arXiv subjects

Peiyu Zhang

Publications and source records attributed to Peiyu Zhang.

At least 19 recordsLinked to original sources

arXiv2026

From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents

Long-term memory enables LLM agents to reuse past experiences, yet retrieving relevant memories does not necessarily provide sufficient evidence for answering a query. Essential information may remain fragmented across memory records, obscured by abstraction, or disconnected from the relations required for reasoning. We identify this relevance-sufficiency gap and propose QEMem, a framework that reformulates memory utilization as the construction of query-specific evidence sets, shifting the focus from individual retrieval relevance to collective evidential support. QEMem integrates three complementary mechanisms: query-guided discovery retrieves evidence across multiple memory granularities; source-grounded reification organizes it into structured ViewCards with explicit evidential roles and source references; and sufficiency-guided refinement selectively recovers missing information. Operating on existing memory stores without modifying memory formation, QEMem achieves 91.43% LLM-judge accuracy on LoCoMo with Claude Opus 4.5, outperforming the strongest evaluated baseline, MemR$^3$, by 7.6 percentage points and NEMORI by 10.7 points under a shared memory store. Further analyses demonstrate improved evidence coverage and strong performance on questions requiring cross-session evidence integration.

cs.AI↗

arXiv2026

LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making

Laboratory experiments involve more than following predefined protocols; they require adaptive decision-making as the experimental state changes. Existing scientific benchmarks rarely assess such evidence-based decisions in laboratory settings. Here we present LabOPBench, a multimodal benchmark of 756 expert-authored, independently reviewed questions in organic synthesis and materials science. Each item pairs laboratory evidence with procedural context and an open-ended judgment, evaluated using a question-specific scoring rubric. Eight multimodal models obtain overall normalized scores of 28.8-45.8%, leaving substantial room for improvement. On a controlled 100-question subset, the strongest models outperform undergraduate participants on average but remain below the average performance of PhD participants. Expert analysis of responses from the three leading models identifies Evidence Misreading and Evidence-Decision Conflict as the dominant error patterns. These results reveal that current models still struggle to turn multimodal perception into reliable laboratory decision-making.

cs.AI↗

arXiv2026

Ideal balanced pairs in n-exangulated categories

This paper is devoted to ideal approximation theory in $n$-exangulated categories. We define ideal balanced pairs and explore their properties and equivalent characterizations. We prove that any complete ideal cotorsion triple $(\mathcal{I},\mathcal{K},\mathcal{J})$ satisfying suitable assumptions yields an ideal balanced pair $(\mathcal{I}, \mathcal{J})$, and the converse holds under additional hypotheses. We further show that for an ideal balanced pair, it is equivalent to an additive subfunctor with enough projective morphisms and enough injective morphisms.

math.CT↗

arXiv2026

Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems

Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect effective communication, a favorable agent architecture, or simply additional reasoning? Because communication methods are commonly evaluated within the systems they were designed for, these factors are difficult to disentangle. Final accuracy further merges corrected errors and corrupted answers into a single outcome, obscuring how communication changes decisions. We introduce Independent--Communicate--Revise (ICR), a controlled framework that evaluates communication as answer revision following independent reasoning. ICR fixes initial reasoning trajectories, measures correction and preservation conditional on both agents' initial correctness, and uses a no-message revision control to quantify gains beyond additional reasoning. Across four reasoning benchmarks, our audit of textual and latent communication reveals that similar aggregate accuracy can conceal substantially different revision behaviors. Compared with transmitting answers alone, full reasoning increases correction while reducing preservation on all four benchmarks, so richer messages amplify beneficial and harmful influence alike. Receiver-policy comparisons on MedQA and GPQA-D further show that a structured verification policy shifts every channel toward greater preservation and lower correction, while its effect on selectivity varies across channels and tasks. These findings challenge treating communication quality as an intrinsic property of a channel. ICR therefore recenters evaluation on selective revision, providing a unified framework for examining how message content and receiver policies jointly produce benefits and harms.

cs.AI↗

arXiv2026

Anomalous pressure-dependent viscosity of basaltic melts and its role in asthenosphere melt accumulation

