Searcharxiv⌕ Search

arXiv subjects

Yuante Li

Publications and source records attributed to Yuante Li.

16 recordsLinked to original sources
arXiv2026

PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users

Conversational assistants are expected to help people with diverse backgrounds, preferences, and communication styles. Yet evaluations centered on a single cooperative user provide limited insight into how reliably an assistant serves users with different personas. We introduce PersonaChatBench, a framework for evaluating task competence and responsiveness to diverse user needs. PersonaChatBench pairs the same underlying task with multiple simulated users, each guided by a private persona card that specifies distinct needs, preferences, and interaction behaviors. By holding the task fixed while varying the user, the framework examines how assistant performance changes across user conditions. We evaluate 20 language models across six domains, separately assessing native task outcomes, fulfillment of expressed persona needs, and simulator fidelity. Our results show that task performance and need fulfillment vary across personas and domains. Strong task performance does not necessarily translate into satisfying individual needs, and models' relative strengths in meeting those needs are not consistent across domains. PersonaChatBench makes these differences measurable, revealing gaps obscured by aggregate scores and helping identify which users an assistant serves well and where adaptation is needed. It provides a basis for evaluating consistency across users and guiding the development of assistants that better accommodate diverse needs in everyday applications.

cs.CL↗
arXiv2026

Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) relies on costly model-generated responses, motivating larger rollout batches and square-root learning-rate scaling. Reported to approximately preserve progress per sample with one optimizer step per rollout, this rule is less understood in practical multi-step training. We develop a two-clock framework that separates the samples needed to make progress from those consumed before collapse. Under a local quadratic model, the square-root rule preserves first-order drift per sample but not progress: larger batches take fewer, longer updates and lose more to curvature, yielding a learning-rate-dependent critical batch beyond which sample efficiency degrades. A drift-threshold hypothesis predicts a complementary failure clock whose sample count remains approximately invariant along the square-root rule. Controlled GRPO experiments on Qwen2.5-Math-1.5B across a $16\times$ batch range support both predictions. Ratio clipping delays failure, especially for larger batches, but the progress gap persists without it. Widening the clip trades stability for a transient speed gain. The progress gap reappears on another dataset, a general-purpose checkpoint, and a 7B model. Finally, we use the two-clock framework to derive a simple multi-step RLVR schedule: start below the critical batch and switch to a larger batch before failure. Our code is available at: https://github.com/WinstonLiyt/two-clocks-rlvr.

cs.LG↗
arXiv2026

Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists

AI agents can now carry out data-driven scientific analyses end to end, and benchmarks assess them by giving an agent a question and a dataset and scoring its final answer against a fixed key. These benchmarks assume that a correct answer was derived from the supplied data, a property we call evidence grounding. However, an agent can also reach the key from prior knowledge or by ruling out the other options, and a score based on a single run cannot tell these cases apart. We show how to test this assumption and find that it often fails. For each question, we build versions of its data files in which the evidence for the answer is left intact, withdrawn or reversed, check each edit with a pre-registered reference statistic, and run the same agent on every version. We then measure evidence-grounded accuracy, which credits a correct answer only if the agent also responds when the evidence is withdrawn and follows it when it is reversed. We evaluate three agent scaffolds and five models on 18 single-cell questions from BAISBench and four synthetic problems from GeneBench-Pro. On the single-cell questions, the Claude agents are 95% accurate and answer 83% correctly without any data, but their evidence-grounded accuracy is only 41%. Hiding gene names raises the share of runs that follow reversed evidence from 58% to 93% on ten gene tasks, suggesting that prior knowledge competes with the supplied data. The benchmark score and LLM judges can also reward answers that ignore the changed evidence. Measuring scientific intelligence rather than recall therefore requires checking whether answers follow the evidence and whether scores reward them for it.

