🔥 Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

💡 The paper discusses the limitations of traditional retrieval methods in complex tasks, particularly in agentic search where agents need to query raw text directly. Conventional retrieval systems use a fixed similarity interface that compresses access into a single step, making it difficult to implement tasks that require multiple steps, such as discovering intermediate entities, combining weak clues, and revising plans. To address this limitation, the authors propose direct corpus interaction, where an agent searches the raw corpus directly using general-purpose tools without any embedding model or retrieval API. This approach requires no offline indexing and adapts naturally to evolving local corpora. The authors evaluate this approach on several benchmarks and tasks, including IR benchmarks and end-to-end agentic search tasks, and find that it substantially outperforms strong baselines, including sparse, dense, and reranking methods. The results indicate that direct corpus interaction is a simple yet effective approach that opens a broader interface-design space for agentic search, and that retrieval quality depends not only on reasoning ability but also on the resolution of the interface through which the model interacts with the corpus. Overall, the paper contributes to the development of more effective agentic search systems by introducing a new approach to retrieval that allows for more flexible and direct interaction with the corpus.

📅 Published on May 3

🔗 Links:
• arXiv: https://arxiv.org/abs/2605.05242
• PDF: https://arxiv.org/pdf/2605.05242
• GitHub: https://github.com/DCI-Agent/DCI-Agent-Lite ⭐ 20

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#AgenticSearch #DirectCorpusInteraction #SemanticRetrieval #InformationRetrievalSystems #QueryingRawText

🔥 UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

💡 The paper presents UI-TARS-2, a native GUI-centered agent model that addresses challenges in data scalability, multi-turn reinforcement learning, and environment stability. The development of autonomous agents for graphical user interfaces is a major challenge in artificial intelligence, with open problems in data scalability, multi-turn reinforcement learning, and environment stability. To address these challenges, the authors propose a systematic training methodology that includes a data flywheel for scalable data generation, a stabilized multi-turn reinforcement learning framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts.

The authors evaluate UI-TARS-2 on various benchmarks, including GUI benchmarks such as Online-Mind2Web, OSWorld, WindowsAgentArena, and AndroidWorld, as well as game environments and software engineering benchmarks. The results show that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5 and strong baselines such as Claude and OpenAI agents. Specifically, UI-TARS-2 reaches high scores on GUI benchmarks, attains a mean normalized score of 59.8 across a 15-game suite, and remains competitive with frontier proprietary models on LMGame-Bench.

The model also generalizes to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. The authors provide detailed analyses of training dynamics, which provide insights into achieving stability and efficiency in large-scale agent reinforcement learning. Overall, the paper demonstrates UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios. The contributions of the paper include the development of a systematic training methodology, the evaluation of UI-TARS-2 on various benchmarks, and the analysis of training dynamics, which provide insights into achieving stability and efficiency in large-scale agent reinforcement learning.

📅 Published on Sep 2, 2025

🔗 Links:
• arXiv: https://arxiv.org/abs/2509.02544
• PDF: https://arxiv.org/pdf/2509.02544
• Project Page: https://seed-tars.com/showcase/ui-tars-2/
• GitHub: https://github.com/bytedance/ui-tars ⭐ 10.3k

🤖 Models citing this paper:
• https://huggingface.co/meituan/EvoCUA-32B-20260105
• https://huggingface.co/meituan/EvoCUA-8B-20260105

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#GraphicalUserInterfaceLearning #MultiTurnReinforcementLearning #GUIAgentDevelopment #AutonomousAgentDesign #ReinforcementLearningForGUI

🎓 Thesis • Dissertation • Research • Programming • Simulation

From a single research idea…
to a complete academic masterpiece.

🔹 Professional assistance for:
✔️ Master’s & PhD Theses
✔️ ISI / Scopus Articles
✔️ Research Proposals & Methodology
✔️ Data Analysis & Statistical Modeling
✔️ AI & Machine Learning Projects
✔️ MATLAB • Python • Simulink • Abaqus • COMSOL • Ansys • ETAP • PSCAD • HOMER • Proteus • LabVIEW
✔️ Electrical, Civil, Mechanical, Medical, Management, Computer Science & All Engineering Fields
✔️ Rare & High-Quality Datasets
✔️ Simulation Projects & Optimization Algorithms
✔️ Academic Presentation Design
✔️ Journal Revision & Reviewer Response Preparation

📊 Accurate Results
📚 Professional Documentation
💻 Clean & Structured Coding
🔒 Full Confidentiality
⏳ On-Time Delivery

Your research deserves more than copy-paste work.
It deserves precision, originality, and engineering-level thinking.

