PyTorchKR Papers

최신 논문

총 139,333편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2505.15155공식 코드 · Papers with Code

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.

arXiv:2505.15146공식 코드 · Papers with Code

lmgame-Bench: How Good are LLMs at Playing Games?

Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and find that directly dropping LLMs into games cannot make an effective evaluation, for three reasons -- brittle vision perception, prompt sensitivity, and potential data contamination. We introduce lmgame-Bench to turn games into reliable evaluations. lmgame-Bench features a suite of platformer, puzzle, and narrative games delivered through a unified Gym-style API and paired with lightweight perception and memory scaffolds, and is designed to stabilize prompt variance and remove contamination. Across 13 leading models, we show lmgame-Bench is challenging while still separating models well. Correlation analysis shows that every game probes a unique blend of capabilities often tested in isolation elsewhere. More interestingly, performing reinforcement learning on a single game from lmgame-Bench transfers both to unseen games and to external planning tasks. Our evaluation code is available at https://github.com/lmgame-org/GamingAgent/lmgame-bench.

arXiv:2505.15134공식 코드 · Papers with Code

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs) performance on challenging math, physics, and coding tasks. We explore three approaches: (1) EM-FT minimizes token-level entropy similarly to instruction finetuning, but on unlabeled outputs drawn from the model; (2) EM-RL: reinforcement learning with negative entropy as the only reward to maximize; (3) EM-INF: inference-time logit adjustment to reduce entropy without any training data or parameter updates. On Qwen-7B, EM-RL, without any labeled data, achieves comparable or better performance than strong RL baselines such as GRPO and RLOO that are trained on 60K labeled examples. Furthermore, EM-INF enables Qwen-32B to match or exceed the performance of proprietary models like GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro on the challenging SciCode benchmark, while being 3x more efficient than self-consistency and sequential refinement. Our findings reveal that many pretrained LLMs possess previously underappreciated reasoning capabilities that can be effectively elicited through entropy minimization alone, without any labeled data or even any parameter updates.

arXiv:2505.15133공식 코드 · Papers with Code

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook the inherent conflict between target-class and non-target-class knowledge flows. Furthermore, low-confidence dark knowledge in non-target classes introduces noisy signals that hinder effective knowledge transfer. To address these limitations, we propose DeepKD, a novel training framework that integrates dual-level decoupling with adaptive denoising. First, through theoretical analysis of gradient signal-to-noise ratio (GSNR) characteristics in task-oriented and non-task-oriented knowledge distillation, we design independent momentum updaters for each component to prevent mutual interference. We observe that the optimal momentum coefficients for task-oriented gradient (TOG), target-class gradient (TCG), and non-target-class gradient (NCG) should be positively related to their GSNR. Second, we introduce a dynamic top-k mask (DTM) mechanism that gradually increases K from a small initial value to incorporate more non-target classes as training progresses, following curriculum learning principles. The DTM jointly filters low-confidence logits from both teacher and student models, effectively purifying dark knowledge during early training. Extensive experiments on CIFAR-100, ImageNet, and MS-COCO demonstrate DeepKD's effectiveness. Our code is available at https://github.com/haiduo/DeepKD.

arXiv:2505.15117공식 코드 · Papers with Code

An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents

Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based search agents that adeptly combine reasoning with search engine use. While the use of RL for training search agents is promising, the optimal design of such agents remains not fully understood. In particular, key factors -- such as (1) reward formulation, (2) the choice and characteristics of the underlying LLM, and (3) the role of the search engine in the RL process -- require further investigation. In this work, we conduct comprehensive empirical studies to systematically investigate these and offer actionable insights. We highlight several key findings: format rewards are effective in improving final performance, whereas intermediate retrieval rewards have limited impact; the scale and initialization of the LLM (general-purpose vs. reasoning-specialized) significantly influence RL outcomes; and the choice of search engine plays a critical role in shaping RL training dynamics and the robustness of the trained agent during inference. These establish important guidelines for successfully building and deploying LLM-based search agents in real-world applications. Code is available at https://github.com/PeterGriffinJin/Search-R1.