cs.AI↗
arXiv2026

Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry

Multi-agent systems are increasingly used for forecasting future events, as deliberation among multiple LLMs is believed to improve reasoning and calibration. Yet existing approaches overlook a critical design choice: what information each agent receives. When all agents are given identical evidence, deliberation collapses into herding rather than genuine belief revision, leaving multi-agent systems little better than a single agent. We identify this as a fundamental gap and propose designed information asymmetry to close it: by partitioning evidence into shared public and disjoint private subsets, each agent holds exclusive knowledge that can only reach others through deliberation. We theoretically show that this decomposition reduces inter-agent error correlation, and instantiate it in InfoDelphi, a framework combining relevance-aware evidence routing, rationale-based iterative deliberation, and confidence-weighted aggregation. On PolyGym, a benchmark of 375 binary forecasting questions derived from real-world prediction markets, InfoDelphi outperforms the strongest single-agent and multi-agent baselines by 12--18% in Brier score and 4--8 percentage points in accuracy. More detailed experiments confirm that removing information asymmetry eliminates most deliberation gains, establishing diversity of input as the key enabler of effective multi-agent reasoning.

cs.AI↗
arXiv2026

FinMamba: Market-Aware Graph Enhanced Multi-Level Mamba for Stock Movement Prediction

Recently, combining stock features with inter-stock correlations has become a common and effective approach for stock movement prediction. However, financial data presents significant challenges due to its low signal-to-noise ratio and the dynamic complexity of the market, which give rise to two key limitations in existing methods. First, the relationships between stocks are highly influenced by multifaceted factors including macroeconomic market dynamics, and current models fail to adaptively capture these evolving interactions under specific market conditions. Second, for the accuracy and timeliness required by real-world trading, existing financial data mining methods struggle to extract beneficial pattern-oriented dependencies from long historical data while maintaining high efficiency and low memory consumption. To address the limitations, we propose FinMamba, a Mamba-GNN-based framework for market-aware and multi-level hybrid stock movement prediction. Specifically, we devise a dynamic graph to learn the changing representations of inter-stock relationships by integrating a pruning module that adapts to market trends. Afterward, with a selective mechanism, the multi-level Mamba discards irrelevant information and resets states to skillfully recall historical patterns across multiple time scales with linear time costs, which are then jointly optimized for reliable prediction. Extensive experiments on U.S. and Chinese stock markets demonstrate the effectiveness of our proposed FinMamba, achieving state-of-the-art prediction accuracy and trading profitability, while maintaining low computational complexity. The code is available at https://github.com/TROUBADOUR000/FinMamba.

cs.CE↗
arXiv2026

FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting

Financial time series (FinTS) record the behavior of human-brain-augmented decision-making, capturing valuable historical information that can be leveraged for profitable investment strategies. Not surprisingly, this area has attracted considerable attention from researchers, who have proposed a wide range of methods based on various backbones. However, the evaluation of the area often exhibits three systemic limitations: 1. Failure to account for the full spectrum of stock movement patterns observed in dynamic financial markets. (Diversity Gap), 2. The absence of unified assessment protocols undermines the validity of cross-study performance comparisons. (Standardization Deficit), and 3. Neglect of critical market structure factors, resulting in inflated performance metrics that lack practical applicability. (Real-World Mismatch). Addressing these limitations, we propose FinTSB, a comprehensive and practical benchmark for financial time series forecasting (FinTSF). To increase the variety, we categorize movement patterns into four specific parts, tokenize and pre-process the data, and assess the data quality based on some sequence characteristics. To eliminate biases due to different evaluation settings, we standardize the metrics across three dimensions and build a user-friendly, lightweight pipeline incorporating methods from various backbones. To accurately simulate real-world trading scenarios and facilitate practical implementation, we extensively model various regulatory constraints, including transaction fees, among others. Finally, we conduct extensive experiments on FinTSB, highlighting key insights to guide model selection under varying market conditions. Overall, FinTSB provides researchers with a novel and comprehensive platform for improving and evaluating FinTSF methods. The code is available at https://github.com/TongjiFinLab/FinTSB.