✨ Turning complex ideas into publishable research.

📩 Contact us for consultation and project evaluation.
https://t.iss.one/Omidyzd62

🔥 QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

💡 The paper introduces QuantAgent, a multi-agent large language model framework designed specifically for high-frequency trading. High-frequency trading requires rapid and precise decisions based on short-term market signals, which is different from traditional financial applications that involve long-term semantic reasoning. Existing large language models are not well-suited for high-frequency trading due to their lack of structured reasoning capabilities and domain-specific tools.

To address this problem, the QuantAgent framework decomposes trading into four specialized agents: Indicator, Pattern, Trend, and Risk. Each agent is equipped with domain-specific tools and structured reasoning capabilities to capture distinct aspects of market dynamics over short temporal windows. The Indicator agent focuses on technical indicators, the Pattern agent focuses on chart patterns, the Trend agent focuses on trend-based features, and the Risk agent focuses on risk management.

The results show that QuantAgent outperforms strong neural and rule-based baselines in terms of predictive accuracy and cumulative return over 4-hour trading intervals. The evaluation was conducted across ten financial instruments, including Bitcoin and Nasdaq futures, using zero-shot evaluations. The findings suggest that combining structured financial priors with language-native reasoning can unlock new potential for real-time decision systems in high-frequency financial markets.

The main contribution of the paper is the introduction of a multi-agent large language model framework that is specifically designed for high-frequency trading. The framework's ability to decompose trading into specialized agents and leverage domain-specific tools and structured reasoning capabilities makes it well-suited for the high-speed and precision-critical demands of high-frequency trading. The results demonstrate the effectiveness of the QuantAgent framework and highlight its potential for use in real-world high-frequency trading applications.

📅 Published on Sep 12, 2025

🔗 Links:
• arXiv: https://arxiv.org/abs/2509.09995
• PDF: https://arxiv.org/pdf/2509.09995
• Project Page: https://Y-Research-SBU.github.io/QuantAgent/
• GitHub: https://github.com/Y-Research-SBU/QuantAgent ⭐ 2.5k

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#HighFrequencyTrading #MultiAgentSystems #LargeLanguageModels #FinancialMachineLearning #AlgorithmicTrading

🔥 3D Gaussian Splatting for Real-Time Radiance Field Rendering

💡 This paper presents a method for real-time novel-view synthesis of scenes using 3D Gaussian splatting for radiance field rendering. The problem addressed is that current methods for novel-view synthesis require costly neural networks to achieve high visual quality, and faster methods trade off speed for quality, making it difficult to achieve real-time rendering at high resolutions.

The proposed method represents the scene using 3D Gaussians, which preserve the desirable properties of continuous volumetric radiance fields while avoiding unnecessary computation in empty space. The method consists of three key elements: first, it starts with sparse points produced during camera calibration and represents the scene with 3D Gaussians; second, it performs interleaved optimization and density control of the 3D Gaussians, optimizing anisotropic covariance to achieve an accurate representation of the scene; and third, it develops a fast visibility-aware rendering algorithm that supports anisotropic splatting and accelerates both training and real-time rendering.

The results demonstrate state-of-the-art visual quality and real-time rendering at 1080p resolution, achieving display rates of at least 30 frames per second. The method is evaluated on several established datasets, showing its effectiveness in achieving high-quality real-time novel-view synthesis. Overall, the paper contributes a novel approach to radiance field rendering, enabling high-quality and efficient rendering of scenes in real-time.

📅 Published on Aug 8, 2023

🔗 Links:
• arXiv: https://arxiv.org/abs/2308.04079
• PDF: https://arxiv.org/pdf/2308.04079
• GitHub: https://github.com/graphdeco-inria/gaussian-splatting ⭐ 21.8k

🤖 Models citing this paper:
• https://huggingface.co/stevee00/InteriorGen3D

📊 Datasets citing this paper:
• https://huggingface.co/datasets/Voxel51/gaussian_splatting
• https://huggingface.co/datasets/Arkanos25/gaussian_splatting

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/Voxel51/2025-ai-timeline

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#3DGaussianSplatting #RealTimeRadianceFieldRendering #NovelViewSynthesis #VolumetricRendering #RadianceFieldRepresentation

🔥 Fish Audio S2 Technical Report

💡 The paper introduces Fish Audio S2, an open source text to speech system that features multi speaker capabilities, multi turn generation, and instruction following control through natural language descriptions. The system utilizes a multi stage training approach, which includes a staged data pipeline covering video captioning, speech captioning, voice quality assessment, and reward modeling. This approach allows for scalable training and improves the overall performance of the system. The authors also release their model weights, fine tuning code, and an inference engine, making it production ready for streaming. The inference engine achieves a real time factor of 0.195 and a time to first audio of below 100 milliseconds, indicating its efficiency and speed. The code and weights are made available on GitHub and Hugging Face, and users are encouraged to try custom voices on the website. Overall, the paper contributes to the advancement of open source text to speech systems, providing a robust and efficient solution for generating high quality speech.

