arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 199 records · Page 11Linked to original sources

arXiv2026

Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental rewards to learn stronger policies, such as GRPO-style optimization. However, applying on-policy RL to MAS remains underexplored and presents unique challenges. Algorithmically, standard GRPO grouping assumptions break down because prompts vary by role and by turn. System-wise, the training stack must support MAS-workflow rollouts and on-policy updates for both single-policy and multi-policy models. We propose AT-GRPO, which includes (i) an agent- and turn-wise grouped RL algorithm tailored to MAS and (ii) a training system that supports both single- and multi-policy regimes. Across game, planning, coding, and math tasks, AT-GRPO delivers substantial gains. On long-horizon planning, it increases accuracy from a 14.0 to 47.0 percent single-agent RL baseline to 96.0 to 99.5 percent. It also improves reasoning performance, with average gains of 3.87 to 7.62 percent on coding tasks and 9.0 to 17.93 percent on math. Code and environments are available at: https://github.com/pettingllms-ai/PettingLLMs.

cs.LG↗

arXiv2026

Learning Provably Correct Distributed Protocols Without Human Knowledge

Provably correct distributed protocols, which are a critical component of modern distributed systems, are highly challenging to design and have often required decades of human effort. These protocols allow multiple agents to coordinate to come to a common agreement in an environment with uncertainty and failures. We formulate protocol design as a search problem over strategies in a game with imperfect information, and the desired correctness conditions are specified in Satisfiability Modulo Theories (SMT). However, standard methods for solving multi-agent games fail to learn correct protocols in this setting, even when the number of agents is small. We propose a learning framework, GGMS, which integrates a specialized variant of Monte Carlo Tree Search with a transformer-based action encoder, a global depth-first search to break out of local minima, and repeated feedback from a model checker. Protocols output by GGMS are verified correct via exhaustive model checking for all executions within the bounded setting. We further prove that, under mild assumptions, the search process is complete: if a correct protocol exists, GGMS will eventually find it. In experiments, we show that GGMS can learn correct protocols for larger settings than existing methods.

cs.AI↗

arXiv2026

One latent to fit them all: a unified representation of baryonic feedback on matter distribution

Accurate and parsimonious quantification of baryonic feedback on matter distribution is of crucial importance for understanding both cosmology and galaxy formation from observational data. This is, however, challenging given the large discrepancy among different models of galaxy formation simulations, and their distinct subgrid physics parameterizations. Using 5,072 simulations from 4 different models covering broad ranges in their parameter spaces, we find a unified 2D latent representation. Compared to the simulations and other phenomenological models, our representation is independent of both time and cosmology, much lower-dimensional, and disentangled in its impacts on the matter power spectra. The common latent space facilitates the comparison of parameter spaces of different models and is readily interpretable by correlation with each. The two latent dimensions provide a complementary representation of baryonic effects, linking black hole and supernova feedback to distinct and interpretable impacts on both the matter power spectrum, and field, level. Our approach enables developing robust and economical analytic models for optimal gain of physical information from data, and is generalizable to other fields with significant modeling uncertainty.

astro-ph.CO↗

arXiv2026

AgentAsk: Multi-Agent Systems Need to Ask

Multi-agent systems (MAS) built on large language models promise improved problem-solving through collaboration, yet they often fail to consistently outperform strong single-agent baselines due to error propagation at inter-agent message handoffs.In this work, we conduct a systematic empirical analysis of such failures and introduce an edge-level error taxonomy that identifies four dominant error types: Data Gap, Signal Corruption, Referential Drift, and Capability Gap, as primary sources of failure in multi-agent interactions. Building on this taxonomy, we propose AgentAsk, a lightweight clarification module designed to intervene at the edge level in MAS to prevent cascading errors. The module operates by strategically applying minimal clarifications at critical points within the system, improving the accuracy and efficiency of the overall task. AgentAsk is trained to balance the trade-offs between clarification cost, latency, and accuracy, while it is also architecture-agnostic and can be easily integrated into existing systems. Evaluated across five benchmarks, AgentAsk consistently improves accuracy by up to 4.69%, while keeping latency and extra costs below 10% compared to baseline MAS, showcasing its high efficiency and minimal overhead.

cs.AI↗

arXiv2026

The Achilles' Heel of Angular Margins: A Chebyshev Polynomial Fix for Speaker Verification