cs.CE↗
arXiv2026

Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches

Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved strong performance at the function and file levels, real-world software engineering requires reasoning over entire repositories, including cross-file dependencies, evolving execution environments, and global semantic consistency. This challenge has led to the emergence of Repository-Level Code Generation (RLCG), where models must retrieve, organize, and utilize repository-scale context to generate coherent and executable code changes. To address these challenges, Retrieval-Augmented Generation (RAG) has become an increasingly important paradigm for repository-level code intelligence. In this survey, we present a comprehensive review of Retrieval-Augmented Code Generation (RACG), with a particular focus on repository-level approaches. Rather than viewing RACG as a static ``retrieve-then-generate'' pipeline, we characterize it as a coupled and evolving process involving context construction, retrieval optimization, generation, and environment interaction. We organize existing methods through a unified analytical framework spanning retrieval substrate, control regime, and evaluation setting. Based on this framework, we systematically examine retrieval strategies, graph-based and non-graph-based retrieval paradigms, training-driven optimizations, and autonomous agent architectures. We further summarize widely used datasets, benchmarks, and system configurations, and discuss key challenges including scalability, reliability, efficiency, and the necessity boundary between RACG and long-context LLMs. Through this survey, we aim to provide a structured understanding of the rapidly evolving RACG landscape and highlight promising directions for future AI-powered software engineering research.

cs.SE↗
arXiv2026

From Observations to States: Latent Time Series Forecasting

Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate predictions often learn latent representations that are temporally disordered and lack continuity. We attribute this to the dominant observation-space forecasting paradigm, where minimizing point-wise errors on noisy and partially observed data encourages shortcut solutions instead of the recovery of underlying system dynamics. To address this, we propose Latent Time Series Forecasting (LatentTSF), a paradigm that shifts TSF from observation regression to latent state prediction. LatentTSF employs an AutoEncoder to project each observation into a learned latent state space and performs forecasting entirely in this space, allowing the model to focus on learning structured temporal dynamics. We provide an information-theoretic analysis showing that the latent objectives can be motivated as surrogates for maximizing mutual information between predicted and ground-truth latent states and future observations. Extensive experiments on widely-used benchmarks confirm that LatentTSF effectively mitigates latent chaos, yielding consistent improvements in both forecasting accuracy and representation quality. Our code is available at https://github.com/Muyiiiii/LatentTSF.

cs.LG↗
arXiv2026

MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants

With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we term MiniApps. These applications require models to not only render visual interfaces but also construct customized interaction logic that adheres to real-world principles. However, existing benchmarks primarily focus on algorithmic correctness or static layout reconstruction, failing to capture the capabilities required for this new paradigm. To address this gap, we introduce MiniAppBench, the first comprehensive benchmark designed to evaluate principle-driven, interactive application generation. Sourced from a real-world application with 10M+ generations, MiniAppBench distills 500 tasks across six domains (e.g., Games, Science, and Tools). Furthermore, to tackle the challenge of evaluating open-ended interactions where no single ground truth exists, we propose MiniAppEval, an agentic evaluation framework. Leveraging browser automation, it performs human-like exploratory testing to systematically assess applications across three dimensions: Intention, Static, and Dynamic. Our experiments reveal that current LLMs still face significant challenges in generating high-quality MiniApps, while MiniAppEval demonstrates high alignment with human judgment, establishing a reliable standard for future research. Our homepage is available in miniappbench.github.io.

cs.AI↗
arXiv2026

Audio Language Model for Deepfake Detection Grounded in Acoustic Chain-of-Thought

Deepfake speech detection systems are often limited to binary classification tasks and struggle to generate interpretable reasoning or provide context-rich explanations for their decisions. These models primarily extract latent embeddings for authenticity detection but fail to leverage structured acoustic evidence such as prosodic, spectral, and physiological attributes in a meaningful manner. This paper introduces CoLMbo-DF, a Feature-Guided Audio Language Model that addresses these limitations by integrating robust deepfake detection with explicit acoustic chain-of-thought reasoning. By injecting structured textual representations of low-level acoustic features directly into the model prompt, our approach grounds the model's reasoning in interpretable evidence and improves detection accuracy. To support this framework, we introduce a novel dataset of audio pairs paired with chain-of-thought annotations. Experiments show that our method, trained on a lightweight open-source language model, significantly outperforms existing audio language model baselines despite its smaller scale, marking a significant advancement in explainable deepfake speech detection.

