arXiv subjects

Chang Guo

Publications and source records attributed to Chang Guo.

14 recordsLinked to original sources

arXiv2026

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-scenario agentic scaling and present AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications. An extensible Domain x Capability x Atomic Difficulty taxonomy aligns these stages and enables fine-grained diagnosis with OmniaBench. AgentOmnia combines bidirectional environment-task synthesis with tool-dependency, program-structured, and solver-based pipelines, constructing 5,018 stateful environments with 255,375 tools and 52,361 tasks. Programs, solvers, and verifiers provide correctness signals, while supervised fine-tuning, online agentic reinforcement learning, and a rollback curriculum support post-training. Evaluation failures translate into Product Requirement Documents (PRDs) for targeted self-evolution. Starting from Qwen3-30B-A3B-Thinking-2507, AgentOmnia raises the pass rate on the OmniaBench challenging subset from 9.16% to 37.11% and the macro-average across OmniaBench, $\tau^2$-Bench, DeepPlanning, and VitaBench from 22.86% to 41.69%. Under a unified protocol,it leads the evaluated agentic post-trained baselines on OmniaBench and retains the highest four-benchmark macro-average. It also surpasses Qwen3-235B-A22B-Thinking-2507 on all four benchmarks and exceeds Qwen3.5-35B-A3B on the macro-average. Gains span three application splits, ten capability dimensions, eight atomic-difficulty factors, and 76 of 90 level-1 domains, indicating broad rather than category-specific improvement. A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings.

cs.AI↗

arXiv2026

Beyond Scaffold Splits: Structural-Frontier Evaluation Reveals Hidden Failures in ADMET Models

Molecular property models are commonly evaluated by holding out Bemis-Murcko scaffolds, yet a scaffold identifier is only one notion of chemical unfamiliarity. We introduce a label-free structural-frontier split that reserves the sparsest and most physicochemically remote scaffold groups, and evaluate it on six public experimental or curated ADMET tasks. Against a 70/10/20 scaffold control with identical acyclic grouping, the frontier inflates equally weighted primary error with a taskwise median of 87.0% and a skew-sensitive mean of 130.3% (descriptive task/seed bootstrap interval, 52.1-246.0%). The mean falls to 75.9% once BBB is removed; that endpoint is the one whose score ranking inverts at the frontier. A message-passing graph-network control still shows a large gap (mean 82.8% over four tasks) and does not invert, so a low-capacity head does not explain the effect. We also test Multi-View Frontier Risk Extrapolation (MV-FREX), a count-adjusted tail-risk penalty over four molecular views, and treat it as a falsifiable probe. It changes normalized frontier error by only 0.16% relative to empirical risk minimization for the perceptron head (interval, -0.43-0.84%) and by -1.9% for the graph network; three fixed robust-penalty controls are likewise inconclusive. Against the published Lo-Hi and DataSAIL splitters, the frontier inflates error more on average, though no split is uniformly hardest. An audit of 31,561 marine natural products further shows that OOD status and agreement with legacy ADMET predictions depend on the molecular view, endpoint, and teacher coverage. Split construction and label provenance are important evaluation constraints in their own right, and the tested training penalties do not resolve the frontier failures we observe.

cs.LG↗

arXiv2026

OmniPresent: Generating Coherent Presentation Suites from Scientific Papers

Transforming static research papers into dynamic media such as posters, slides, and videos is essential for effective dissemination but remains a labor-intensive challenge. Existing automated approaches often treat these formats in isolation and consequently fail to maintain semantic consistency across the entire presentation suite. We address this fragmentation by formalizing the task of unified presentation suite generation and proposing $\textbf{OmniPresent}$ to orchestrate the creation of coherent deliverables. Our framework adopts a renderable HTML representation to enable centralized content planning and a self-correcting verify-and-repair loop that actively resolves conflicts across modalities. We further facilitate scalable research in this domain by releasing $\textbf{OmniPreBench}$, a comprehensive dataset comprising over one thousand papers with paired artifacts, and establishing a rigorous VLM-based evaluation protocol. Empirical results confirm that our method generates high-quality and faithful presentation suites that significantly surpass strong baselines in both accuracy and visual appeal.