📅 Published on Mar 9

🔗 Links:
• arXiv: https://arxiv.org/abs/2603.08823
• PDF: https://arxiv.org/pdf/2603.08823
• Project Page: https://fish.audio/
• GitHub: https://github.com/fishaudio/fish-speech ⭐ 30.2k

🤖 Models citing this paper:
• https://huggingface.co/fishaudio/s2-pro
• https://huggingface.co/drbaph/s2-pro-fp8
• https://huggingface.co/mlx-community/fish-audio-s2-pro-bf16

📊 Datasets citing this paper:
• https://huggingface.co/datasets/Izzyzlin/CFSDD

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/artificialguybr/fish-s2-pro-zero
• https://huggingface.co/spaces/fguilleme/fish-s2-pro-zero
• https://huggingface.co/spaces/MAYA-AI/fish-s2-pro-zero

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#TextToSpeechSystems #MultispeakerSynthesis #NaturalLanguageProcessing #SpeechGenerationModels #RealTimeAudioProcessing

🔥 Flow-OPD: On-Policy Distillation for Flow Matching Models

💡 The paper addresses limitations in existing Flow Matching text-to-image models, which suffer from two main issues: reward sparsity and gradient interference. These problems lead to poor generation quality and alignment metrics. To overcome these challenges, the authors propose Flow-OPD, a two-stage alignment approach that combines on-policy distillation and manifold anchor regularization.

In the first stage, the authors fine-tune domain-specialized teacher models using single-reward GRPO fine-tuning, allowing each expert to reach its performance ceiling. Then, they establish a robust initial policy through a Flow-based Cold-Start scheme and consolidate heterogeneous expertise into a single student model.

The authors also introduce Manifold Anchor Regularization, which leverages a task-agnostic teacher to provide full-data supervision and anchors generation to a high-quality manifold. This helps mitigate aesthetic degradation commonly observed in purely RL-driven alignment.

The results show that Flow-OPD significantly improves generation quality and alignment metrics, raising the GenEval score from 63 to 92 and the OCR accuracy from 59 to 94. This represents an overall improvement of roughly 10 points over vanilla GRPO, while preserving image fidelity and human-preference alignment. The authors also observe an emergent teacher-surpassing effect, where the student model outperforms the teacher models. Overall, Flow-OPD establishes a scalable alignment paradigm for building generalist text-to-image models.

📅 Published on May 8

🔗 Links:
• arXiv: https://arxiv.org/abs/2605.08063
• PDF: https://arxiv.org/pdf/2605.08063
• Project Page: https://costaliya.github.io/Flow-OPD/
• GitHub: https://github.com/CostaliyA/Flow-OPD ⭐ 79

🤖 Models citing this paper:
• https://huggingface.co/CostaliyA/Flow-OPD

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#FlowMatchingModels #OnPolicyDistillation #TextToImageSynthesis #ManifoldAnchorRegularization #FlowOPD

🔥 HumanNet: Scaling Human-centric Video Learning to One Million Hours

💡 The paper introduces HumanNet, a large-scale human-centric video dataset that captures how humans interact with the physical world, with the goal of advancing embodied intelligence. The problem addressed is the lack of large, diverse, and richly annotated human activity data, which hinders progress in learning physical interaction. To solve this, the authors created a one-million-hour video corpus that spans first-person and third-person perspectives, covering various activities, human-object interactions, and long-horizon behaviors in diverse environments. The dataset is annotated with interaction-centric information, including captions, motion descriptions, and hand and body-related signals.

The method involves a systematic data curation paradigm that treats human-centric filtering, temporal structuring, viewpoint diversity, and annotation enrichment as key design principles. This approach transforms unstructured internet video into a scalable substrate for representation learning, activity understanding, motion generation, and human-to-robot transfer.