cs.SD↗
arXiv2025

R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science

Recent advances in AI and ML have transformed data science, yet increasing complexity and expertise requirements continue to hinder progress. Although crowd-sourcing platforms alleviate some challenges, high-level machine learning engineering (MLE) tasks remain labor-intensive and iterative. We introduce R&D-Agent, a comprehensive, decoupled, and extensible framework that formalizes the MLE process. R&D-Agent defines the MLE workflow into two phases and six components, turning agent design for MLE from ad-hoc craftsmanship into a principled, testable process. Although several existing agents report promising gains on their chosen components, they can mostly be summarized as a partial optimization from our framework's simple baseline. Inspired by human experts, we designed efficient and effective agents within this framework that achieve state-of-the-art performance. Evaluated on MLE-Bench, the agent built on R&D-Agent ranks as the top-performing machine learning engineering agent, achieving 35.1% any medal rate, demonstrating the ability of the framework to speed up innovation and improve accuracy across a wide range of data science applications. We have open-sourced R&D-Agent on GitHub: https://github.com/microsoft/RD-Agent.

cs.AI↗
arXiv2025

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization

Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak interpretability, and fragmented coordination across key components such as factor mining and model innovation. In this paper, we propose R&D-Agent for Quantitative Finance, in short RD-Agent(Q), the first data-centric multi-agent framework designed to automate the full-stack research and development of quantitative strategies via coordinated factor-model co-optimization. RD-Agent(Q) decomposes the quant process into two iterative stages: a Research stage that dynamically sets goal-aligned prompts, formulates hypotheses based on domain priors, and maps them to concrete tasks, and a Development stage that employs a code-generation agent, Co-STEER, to implement task-specific code, which is then executed in real-market backtests. The two stages are connected through a feedback stage that thoroughly evaluates experimental outcomes and informs subsequent iterations, with a multi-armed bandit scheduler for adaptive direction selection. Empirically, RD-Agent(Q) achieves up to 2X higher annualized returns than classical factor libraries using 70% fewer factors, and outperforms state-of-the-art deep time-series models on real markets. Its joint factor-model optimization delivers a strong balance between predictive accuracy and strategy robustness. Our code is available at: https://github.com/microsoft/RD-Agent.

q-fin.CP↗
arXiv2025

QuantMind: A Context-Engineering Based Knowledge Framework for Quantitative Finance

Quantitative research increasingly relies on unstructured financial content such as filings, earnings calls, and research notes, yet existing LLM and RAG pipelines struggle with point-in-time correctness, evidence attribution, and integration into research workflows. To tackle this, We present QuantMind, an intelligent knowledge extraction and retrieval framework tailored to quantitative finance. QuantMind adopts a two-stage architecture: (i) a knowledge extraction stage that transforms heterogeneous documents into structured knowledge through multi-modal parsing of text, tables, and formulas, adaptive summarization for scalability, and domain-specific tagging for fine-grained indexing; and (ii) an intelligent retrieval stage that integrates semantic search with flexible strategies, multi-hop reasoning across sources, and knowledge-aware generation for auditable outputs. A controlled user study demonstrates that QuantMind improves both factual accuracy and user experience compared to unaided reading and generic AI assistance, underscoring the value of structured, domain-specific context engineering for finance.