cs.SE↗

arXiv2026

IEMAS: An Incentive-Efficiency Routing Framework for Open Agentic Web Ecosystems

The transition to open, distributed Multi-Agent Systems (MAS) promises scalable intelligence but introduces a non-trivial tension: maximizing global efficiency requires cooperative, resource-aware scheduling, yet autonomous agents may be self-interested and cannot be managed by a centralized controller. Prior approaches fall short in two key areas: they typically focus on single-query routing, neglecting long-term resource reuse (e.g., KV-caching) and the complexities of system-level many-to-many matching; furthermore, they rely on generic incentive mechanisms that ignore the distinct characteristics of LLM inference. To bridge this gap, we propose IEMAS (Incentive-Efficiency Mechanism for Multi-Agent Systems), a distributed framework that aligns economic incentives with system performance. IEMAS integrates a probabilistic predictive model to estimate Quality of Service (QoS) under uncertainty, which feeds into a VCG-based bipartite matching mechanism. This design guarantees truthful capability reporting and social optimality while explicitly leveraging KV cache-affinity to minimize computational redundancy. We implement IEMAS on top of vLLM and evaluate it via extensive simulations. Results demonstrate that our incentive-efficiency co-design reducing average service cost by 35% and end-to-end latency by up to 2.9 compared to baselines.

cs.NI↗

arXiv2026

FS_GPlib: Breaking the Web-Scale Barrier - A Unified Acceleration Framework for Graph Propagation Models

Propagation models are essential for modeling and simulating dynamic processes such as epidemics and information diffusion. However, existing tools struggle to scale to large-scale graphs that emerge across social networks, epidemic networks and so on, due to limited algorithmic efficiency, weak scalability, and high communication overhead. We present FS_GPlib, a unified library that enables efficient, high-fidelity propagation modeling on Web-scale graphs. FS_GPlib introduces a dual-acceleration framework: it combines micro-level synchronous message-passing updates with macro-level batched Monte Carlo simulation, leveraging high-dimensional tensor operations for parallel execution. To further enhance scalability, it supports distributed simulation via a novel target-node-based graph partitioning strategy that minimizes communication overhead while maintaining load balance. Theoretically, we show that under ideal assumptions, the runtime of simulations converges approximately to a constant. Extensive experiments demonstrate up to 35,000 times speedup over standard libraries such as NDlib and execution of a full Monte Carlo simulation on a Web-scale (billion-edge) graph in 11 seconds while maintaining high simulation fidelity. FS_GPlib supports 29 propagation models-including epidemic and opinion dynamics and dynamic network models-and offers a lightweight Python API compatible with mainstream data science ecosystems. By addressing the unique challenges of modeling diffusion and cascades on the Web, FS_GPlib provides a scalable, extensible, and theoretically grounded solution for large-scale propagation analysis in epidemiology, social media analysis, and online network dynamics. Code available at: https://github.com/Allen-Ciel/FS_GPlib.

cs.SI↗

arXiv2026

O^3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading

Log-Structured Merge-tree-based Key-Value Stores (LSM-KVS) have been optimized and redesigned for disaggregated storage via techniques such as compaction offloading to reduce the network I/Os between compute and storage. However, the constrained memory space and slow flush at the compute node severely limit the overall write throughput of existing optimizations. In this paper, we propose O3-LSM, a fundamental new LSM-KVS architecture, that leverages the shared Disaggregated Memory (DM) to support a three-layer offloading, i.e., memtable Offloading, flush Offloading, and the existing compaction Offloading. Compared to the existing disaggregated LSM-KVS with compaction offloading only, O3-LSM maximizes the write performance by addressing the above issues. O3-LSM first leverages a novel DM-Optimized Memtable to achieve dynamic memtable offloading, which extends the write buffer while enabling fast, asynchronous, and parallel memtable transmission. Second, we propose Collaborative Flush Offloading that decouples the flush control plane from execution and supports memtable flush offloading at any node with dedicated scheduling and global optimizations. Third, O3-LSM is further improved with the Shard-Level Optimization, which partitions the memtable into shards based on disjoint key-ranges that can be transferred and flushed independently, unlocking parallelism across shards. Besides, to mitigate slow lookups in the disaggregated setting, O3-LSM also employs an adaptive Cache-Enhanced Read Delegation mechanism to combine a compact local cache with DM-assisted memtable delegated read. Our evaluation shows that O3-LSM achieves up to 4.5X write, 5.2X range query, and 1.8X point lookup throughput improvement, and up to 76% P99 latency reduction compared with Disaggregated-RocksDB, CaaS-LSM, and Nova-LSM.