The asthenosphere's mechanical weakness enables plate tectonics, but its origin is debated. Partial melt has been proposed to cause this softening, yet recent studies suggest that the measured viscosity minimum in basaltic melts, an essential control on melt mobility, is an experimental artifact. Using quantum mechanics-based, machine learning-accelerated molecular dynamics, we extend simulation timescales by more than a factor of 1000 and achieve percent-level precision. We show that basaltic melt exhibits a robust viscosity minimum (approximately 20% below 1-bar values) at approximately 3 GPa, driven by pressure-induced reorganization of aluminum coordination that facilitates shear relaxation while silicon-oxygen polyhedra remain structurally rigid. Our results reveal a depth-dependent rheological transition: melt mobility peaks below approximately 150 km, promoting efficient extraction, but declines sharply during ascent, causing melt to stagnate beneath the lithosphere. This mechanism provides a physical basis for the dual seismic signatures of a melt-depleted deep asthenosphere and a melt-enriched layer near the lithosphere-asthenosphere boundary.

physics.chem-ph↗

arXiv2026

Elasticity of polycrystalline davemaoite constrains its grain size in the lower mantle

Earth's lower mantle hosts large low shear-velocity provinces (LLSVPs) beneath Africa and the Pacific, but their origin remains debated. Davemaoite, a major lower-mantle mineral, has been proposed as a contributor to these anomalies; however, its experimentally measured shear modulus is approximately 30% lower than first-principles predictions, a longstanding discrepancy between theory and experiment. Here, using million-atom machine-learning molecular dynamics simulations, we show that nanoscale grain-boundary disorder, invisible to conventional x-ray diffraction, can reconcile this gap. Introducing 5.8 vol% disordered regions reduces the shear and bulk moduli by 37% and 12%, respectively. This shear-selective softening can reproduce LLSVP-like seismic anomalies in basalt-rich assemblages, but only at disorder levels corresponding to grain sizes smaller than those expected in the lower mantle. Combining the disorder-elasticity relationship with seismic constraints, we derive a minimum davemaoite grain size of approximately 100 nm. This limit is consistent with mantle grain growth models and with attenuation-based evidence for coarse-grained LLSVPs.

physics.chem-ph↗

arXiv2026

Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction

Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and for identifying functional signatures. Existing studies have linked fractal and multifractal scaling to age and examined the reliability of individual features. However, prediction repeatability depends on how features fluctuate jointly and how a predictor combines them, which feature-wise reliability assessments do not capture. To address this problem, we propose Repeat-informed Multifractal Curve Regression (RMCR), a structured framework for learning stable age-predictive patterns from multifractal curves. By jointly modeling curve structure and repeat-scan variability, RMCR learns predictive combinations of fluctuation orders that target both accuracy and within-subject consistency. Relative to a matched run-level ridge baseline, RMCR reduces single-run MAE by 6.1% on HCP-A and 7.9% on an external Cam-CAN cohort, and within-visit repeat absolute difference by 18.5% on HCP-A, using a single scan at inference.

cs.LG↗

arXiv2026

HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling

Multi-label classification (MLC) requires predicting multiple relevant labels for each instance, where a central challenge is modeling complex label dependencies arising from co-occurrence patterns. Existing approaches are limited in capturing high-order label correlations, relying on implicit learning through contrastive objectives or pairwise attention mechanisms without structural guidance. We propose HyperLabel, an encoder-decoder framework that explicitly models label dependencies through hypergraph neural networks. Our contributions are twofold: (i) We construct a label hypergraph where sample-defined hyperedges naturally encode multi-way co-occurrence patterns, providing explicit structural prior knowledge that captures relationships beyond pairwise interactions. (ii) We propose a unified cross-modal learning approach where HGNN+ performs bidirectional message passing to integrate feature information with label structure, and a shared cross-attention decoder processes both modalities through complementary learning objectives. Extensive experiments on seven benchmark datasets demonstrate that HyperLabel achieves state-of-the-art performance, with particularly significant improvements on macro-F1 scores (+10.3% on Delicious, +8.2% on Bibtex), validating that explicit hypergraph structure effectively captures complex label relationships. The code is available at https://github.com/iZHpy/Multi-label_hypergraph .

cs.LG↗

arXiv2026

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

cs.AI↗

arXiv2026

CARE: Context-Aware Ranking Evolution with Executable Scoring Programs for Budgeted Reaction Optimization