Angular margin losses, such as AAM-Softmax, have become the de facto in speaker and face verification. Their success hinges on directly manipulating the angle between features and class prototypes. However, this manipulation relies on the arccos function to recover the angle, introducing a significant yet overlooked source of training instability. The derivative of arccos explodes at its boundaries, causing gradient peaks during optimisation. Furthermore, the formulation fails to generate a sufficiently sharp gradient for hard-to-classify examples. We address these issues by proposing ChebyAAM, a loss that replaces the arccos operation with its Chebyshev polynomial approximation. This substitution eliminates gradient explosion and applies a stronger corrective signal to hard examples, leading to more effective optimisation. Experiments on three benchmarks (VoxCeleb, SITW, and CN-Celeb) demonstrate that our method resolves the instability and consistently improves performance. Our work suggests that approximating angular operations, rather than calculating them explicitly, offers a more robust path for designing future metric learning losses. Code is available at https://github.com/ExtraOrdinaryLab/vibe.

cs.SD↗

arXiv2026

Long-term Monitoring of Kernel and Hardware Events to Understand Latency Variance

This paper presents our experience to understand latency variance caused by kernel and hardware events, which are often invisible at the application level. For this purpose, we have built VarMRI, a tool chain to monitor and analyze those events in the long term. To mitigate the "big data" problem caused by long-term monitoring, VarMRI selectively records a subset of events following two principles: it only records events that are affecting the requests recorded by the application; it records coarse-grained information first and records additional information only when necessary. Furthermore, VarMRI introduces an analysis method that is efficient on large amount of data, robust on different data set and against missing data, and informative to the user. VarMRI has helped us to carry out a 3,000-hour study of six applications and benchmarks on CloudLab. It reveals a wide variety of events causing latency variance, including interrupt preemption, Java GC, pipeline stall, NUMA balancing etc.; simple optimization or tuning can reduce tail latencies by up to 31%. Furthermore, the impacts of some of these events vary significantly across different experiments, which confirms the necessity of long-term monitoring.

cs.PF↗

arXiv2026

Improving Database Performance by Application-side Transaction Merging

This paper explores a new opportunity to improve the performance of transaction processing at the application side by merging structurely similar statements or transactions. Concretely, we re-write transactions to 1) merge similar statements using specific SQL semantics; 2) eliminate redundant reads; and 3) merge contending statements across transactions by pre-computing their aggregated effect. Following this idea, we present the design of TransactionMerger, a middleware to collect and merge transactions across different clients. We further present a static analysis tool to identify the merging opportunity without violating isolation as well as our experience of re-writing transactions in TPC-C and Spree, a popular real-world application. Our evaluation shows that such transaction merging can improve TPC-C throughput by up to 2.65X and Spree throughput by 3.52X.

cs.DB↗

arXiv2026

PADE: A Predictor-Free Sparse Attention Accelerator via Unified Execution and Stage Fusion

Attention-based models have revolutionized AI, but the quadratic cost of self-attention incurs severe computational and memory overhead. Sparse attention methods alleviate this by skipping low-relevance token pairs. However, current approaches lack practicality due to the heavy expense of added sparsity predictor, which severely drops their hardware efficiency. This paper advances the state-of-the-art (SOTA) by proposing a bit-serial enable stage-fusion (BSF) mechanism, which eliminates the need for a separate predictor. However, it faces key challenges: 1) Inaccurate bit-sliced sparsity speculation leads to incorrect pruning; 2) Hardware under-utilization due to fine-grained and imbalanced bit-level workloads. 3) Tiling difficulty caused by the row-wise dependency in sparsity pruning criteria. We propose PADE, a predictor-free algorithm-hardware co-design for dynamic sparse attention acceleration. PADE features three key innovations: 1) Bit-wise uncertainty interval-enabled guard filtering (BUI-GF) strategy to accurately identify trivial tokens during each bit round; 2) Bidirectional sparsity-based out-of-order execution (BS-OOE) to improve hardware utilization; 3) Interleaving-based sparsity-tiled attention (ISTA) to reduce both I/O and computational complexity. These techniques, combined with custom accelerator designs, enable practical sparsity acceleration without relying on an added sparsity predictor. Extensive experiments on 22 benchmarks show that PADE achieves 7.43x speed up and 31.1x higher energy efficiency than Nvidia H100 GPU. Compared to SOTA accelerators, PADE achieves 5.1x, 4.3x and 3.4x energy saving than Sanger, DOTA and SOFA.

cs.AR↗

arXiv2026

Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search

Protein evolution through amino acid mutations is a cornerstone of life sciences. Recent advances in protein language models have shown rich evolutionary patterns, offering unprecedented potential for in-silicon directed evolution. However, existing directed evolution methods largely rely on heuristic evolution strategies and have yet to efficiently integrate the transformative protein language models with advanced optimization techniques, such as reinforcement learning, to adaptively learn superior evolution policies. To bridge this gap, we propose AlphaDE, a novel framework that evolves protein sequences by harnessing the innovative paradigms of large language models, such as fine-tuning and test-time inference. First, AlphaDE fine-tunes pretrained protein language models using masked language modeling on homologous protein sequences to activate the evolutionary plausibility of the interested protein family. Second, AlphaDE introduces test-time inference based on Monte Carlo tree search, which effectively evolves proteins with evolutionary guidance from the fine-tuned protein language model. Extensive benchmark experiments show that AlphaDE remarkably outperforms previous state-of-the-art methods even with few-shot fine-tuning. A case study further demonstrates that AlphaDE supports condensing the protein sequence space of avGFP through computational evolution.