arXiv:2505.15116공식 코드 · Papers with Code

Graph Foundation Models: A Comprehensive Survey

Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through large-scale pretraining and generalization, extending these capabilities to graphs -- characterized by non-Euclidean structures and complex relational semantics -- poses unique challenges and opens new opportunities. To this end, Graph Foundation Models (GFMs) aim to bring scalable, general-purpose intelligence to structured data, enabling broad transfer across graph-centric tasks and domains. This survey provides a comprehensive overview of GFMs, unifying diverse efforts under a modular framework comprising three key components: backbone architectures, pretraining strategies, and adaptation mechanisms. We categorize GFMs by their generalization scope -- universal, task-specific, and domain-specific -- and review representative methods, key innovations, and theoretical insights within each category. Beyond methodology, we examine theoretical foundations including transferability and emergent capabilities, and highlight key challenges such as structural alignment, heterogeneity, scalability, and evaluation. Positioned at the intersection of graph learning and general-purpose AI, GFMs are poised to become foundational infrastructure for open-ended reasoning over structured data. This survey consolidates current progress and outlines future directions to guide research in this rapidly evolving field. Resources are available at https://github.com/Zehong-Wang/Awesome-Foundation-Models-on-Graphs.

arXiv:2505.15111공식 코드 · Papers with Code

iPad: Iterative Proposal-centric End-to-End Autonomous Driving

End-to-end (E2E) autonomous driving systems offer a promising alternative to traditional modular pipelines by reducing information loss and error accumulation, with significant potential to enhance both mobility and safety. However, most existing E2E approaches directly generate plans based on dense bird's-eye view (BEV) grid features, leading to inefficiency and limited planning awareness. To address these limitations, we propose iterative Proposal-centric autonomous driving (iPad), a novel framework that places proposals - a set of candidate future plans - at the center of feature extraction and auxiliary tasks. Central to iPad is ProFormer, a BEV encoder that iteratively refines proposals and their associated features through proposal-anchored attention, effectively fusing multi-view image data. Additionally, we introduce two lightweight, proposal-centric auxiliary tasks - mapping and prediction - that improve planning quality with minimal computational overhead. Extensive experiments on the NAVSIM and CARLA Bench2Drive benchmarks demonstrate that iPad achieves state-of-the-art performance while being significantly more efficient than prior leading methods.

arXiv:2505.15083공식 코드 · Papers with Code

Robust Multi-Modal Forecasting: Integrating Static and Dynamic Features

Time series forecasting plays a crucial role in various applications, particularly in healthcare, where accurate predictions of future health trajectories can significantly impact clinical decision-making. Ensuring transparency and explainability of the models responsible for these tasks is essential for their adoption in critical settings. Recent work has explored a top-down approach to bi-level transparency, focusing on understanding trends and properties of predicted time series using static features. In this work, we extend this framework by incorporating exogenous time series features alongside static features in a structured manner, while maintaining cohesive interpretation. Our approach leverages the insights of trajectory comprehension to introduce an encoding mechanism for exogenous time series, where they are decomposed into meaningful trends and properties, enabling the extraction of interpretable patterns. Through experiments on several synthetic datasets, we demonstrate that our approach remains predictive while preserving interpretability and robustness. This work represents a step towards developing robust, and generalized time series forecasting models. The code is available at https://github.com/jeremy-qin/TIMEVIEW

arXiv:2505.15075공식 코드 · Papers with Code

Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs

The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages, especially when integrating cultural knowledge, remains a significant challenge. To better assess this issue, we introduce two new benchmarks: KnowRecall and VisRecall, which evaluate cross-lingual consistency in MLLMs. KnowRecall is a visual question answering benchmark designed to measure factual knowledge consistency in 15 languages, focusing on cultural and historical questions about global landmarks. VisRecall assesses visual memory consistency by asking models to describe landmark appearances in 9 languages without access to images. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, still struggle to achieve cross-lingual consistency. This underscores the need for more robust approaches that produce truly multilingual and culturally aware models.