cs.DB↗

arXiv2026

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text generation problem, suffering from hallucination, overlooked critiques, and a lack of verifiable grounding. To address these limitations, we introduce $\textbf{RebuttalAgent}$, the first multi-agents framework that reframes rebuttal generation as an evidence-centric planning task. Our system decomposes complex feedback into atomic concerns and dynamically constructs hybrid contexts by synthesizing compressed summaries with high-fidelity text while integrating an autonomous and on-demand external search module to resolve concerns requiring outside literature. By generating an inspectable response plan before drafting, $\textbf{RebuttalAgent}$ ensures that every argument is explicitly anchored in internal or external evidence. We validate our approach on the proposed $\textbf{RebuttalBench}$ and demonstrate that our pipeline outperforms strong baselines in coverage, faithfulness, and strategic coherence, offering a transparent and controllable assistant for the peer review process.

cs.AI↗

arXiv2025

Structure-Aware Optimal Intervention for Rumor Dynamics on Networks: Node-Level, Time-Varying, and Resource-Constrained

Rumor propagation in social networks undermines social stability and public trust, calling for interventions that are both effective and resource-efficient. We develop a node-level, time-varying optimal intervention framework that allocates limited resources according to the evolving diffusion state. Unlike static, centrality-based heuristics, our approach derives control weights by solving a resource-constrained optimal control problem tightly coupled to the network structure. Across synthetic and real-world networks, the method consistently lowers both the infection peak and the cumulative infection area relative to uniform and centrality-based static allocations. Moreover, it reveals a stage-aware law: early resources prioritize influential hubs to curb rapid spread, whereas later resources shift to peripheral nodes to eliminate residual transmission. By integrating global efficiency with fine-grained adaptability, the framework offers a scalable and interpretable paradigm for misinformation management and crisis response.

cs.SI↗

arXiv2025

Human-Agent Collaborative Paper-to-Page Crafting

In the quest for scientific progress, communicating research is as vital as the discovery itself. Yet, researchers are often sidetracked by the manual, repetitive chore of building project webpages to make their dense papers accessible. While automation has tackled static slides and posters, the dynamic, interactive nature of webpages has remained an unaddressed challenge. To bridge this gap, we reframe the problem, arguing that the solution lies not in a single command, but in a collaborative, hierarchical process. We introduce $\textbf{AutoPage}$, a novel multi-agent system that embodies this philosophy. AutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline from narrative planning to multimodal content generation and interactive rendering. To combat AI hallucination, dedicated "Checker" agents verify each step against the source paper, while optional human checkpoints ensure the final product aligns perfectly with the author's vision, transforming the system from a mere tool into a powerful collaborative assistant. To rigorously validate our approach, we also construct $\textbf{PageBench}$, the first benchmark for this new task. Experiments show AutoPage not only generates high-quality, visually appealing pages but does so with remarkable efficiency in under 15 minutes for less than \$0.1. Code and dataset will be released at $\href{https://mqleet.github.io/AutoPage_ProjectPage/}{Webpage}$.

cs.SE↗

arXiv2025

StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models

Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire response, are too coarse to guide models through intricate problems with multiple sub-parts. To address this, we introduce StructVRM, a method that aligns multimodal reasoning with Structured and Verifiable Reward Models. At its core is a model-based verifier trained to provide fine-grained, sub-question-level feedback, assessing semantic and mathematical equivalence rather than relying on rigid string matching. This allows for nuanced, partial credit scoring in previously intractable problem formats. Extensive experiments demonstrate the effectiveness of StructVRM. Our trained model, Seed-StructVRM, achieves state-of-the-art performance on six out of twelve public multimodal benchmarks and our newly curated, high-difficulty STEM-Bench. The success of StructVRM validates that training with structured, verifiable rewards is a highly effective approach for advancing the capabilities of multimodal models in complex, real-world reasoning domains.