cs.AI↗

arXiv2026

Channel Estimation for RIS-Assisted mmWave Systems via Diffusion Models

Reconfigurable intelligent surface (RIS) has been recognized as a promising technology for next-generation wireless communications. However, the performance of RIS-assisted systems critically depends on accurate channel state information (CSI). To address this challenge, this letter proposes a novel channel estimation method for RIS-aided millimeter-wave (mmWave) systems based on diffusion models (DMs). Specifically, the forward diffusion process of the original signal is formulated to model the received signal as a noisy observation within the framework of DMs. Subsequently, the channel estimation task is formulated as the reverse diffusion process, and a sampling algorithm based on denoising diffusion implicit models (DDIMs) is developed to enable effective inference. Furthermore, a lightweight neural network, termed BRCNet, is introduced to replace the conventional U-Net, significantly reducing the number of parameters and computational complexity. Extensive experiments conducted under various scenarios demonstrate that the proposed method consistently outperforms existing baselines.

eess.SP↗

arXiv2026

PC2P: Multi-Agent Path Finding via Personalized-Enhanced Communication and Crowd Perception

Distributed Multi-Agent Path Finding (MAPF) integrated with Multi-Agent Reinforcement Learning (MARL) has emerged as a prominent research focus, enabling real-time cooperative decision-making in partially observable environments through inter-agent communication. However, due to insufficient collaborative and perceptual capabilities, existing methods are inadequate for scaling across diverse environmental conditions. To address these challenges, we propose PC2P, a novel distributed MAPF method derived from a Q-learning-based MARL framework. Initially, we introduce a personalized-enhanced communication mechanism based on dynamic graph topology, which ascertains the core aspects of ``who" and ``what" in interactive process through three-stage operations: selection, generation, and aggregation. Concurrently, we incorporate local crowd perception to enrich agents' heuristic observation, thereby strengthening the model's guidance for effective actions via the integration of static spatial constraints and dynamic occupancy changes. To resolve extreme deadlock issues, we propose a region-based deadlock-breaking strategy that leverages expert guidance to implement efficient coordination within confined areas. Experimental results demonstrate that PC2P achieves superior performance compared to state-of-the-art distributed MAPF methods in varied environments. Ablation studies further confirm the effectiveness of each module for overall performance.

cs.MA↗

arXiv2025

Motion-driven quantum dissipation in an open electronic system with nonlocal interaction

In this paper, we study excitations and dissipation in two infinite parallel metallic plates undergoing relative motion. The degrees of freedom of the electrons in both plates are modeled using the 1+2 dimensional Dirac field, and a nonlocal potential is selected to describe the interaction between the two plates. The internal relative motion is introduced via a Galilean boost, with one plate assumed to slide relative to the other. We then calculate the effective action of the system and derive the vacuum occupation number in momentum space using a perturbative method. Numerical plots reveal that the vacuum occupation number, as a function of momentum, is isotropic for a motion speed $v = 0$ and anisotropic for nonzero $v$. The relative motion induces energy transfer between the plates, leading to on-shell excitations in a manner analogous to the dissipative process of the Schwinger effect. Consequently, we study the motion-induced dissipation effects and the dissipative forces through the quantum action. Numerical results demonstrate that both the imaginary part of the quantum action due to the motion boost and the dissipative force exhibit a threshold as functions of $v$, and both are positively correlated with $v$.

quant-ph↗

arXiv2025

LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis

Sophisticated text-centric forgeries, fueled by rapid AIGC advancements, pose a significant threat to societal security and information authenticity. Current methods for text-centric forgery analysis are often limited to coarse-grained visual analysis and lack the capacity for sophisticated reasoning. Moreover, they typically treat detection, grounding, and explanation as discrete sub-tasks, overlooking their intrinsic relationships for holistic performance enhancement. To address these challenges, we introduce LogicLens, a unified framework for Visual-Textual Co-reasoning that reformulates these objectives into a joint task. The deep reasoning of LogicLens is powered by our novel Cross-Cues-aware Chain of Thought (CCT) mechanism, which iteratively cross-validates visual cues against textual logic. To ensure robust alignment across all tasks, we further propose a weighted multi-task reward function for GRPO-based optimization. Complementing this framework, we first designed the PR$^2$ (Perceiver, Reasoner, Reviewer) pipeline, a hierarchical and iterative multi-agent system that generates high-quality, cognitively-aligned annotations. Then, we constructed RealText, a diverse dataset comprising 5,397 images with fine-grained annotations, including textual explanations, pixel-level segmentation, and authenticity labels for model training. Extensive experiments demonstrate the superiority of LogicLens across multiple benchmarks. In a zero-shot evaluation on T-IC13, it surpasses the specialized framework by 41.4% and GPT-4o by 23.4% in macro-average F1 score. Moreover, on the challenging dense-text T-SROIE dataset, it establishes a significant lead over other MLLM-based methods in mF1, CSS, and the macro-average F1. Our dataset, model, and code will be made publicly available.