arXiv:2505.15068공식 코드 · Papers with Code

ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges

Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity of real-world problems, which demand open-ended, interdisciplinary reasoning and integration of computational tools. To address this gap, we introduce ModelingBench, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains, ranging from urban traffic optimization to ecosystem resource planning. These tasks require translating natural language into formal mathematical formulations, applying appropriate tools, and producing structured, defensible reports. ModelingBench also supports multiple valid solutions, capturing the ambiguity and creativity of practical modeling. We also present ModelingAgent, a multi-agent framework that coordinates tool use, supports structured workflows, and enables iterative self-refinement to generate well-grounded, creative solutions. To evaluate outputs, we further propose ModelingJudge, an expert-in-the-loop system leveraging LLMs as domain-specialized judges assessing solutions from multiple expert perspectives. Empirical results show that ModelingAgent substantially outperforms strong baselines and often produces solutions indistinguishable from those of human experts. Together, our work provides a comprehensive framework for evaluating and advancing real-world problem-solving in open-ended, interdisciplinary modeling challenges.

arXiv:2505.15047공식 코드 · Papers with Code

PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration

Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality constraints. This often leads to aimless hypothesizing and a failure to consistently link hypotheses with evidence, thereby hindering systematic uncertainty reduction. Overcoming these limitations fundamentally requires systematic uncertainty reduction. We introduce \texttt{PiFlow}, an information-theoretical framework, treating automated scientific discovery as a structured uncertainty reduction problem guided by principles (e.g., scientific laws). In evaluations across three distinct scientific domains -- discovering nanomaterial structures, bio-molecules, and superconductor candidates with targeted properties -- our method significantly improves discovery efficiency, reflected by a 73.55\% increase in the Area Under the Curve (AUC) of property values versus exploration steps, and enhances solution quality by 94.06\% compared to a vanilla agent system. Overall, \texttt{PiFlow} serves as a Plug-and-Play method, establishing a novel paradigm shift in highly efficient automated scientific discovery, paving the way for more robust and accelerated AI-driven research. Code is publicly available at our \href{https://github.com/amair-lab/PiFlow}{GitHub}.

arXiv:2505.15046공식 코드 · Papers with Code

ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding

The emergence of Multi-modal Large Language Models (MLLMs) presents new opportunities for chart understanding. However, due to the fine-grained nature of these tasks, applying MLLMs typically requires large, high-quality datasets for task-specific fine-tuning, leading to high data collection and training costs. To address this, we propose ChartCards, a unified chart-metadata generation framework for multi-task chart understanding. ChartCards systematically synthesizes various chart information, including data tables, visualization code, visual elements, and multi-dimensional semantic captions. By structuring this information into organized metadata, ChartCards enables a single chart to support multiple downstream tasks, such as text-to-chart retrieval, chart summarization, chart-to-table conversion, chart description, and chart question answering. Using ChartCards, we further construct MetaChart, a large-scale high-quality dataset containing 10,862 data tables, 85K charts, and 170 K high-quality chart captions. We validate the dataset through qualitative crowdsourcing evaluations and quantitative fine-tuning experiments across various chart understanding tasks. Fine-tuning six different models on MetaChart resulted in an average performance improvement of 5% across all tasks. The most notable improvements are seen in text-to-chart retrieval and chart-to-table tasks, with Long-CLIP and Llama 3.2-11B achieving improvements of 17% and 28%, respectively.