cs.AI↗

arXiv2024

Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching

Although Large Language Models (LLMs) have demonstrated remarkable capabilities, their massive parameter counts and associated extensive computing make LLMs' deployment the main part of carbon emission from nowadays AI applications. Compared to modern GPUs like H$100$, it would be significantly carbon-sustainable if we could leverage old-fashioned GPUs such as M$40$ (as shown in Figure 1, M$40$ only has one third carbon emission of H$100$'s) for LLM servings. However, the limited High Bandwidth Memory (HBM) available on such GPU often cannot support the loading of LLMs due to the gigantic model size and intermediate activation data, making their serving challenging. For instance, a LLaMA2 model with $70$B parameters typically requires $128$GB for inference, which substantially surpasses $24$GB HBM in a $3090$ GPU and remains infeasible even considering the additional $64$GB DRAM. To address this challenge, this paper proposes a mixed-precision with a model modularization algorithm to enable LLM inference on outdated hardware with resource constraints. (The precision denotes the numerical precision like FP16, INT8, INT4) and multi-level caching (M2Cache).) Specifically, our M2Cache first modulizes neurons in LLM and creates their importance ranking. Then, it adopts a dynamic sparse mixed-precision quantization mechanism in weight space to reduce computational demands and communication overhead at each decoding step. It collectively lowers the operational carbon emissions associated with LLM inference. Moreover, M2Cache introduces a three-level cache management system with HBM, DRAM, and SSDs that complements the dynamic sparse mixed-precision inference. To enhance communication efficiency, M2Cache maintains a neuron-level mixed-precision LRU cache in HBM, a larger layer-aware cache in DRAM, and a full model in SSD.

cs.LG↗

arXiv2024

A Zoned Storage Optimized Flash Cache on ZNS SSDs

Zoned Namespace SSDs (ZNS) are introduced recently to mitigate the block interface penalties of flash-based SSDs. It is a good opportunity for flash cache to address cache throughput and write amplification (WA) issues by fully controlling data allocation and garbage collection via zone-based interfaces. However, there are several critical challenges that need to be addressed including zone-interface compatibility, data management of large zone size, and a better tradeoff between throughput, cache hit ratio, and WA. In this paper, we present Z-CacheLib, a zoned storage optimized flash cache on ZNS SSDs. In Z-CacheLib, we propose: 1) a new zStorage Engine for ZNS SSDs with low mapping and operational overhead, and 2) a novel zCache Engine with cross-layer optimizations to resolve the throughput regression and WA issues of garbage collection, which consists of delayed data eviction with virtual over-provisioning (vOP), a top-down eviction policy (zLRU) optimized from LRU, and a bottom-up drop mechanism (zDrop) for low WA. Our evaluation shows that Z-CacheLib can achieve up to 2X throughput, 5% improvement hit ratio, and almost no WA compared to CacheLib with compatible regular SSDs, demonstrating benefits of using ZNS SSDs for cache. Moreover, Z-CacheLib can achieve up to 6X throughput and 92% WA reduction compared with F2FS-based scheme.

cs.PF↗

arXiv2022

SAPPHIRE: Search for exotic parity-violation interactions with quantum spin amplifiers

Quantum sensing provides sensitive tabletop tools to search for exotic spin-dependent interactions beyond the Standard Model, which has attracted great attention in theories and experiments. Here we develop a technique based on quantum Spin Amplifier for Particle PHysIcs REsearch (SAPPHIRE) to resonantly search for exotic interactions, specifically parity-odd spin-spin interactions. The present technique effectively amplifies the pseudomagnetic field generated by exotic interactions by a factor of about 200 while being insensitive to spurious external magnetic fields. Our studies, using such a quantum amplification technique, open the doors to exploring the parity-violation interactions mediated by Z' bosons in the challenging parameter space (force range between 3 mm and 0.1 km) and set the most stringent constraints on Z'-mediated electron-neutron couplings, significantly improving previous limits by up to five orders of magnitude. Moreover, our bounds on Z'-mediated couplings between nucleons reaches into a hitherto unexplored parameter space (force range below 1 m), complementing the existing astrophysical and laboratory studies.

quant-ph↗

arXiv2022

Limits on axions and axionlike particles within the axion window using a spin-based amplifier

Searches for the axion and axionlike particles may hold the key to unlocking some of the deepest puzzles about our universe, such as dark matter and dark energy. Here we use the recently demonstrated spin-based amplifier to constrain such hypothetical particles within the well-motivated ``axion window'' (1 $\mu$eV-1 meV) through searching for an exotic spin-spin interaction between polarized electron and neutron spins. The key ingredient is the use of hyperpolarized long-lived $^{129}$Xe nuclear spins as an amplifier for the pseudomagnetic field generated by the exotic interaction. Using such a spin sensor, we obtain a direct upper bound on the product of coupling constants $g_p^e g_p^n$. The spin-based amplifier technique can be extended to searches for a wide variety of hypothetical particles beyond the Standard Model.

physics.ins-det↗