cs.AI↗

arXiv2025

Confinement in metal-organic frameworks as a route to harnessing liquid barocalorics in the solid-state

Barocaloric (BC) effects at liquid-vapor transitions in hydrofluorocarbons drive most commercial technologies used for heating and cooling in the heating, ventilation and air-conditioning sector. However, these fluids suffer from huge global warming potential and alternative gases are less efficient, toxic or flammable. Solid-solid and solid-liquid BC materials have zero global warming potential and could even improve on current device efficiencies. Whilst solid-liquid BCs typically outperform solid-solid BCs, the latter are advantageous as they avoid leaks and present easier handling and recyclability thus facilitating waste management. Here we confine the solid-liquid BC stearic acid inside the nanopores of a functionalised metal-organic framework (MOF) and demonstrate that the colossal BC properties are retained in a solid-state material. Moreover, the enhanced interactions between the pore surface and the BC material allow a level of active control over the thermal response, as opposed to passive encapsulation. Our results open novel avenues to exploit and tune colossal BC effects in a wide range of combinations of solid-liquid BC materials embedded within functionalized MOFs, without the associated engineering drawbacks.

cond-mat.mtrl-sci↗

arXiv2025

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

cs.CV↗

arXiv2025

Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods

This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes, primarily due to the nature of set-based pooling of the neighborhood aggregation scheme. Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models. Importantly, we observe that the denser the graph, the greater such the improvement. We attribute this to the characteristics of node embeddings, where the link state of each link sample could be encoded into the embeddings of nodes that are involved in the neighborhood aggregation of the two nodes in that link sample. In denser graphs, every node could have more opportunities to attend the neighborhood aggregation of other nodes and encode states of more link samples to its embedding, thus learning better node embeddings for link prediction. Lastly, we demonstrate that the insights gained from our research carry important implications in identifying the limitations of existing link prediction methods, which could guide the future development of more robust algorithms.

cs.SI↗

arXiv2025

PETGraphDB: A Property Evolution Temporal Graph Data Management System

Temporal graphs are graphs whose nodes and edges, together with their associated properties, continuously change over time. With the development of Internet of Things (IoT) systems, a subclass of the temporal graph, i.e., Property Evolution Temporal Graph, in which the value of properties on nodes or edges changes frequently while the graph's topology barely changes, is growing rapidly. However, existing temporal graph management solutions are not oriented to the Property Evolution Temporal Graph data, which leads to highly complex data modeling and low-performance query processing of temporal graph queries. To solve these problems, we developed PETGraph, a data management system for Property Evolution Temporal Graph data. PETGraph adopts a valid-time temporal property graph data model to facilitate data modeling, supporting ACID features with transactions. To improve temporal graph query performance, we designed a space-efficient temporal property storage and a fine-granularity multi-level locking mechanism. Experimental results show that PETGraph requires, on average, only 33% of the storage space needed by the current best data management solution. Additionally, it achieves an average of 58.8 times higher transaction throughput in HTAP workloads compared to the best current solutions and outperforms them by an average of 267 times in query latency.

cs.DB↗

arXiv2025

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

Training Vision-Language-Action (VLA) models for generalist robots typically requires large-scale real-world robot data, which is expensive and time-consuming to collect. The inefficiency of physical data collection severely limits the scalability, and generalization capacity of current VLA systems. To address this challenge, we introduce GigaBrain-0, a novel VLA foundation model empowered by world model-generated data (e.g., video generation, real2real transfer, human transfer, view transfer, sim2real transfer data). By leveraging world models to generate diverse data at scale, GigaBrain-0 significantly reduces reliance on real robot data while improving cross-task generalization. Our approach further improves policy robustness through RGBD input modeling and embodied Chain-of-Thought (CoT) supervision, enabling the model to reason about spatial geometry, object states, and long-horizon dependencies during task execution. This leads to substantial gains in real-world performance on dexterous, long-horizon, and mobile manipulation tasks. Extensive experiments demonstrate that GigaBrain-0 achieves superior generalization across variations in appearances (e.g., textures, colors), object placements, and camera viewpoints. Additionally, we present GigaBrain-0-Small, an optimized lightweight variant designed to run efficiently on devices such as the NVIDIA Jetson AGX Orin.

cs.RO↗