arXiv:2505.15034공식 코드 · Papers with Code

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning

Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as a policy guided by a verifier (reward model). However, current RL post-training methods for LLMs typically use verifiers that are fixed (rule-based or frozen pretrained) or trained discriminatively via supervised fine-tuning (SFT). Such designs are susceptible to reward hacking and generalize poorly beyond their training distributions. To overcome these limitations, we propose Tango, a novel framework that uses RL to concurrently train both an LLM generator and a verifier in an interleaved manner. A central innovation of Tango is its generative, process-level LLM verifier, which is trained via RL and co-evolves with the generator. Importantly, the verifier is trained solely based on outcome-level verification correctness rewards without requiring explicit process-level annotations. This generative RL-trained verifier exhibits improved robustness and superior generalization compared to deterministic or SFT-trained verifiers, fostering effective mutual reinforcement with the generator. Extensive experiments demonstrate that both components of Tango achieve state-of-the-art results among 7B/8B-scale models: the generator attains best-in-class performance across five competition-level math benchmarks and four challenging out-of-domain reasoning tasks, while the verifier leads on the ProcessBench dataset. Remarkably, both components exhibit particularly substantial improvements on the most difficult mathematical reasoning problems. Code is at: https://github.com/kaiwenzha/rl-tango.

arXiv:2505.15031공식 코드 · Papers with Code

Are the confidence scores of reviewers consistent with the review content? Evidence from top conference proceedings in AI

Peer review is vital in academia for evaluating research quality. Top AI conferences use reviewer confidence scores to ensure review reliability, but existing studies lack fine-grained analysis of text-score consistency, potentially missing key details. This work assesses consistency at word, sentence, and aspect levels using deep learning and NLP conference review data. We employ deep learning to detect hedge sentences and aspects, then analyze report length, hedge word/sentence frequency, aspect mentions, and sentiment to evaluate text-score alignment. Correlation, significance, and regression tests examine confidence scores' impact on paper outcomes. Results show high text-score consistency across all levels, with regression revealing higher confidence scores correlate with paper rejection, validating expert assessments and peer review fairness.

arXiv:2505.15011공식 코드 · Papers with Code

HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning

Our society is governed by a set of norms which together bring about the values we cherish such as safety, fairness or trustworthiness. The goal of value-alignment is to create agents that not only do their tasks but through their behaviours also promote these values. Many of the norms are written as laws or rules (legal / safety norms) but even more remain unwritten (social norms). Furthermore, the techniques used to represent these norms also differ. Safety / legal norms are often represented explicitly, for example, in some logical language while social norms are typically learned and remain hidden in the parameter space of a neural network. There is a lack of approaches in the literature that could combine these various norm representations into a single algorithm. We propose a novel method that integrates these norms into the reinforcement learning process. Our method monitors the agent's compliance with the given norms and summarizes it in a quantity we call the agent's reputation. This quantity is used to weigh the received rewards to motivate the agent to become value-aligned. We carry out a series of experiments including a continuous state space traffic problem to demonstrate the importance of the written and unwritten norms and show how our method can find the value-aligned policies. Furthermore, we carry out ablations to demonstrate why it is better to combine these two groups of norms rather than using either separately.

arXiv:2505.15009공식 코드 · Papers with Code

One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks

We study the approximation capabilities and on-convergence behaviors of one-layer transformers on the noiseless and noisy in-context reasoning of next-token prediction. Existing theoretical results focus on understanding the in-context reasoning behaviors for either the first gradient step or when the number of samples is infinite. Furthermore, no convergence rates nor generalization abilities were known. Our work addresses these gaps by showing that there exists a class of one-layer transformers that are provably Bayes-optimal with both linear and ReLU attention. When being trained with gradient descent, we show via a finite-sample analysis that the expected loss of these transformers converges at linear rate to the Bayes risk. Moreover, we prove that the trained models generalize to unseen samples as well as exhibit learning behaviors that were empirically observed in previous works. Our theoretical findings are further supported by extensive empirical validations.