The results show that HumanNet can be used to train vision-language-action models, and that egocentric human video can effectively replace robot data for training. In a controlled experiment, the authors found that continued training with 1000 hours of egocentric video from HumanNet surpassed the performance of continued training with 100 hours of real-robot data. This suggests that human-centric video can be a scalable and cost-effective substitute for robot data, and that HumanNet can be used to explore the opportunity to scale embodied foundation models using human-centric videos. Overall, the paper contributes a large-scale dataset and a systematic data curation paradigm that can advance embodied intelligence and learning physical interaction.

📅 Published on May 7

🔗 Links:
• arXiv: https://arxiv.org/abs/2605.06747
• PDF: https://arxiv.org/pdf/2605.06747
• Project Page: https://dagroup-pku.github.io/HumanNet/
• GitHub: https://github.com/DAGroup-PKU/HumanNet ⭐ 65

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#HumanCentricVideoLearning #EmbodiedIntelligence #LargeScaleVideoDatasets #HumanActivityRecognition #VideoUnderstanding

🔥 MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

💡 The paper presents MACE-Dance, a music-driven dance video generation framework that combines cascaded Mixture-of-Experts with diffusion models and specialized training strategies. The goal is to generate high-quality dance videos with realistic human motion and visual appearance, driven by music. Existing methods in related domains such as music-driven 3D dance generation and pose-driven image animation cannot be directly applied to this task, and current studies struggle to achieve both high-quality visual appearance and realistic human motion.

The MACE-Dance framework consists of two experts: the Motion Expert and the Appearance Expert. The Motion Expert generates 3D motion from music, ensuring kinematic plausibility and artistic expressiveness, using a diffusion model with a BiMamba-Transformer hybrid architecture and a Guidance-Free Training strategy. The Appearance Expert synthesizes motion- and reference-conditioned videos, preserving visual identity with spatiotemporal coherence, using a decoupled kinematic-aesthetic fine-tuning strategy.

The paper claims that MACE-Dance achieves state-of-the-art performance in both 3D dance generation and pose-driven image animation. To evaluate the framework, the authors curate a large-scale and diverse dataset and design a motion-appearance evaluation protocol. The results show that MACE-Dance outperforms existing methods, demonstrating its effectiveness in generating high-quality dance videos with realistic human motion and visual appearance. The code for MACE-Dance is made available, allowing for further research and development in music-driven dance video generation.

📅 Published on May 7

🔗 Links:
• arXiv: https://arxiv.org/abs/2512.18181
• PDF: https://arxiv.org/pdf/2512.18181
• GitHub: https://github.com/AMAP-ML/MACE-Dance ⭐ 84

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#MusicDrivenVideoGeneration #DanceVideoSynthesis #MotionAppearanceModelling #CascadedMixtureOfExperts #MusicDrivenDanceGeneration

🔥 HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents

💡 The paper introduces HyperEyes, a parallel multimodal search agent designed to optimize inference efficiency through dual-grained reinforcement learning. Existing multimodal search agents process target entities sequentially, which can lead to redundant interaction rounds and decreased efficiency. HyperEyes addresses this issue by fusing visual grounding and retrieval into a single atomic action, enabling concurrent search across multiple entities.

The HyperEyes system is trained in two stages. The first stage involves a Parallel-Amenable Data Synthesis Pipeline that generates efficiency-oriented trajectories via Progressive Rejection Sampling. The second stage utilizes a Dual-Grained Efficiency-Aware Reinforcement Learning framework, which operates at two levels. At the macro level, the framework uses a trajectory-level reward called TRACE, which is designed to suppress superfluous tool calls without restricting genuine multi-hop search. At the micro level, the framework adapts On-Policy Distillation to inject dense token-level corrective signals from an external teacher on failed rollouts, mitigating the credit-assignment deficiency of sparse outcome rewards.

The paper also introduces a new benchmark called IMEB, which jointly evaluates search capability and efficiency. The results show that HyperEyes surpasses the strongest comparable open-source agent by 9.9% in accuracy, while using 5.3x fewer tool-call rounds on average. The HyperEyes system demonstrates the effectiveness of dual-grained reinforcement learning in optimizing inference efficiency and achieving better search results. Overall, the paper contributes to the development of more efficient and effective multimodal search agents.

📅 Published on May 8

🔗 Links:
• arXiv: https://arxiv.org/abs/2605.07177
• PDF: https://arxiv.org/pdf/2605.07177
• GitHub: https://github.com/DeepExperience/HyperEyes ⭐ 34

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://t.iss.one/PaperNexus

#MultimodalSearchAgents #ReinforcementLearning #ParallelSearchAlgorithms #EfficiencyAwareSystems #DualGrainedLearning