language model (LLM) agents receive time series data and source reports, while the withheld target release provides ground truth. TimeSage-EV evaluates state identification, data summarization, and outlook reasoning. Experiments with frontier LLM agents and TimeSage-1.0, a novel self-evolving agent with a reusable analytical skill library, reveal significant performance gaps across model tiers and recurring failures in temporal validity, exogenous context use, and adaptation. We release TimeSage-EV as a research resource with monthly updates, code, a leaderboard, and failure-mode analyses.

cs.AI↗
arXiv2026

GradientStabilizer:Fix the Norm, Not the Gradient

Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence. Widely used safeguards such as gradient clipping mitigate these failures but require threshold tuning and indiscriminately truncate large updates. We propose GradientStabilizer, a lightweight, drop-in gradient transform that preserves the instantaneous gradient direction while replacing the update magnitude with a statistically stabilized estimate derived from running gradient-norm statistics. We prove that the resulting stabilized magnitude is uniformly bounded on spike steps, independent of the spike size, and show how this boundedness controls optimizer state evolution in adaptive methods. Across LLM pre-training (FP16), quantization-aware pre-training (FP4), ImageNet classification, reinforcement learning, and time-series forecasting, GradientStabilizer consistently improves training stability, widens stable learning-rate regions, and reduces divergence relative to clipping-based baselines, even substantially reducing Adam's sensitivity to weight-decay strength. Code will be released soon.

cs.LG↗
arXiv2026

Bridging AI and Energy Forecasting: An Autonomous Workflow with Customized Toolkit

Energy forecasting is crucial for the power grid, but fundamentally different from general time series analysis: it highly relies on covariates like meteorological factors, and its goals must align with actual power grid operations, such as risk assessment and system reliability. In order to bridge the huge gap between advanced machine learning forecasting models and actual power grid demand, this paper proposes an autonomous forecasting workflow based on LLMs. As a virtual analyst, the agent replaces tedious manual adjustments by autonomously analyzing data features, dynamically orchestrating optimal forecasting pipelines, and generating actionable analysis reports for decision-makers. The carefully arranged pipeline directly addresses the demand of the power grid through probabilistic forecasting for uncertainty quantification. Furthermore, the framework acts as an automated testbed, enabling seamless A/B testing of specific algorithmic plugins across various architectures to evaluate their empirical effectiveness. As the foundation of the algorithm, the underlying toolkit integrates 31 advanced temporal architectures and 6 customized exogenous modules, resulting in 146 highly configurable variants. In addition, to provide experience references for the agents, we established a large-scale benchmark on 21 energy datasets and released new high-quality renewable energy datasets with meteorological factors.

cs.LG↗
arXiv2026

Adapting Embedding Models for Agent Capability Retrieval

Open agent marketplaces list native agents, tool bundles, and reusable skill packages in the same search interface, yet practitioners still have little guidance on how to retrieve across this mixed catalog. We study whether off-the-shelf retrieval models, trained for general text retrieval, can be adapted to match user queries to executable agent capabilities, and whether the learned signal transfers beyond the benchmark used for tuning. We fine-tune three open retrieval backbones, BGE-base, KaLM-v1.5, and EasyRec, on AgentSelect, which represents marketplace-visible units as capability profiles derived from public metadata, and test transfer on two catalogs not seen during training: MuleRun native agents and a ClawHub benchmark of 50 skills with 1,000 queries. Adaptation helps on both catalogs. Code and data will be released upon publication.

cs.IR↗
arXiv2026

M3F-UAV: A Missing-Modality Multimodal Foundation Model for Low-Altitude Wireless Sensing

Low-altitude unmanned aerial vehicles (UAVs) are emerging as key platforms for wireless intelligence tasks. However, practical low-altitude wireless systems usually operate in complex urban environments, where visual occlusion, sparse geometric observations, multipath propagation, and sensor failures may degrade the reliability of single-modality models. To address these challenges, this paper proposes M3F-UAV, a missing-modality multimodal foundation model for low-altitude wireless sensing. The proposed framework learns a unified multimodal representation from visual, geometric, and wireless observations. Specifically, modality-specific pretrained feature extractors are adopted for RGB/depth images, LiDAR point clouds, and CSI matrices, respectively. Through cross-modal fusion and missing-modality-aware pretraining with feature-level masked reconstruction and UAV localization objectives, M3F-UAV can extract fixed-size features from different modality combinations and adapt them to downstream low-altitude wireless tasks with lightweight task heads. Experiments on the LAMBDA dataset show that M3F-UAV outperforms single-modality baselines and maintains robust performance under missing-modality settings.

eess.SP↗
arXiv2026

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a trade-off: Parametric Adaptation can cause catastrophic forgetting and requires costly multi-domain maintenance, while Non-Parametric Retrieval improves forecasts but incurs high inference latency due to datastore search. We propose Parametric Memory Distillation and implement it as TS-Memory, a lightweight memory adapter that augments frozen TSFMs. TS-Memory is trained in two stages. First, we construct an offline, retrieval-leakage-safe kNN teacher that synthesizes confidence-aware quantile targets from retrieved futures. Second, we distill this retrieval-induced distributional correction into a lightweight memory adapter via confidence-gated supervision. During inference, TS-Memory fuses memory and backbone predictions with constant-time overhead, enabling retrieval-free deployment. Experiments across diverse TSFMs and benchmarks demonstrate consistent improvements in both point and probabilistic forecasting over representative adaptation methods, with efficiency comparable to the frozen backbone. Code: https://github.com/sisuolv/TS-Memory.

cs.LG↗
arXiv2026

RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty

Benchmarks establish a standardized evaluation framework to systematically assess the performance of large language models (LLMs), facilitating objective comparisons and driving advancements in the field. However, existing benchmarks fail to differentiate question difficulty, limiting their ability to effectively distinguish models' capabilities. To address this limitation, we propose RankLLM, a novel framework designed to quantify both question difficulty and model competency. RankLLM introduces difficulty as the primary criterion for differentiation, enabling a more fine-grained evaluation of LLM capabilities. RankLLM's core mechanism facilitates bidirectional score propagation between models and questions. The core intuition of RankLLM is that a model earns a competency score when it correctly answers a question, while a question's difficulty score increases when it challenges a model. Using this framework, we evaluate 30 models on 35,550 questions across multiple domains. RankLLM achieves 90% agreement with human judgments and consistently outperforms strong baselines such as IRT. It also exhibits strong stability, fast convergence, and high computational efficiency, making it a practical solution for large-scale, difficulty-aware LLM evaluation.

cs.CL↗