arXiv:2505.15008공식 코드 · Papers with Code

Know When to Abstain: Optimal Selective Classification with Likelihood Ratios

Selective classification enhances the reliability of predictive models by allowing them to abstain from making uncertain predictions. In this work, we revisit the design of optimal selection functions through the lens of the Neyman--Pearson lemma, a classical result in statistics that characterizes the optimal rejection rule as a likelihood ratio test. We show that this perspective not only unifies the behavior of several post-hoc selection baselines, but also motivates new approaches to selective classification which we propose here. A central focus of our work is the setting of covariate shift, where the input distribution at test time differs from that at training. This realistic and challenging scenario remains relatively underexplored in the context of selective classification. We evaluate our proposed methods across a range of vision and language tasks, including both supervised learning and vision-language models. Our experiments demonstrate that our Neyman--Pearson-informed methods consistently outperform existing baselines, indicating that likelihood ratio-based selection offers a robust mechanism for improving selective classification under covariate shifts. Our code is publicly available at https://github.com/clear-nus/sc-likelihood-ratios.

arXiv:2505.14983공식 코드 · Papers with Code

Toward Informed AV Decision-Making: Computational Model of Well-being and Trust in Mobility

For future human-autonomous vehicle (AV) interactions to be effective and smooth, human-aware systems that analyze and align human needs with automation decisions are essential. Achieving this requires systems that account for human cognitive states. We present a novel computational model in the form of a Dynamic Bayesian Network (DBN) that infers the cognitive states of both AV users and other road users, integrating this information into the AV's decision-making process. Specifically, our model captures the well-being of both an AV user and an interacting road user as cognitive states alongside trust. Our DBN models infer beliefs over the AV user's evolving well-being, trust, and intention states, as well as the possible well-being of other road users, based on observed interaction experiences. Using data collected from an interaction study, we refine the model parameters and empirically assess its performance. Finally, we extend our model into a causal inference model (CIM) framework for AV decision-making, enabling the AV to enhance user well-being and trust while balancing these factors with its own operational costs and the well-being of interacting road users. Our evaluation demonstrates the model's effectiveness in accurately predicting user's states and guiding informed, human-centered AV decisions.

arXiv:2502.05724공식 코드 · Papers with Code

Rethinking Link Prediction for Directed Graphs

Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. However, these methods often lack a thorough analysis of their expressiveness and suffer from effective benchmarks for a fair evaluation. In this paper, we propose a unified framework to assess the expressiveness of existing methods, highlighting the impact of dual embeddings and decoder design on directed link prediction performance. To address limitations in current benchmark setups, we introduce DirLinkBench, a robust new benchmark with comprehensive coverage, standardized evaluation, and modular extensibility. The results on DirLinkBench show that current methods struggle to achieve strong performance, while DiGAE outperforms other baselines overall. We further revisit DiGAE theoretically, showing its graph convolution aligns with GCN on an undirected bipartite graph. Inspired by these insights, we propose a novel Spectral Directed Graph Auto-Encoder SDGAE that achieves state-of-the-art average performance on DirLinkBench. Finally, we analyze key factors influencing directed link prediction and highlight open challenges in this field.

arXiv:2505.15810공식 코드 · Papers with Code

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update-each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain-of-thought reasoning, but longer chains unexpectedly lead to worse grounding performance. Output evaluation: Reward functions based on hit signals or box area allow models to exploit box size, leading to reward hacking and poor localization quality. Policy update: Online RL tends to overfit easy examples due to biases in length and sample difficulty, leading to under-optimization on harder cases. To address these issues, we propose three targeted solutions. First, we adopt a Fast Thinking Template that encourages direct answer generation, reducing excessive reasoning during training. Second, we incorporate a box size constraint into the reward function to mitigate reward hacking. Third, we revise the RL objective by adjusting length normalization and adding a difficulty-aware scaling factor, enabling better optimization on hard samples. Our GUI-G1-3B, trained on 17K public samples with Qwen2.5-VL-3B-Instruct, achieves 90.3% accuracy on ScreenSpot and 37.1% on ScreenSpot-Pro. This surpasses all prior models of similar size and even outperforms the larger UI-TARS-7B, establishing a new state-of-the-art in GUI agent grounding. The project repository is available at https://github.com/Yuqi-Zhou/GUI-G1.