cs.CE↗
arXiv2025

MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU

As financial markets grow increasingly complex in the big data era, accurate stock prediction has become more critical. Traditional time series models, such as GRUs, have been widely used but often struggle to capture the intricate nonlinear dynamics of markets, particularly in the flexible selection and effective utilization of key historical information. Recently, methods like Graph Neural Networks and Reinforcement Learning have shown promise in stock prediction but require high data quality and quantity, and they tend to exhibit instability when dealing with data sparsity and noise. Moreover, the training and inference processes for these models are typically complex and computationally expensive, limiting their broad deployment in practical applications. Existing approaches also generally struggle to capture unobservable latent market states effectively, such as market sentiment and expectations, microstructural factors, and participant behavior patterns, leading to an inadequate understanding of market dynamics and subsequently impact prediction accuracy. To address these challenges, this paper proposes a stock prediction model, MCI-GRU, based on a multi-head cross-attention mechanism and an improved GRU. First, we enhance the GRU model by replacing the reset gate with an attention mechanism, thereby increasing the model's flexibility in selecting and utilizing historical information. Second, we design a multi-head cross-attention mechanism for learning unobservable latent market state representations, which are further enriched through interactions with both temporal features and cross-sectional features. Finally, extensive experiments on four main stock markets show that the proposed method outperforms SOTA techniques across multiple metrics. Additionally, its successful application in real-world fund management operations confirms its effectiveness and practicality.

q-fin.ST↗
arXiv2025

DeepMath-Creative: A Benchmark for Evaluating Mathematical Creativity of Large Language Models

To advance the mathematical proficiency of large language models (LLMs), the DeepMath team has launched an open-source initiative aimed at developing an open mathematical LLM and systematically evaluating its mathematical creativity. This paper represents the initial contribution of this initiative. While recent developments in mathematical LLMs have predominantly emphasized reasoning skills, as evidenced by benchmarks on elementary to undergraduate-level mathematical tasks, the creative capabilities of these models have received comparatively little attention, and evaluation datasets remain scarce. To address this gap, we propose an evaluation criteria for mathematical creativity and introduce DeepMath-Creative, a novel, high-quality benchmark comprising constructive problems across algebra, geometry, analysis, and other domains. We conduct a systematic evaluation of mainstream LLMs' creative problem-solving abilities using this dataset. Experimental results show that even under lenient scoring criteria -- emphasizing core solution components and disregarding minor inaccuracies, such as small logical gaps, incomplete justifications, or redundant explanations -- the best-performing model, O3 Mini, achieves merely 70% accuracy, primarily on basic undergraduate-level constructive tasks. Performance declines sharply on more complex problems, with models failing to provide substantive strategies for open problems. These findings suggest that, although current LLMs display a degree of constructive proficiency on familiar and lower-difficulty problems, such performance is likely attributable to the recombination of memorized patterns rather than authentic creative insight or novel synthesis.

cs.AI↗
arXiv2025

LSR-IGRU: Stock Trend Prediction Based on Long Short-Term Relationships and Improved GRU

Stock price prediction is a challenging problem in the field of finance and receives widespread attention. In recent years, with the rapid development of technologies such as deep learning and graph neural networks, more research methods have begun to focus on exploring the interrelationships between stocks. However, existing methods mostly focus on the short-term dynamic relationships of stocks and directly integrating relationship information with temporal information. They often overlook the complex nonlinear dynamic characteristics and potential higher-order interaction relationships among stocks in the stock market. Therefore, we propose a stock price trend prediction model named LSR-IGRU in this paper, which is based on long short-term stock relationships and an improved GRU input. Firstly, we construct a long short-term relationship matrix between stocks, where secondary industry information is employed for the first time to capture long-term relationships of stocks, and overnight price information is utilized to establish short-term relationships. Next, we improve the inputs of the GRU model at each step, enabling the model to more effectively integrate temporal information and long short-term relationship information, thereby significantly improving the accuracy of predicting stock trend changes. Finally, through extensive experiments on multiple datasets from stock markets in China and the United States, we validate the superiority of the proposed LSR-IGRU model over the current state-of-the-art baseline models. We also apply the proposed model to the algorithmic trading system of a financial company, achieving significantly higher cumulative portfolio returns compared to other baseline methods. Our sources are released at https://github.com/ZP1481616577/Baselines_LSR-IGRU.

q-fin.ST↗