High-throughput experimentation can evaluate many reaction conditions, yet combinatorial condition spaces still exceed the available experiment budget. This makes experiment selection a sequential decision problem: each new condition must be chosen from limited observations before its outcome is known. LLMs can express task-specific selection logic. A direct recommendation, however, is neither a persistent executable object that can be validated and revised nor an independently auditable decision rule. We introduce CARE, a reference-conditioned controller that separates program synthesis from experiment selection. An LLM writes an executable scoring program that ranks the remaining conditions, while a non-LLM reference policy supplies a numerical candidate and support summary. CARE forms an optional alternative from the program, applies a reference-conditioned intervention gate to compare it with the reference, and records the decision before the selected outcome is revealed. Each new outcome updates controller state and can trigger retention, revision, or regeneration of the active program. This outcome-guided program evolution changes the scoring logic without updating the LLM parameters. In matched offline replay with 30 seeds on eight reaction-optimization tasks, CARE attains the lowest normalized regret, the highest normalized best-so-far AUC, and the highest Top-1% Success@15 among the evaluated methods. These results support using a scoring program written by an LLM as one component of a reference-conditioned optimizer rather than as a standalone experiment selector.

cs.LG↗

arXiv2026

Emergent Skyrmion Hall Effect in $d$-wave Altermagnets at Finite Temperature

Altermagnets combine compensated magnetic order with unconventional symmetry-dependent responses, offering a promising platform for spintronic applications. Here, we show that a voltage-controlled magnetic-anisotropy gradient drives altermagnetic (ATM) skyrmions in a nearly rectilinear, Hall-free manner in the absence of thermal fluctuations, owing to their strongly compensated gyrotropic response. Thermal magnons qualitatively modify this behavior by increasing the longitudinal drag through magnon--skyrmion scattering and generating a transverse reaction force through handedness-dependent skew scattering. Owing to the anisotropic altermagnetic magnon band structure, the relative transport weights of the two magnon handednesses are interchanged between propagation along the $x$ and $y$ directions, resulting in transverse skyrmion drifts of opposite sign. By contrast, along the high-symmetry direction, the two magnon handednesses remain degenerate and their transverse contributions cancel, preserving Hall-free motion even at finite temperature. We thus uncover a thermally emergent anisotropic skyrmion Hall effect whose direction-dependent magnitude and sign originate from the intrinsic symmetry-dependent magnon spectrum, making it a generic finite-temperature dynamical feature of ATM skyrmions. Our results establish a low-power route toward electrically controlled and thermally tunable ATM skyrmion transport.

cond-mat.mtrl-sci↗

arXiv2026

SureRoute: Toward a Hallucination-Free Self-Improving Platform for Retrosynthesis

AI models, including large language models, are increasingly integrated into scientific discovery workflows, yet they remain prone to hallucination. In experimental sciences, such errors translate directly into failed wet-lab validations and wasted resources; in self-improving agentic systems, confident errors risk being reinforced rather than corrected. Retrosynthesis provides a representative example of this failure mode: existing models can generate chemically plausible routes, but cannot reliably determine which routes are experimentally feasible. We define \textbf{Chemical Hallucination} as a route that appears valid yet fails under competing reactive sites, unresolved selectivity, or missing mechanistic support, a failure largely invisible to the Recall@$K$ metric. We introduce \textbf{SureRoute}, a chemical verifier-anchored retrosynthesis platform that suppresses Chemical Hallucination. SureRoute combines a multi-model ensemble, data asset retrieval, and \textbf{ChemHarness}, an executable chemical intuition engine for route verification and reliability-first ranking. On a benchmark of 350 real-world industrial targets, SureRoute reaches 74.3\% recall@1, 2.2--3.5$\times$ that of seven single-step models and three frontier LLMs, while cutting top-1 Chemical Hallucination to 4.6\%, a 4--6$\times$ reduction relative to frontier LLMs. As a model-agnostic reranker, ChemHarness drives detectable hallucination toward near-zero across arbitrary backbone candidates. SureRoute shows that reliable scientific AI requires not only strong generation, but executable verification.

q-bio.QM↗

arXiv2026

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sustain gains as depth increases, exhibiting degradation, early plateauing, or saturation. We propose ReM-MoA, a memory-augmented MoA framework that sustains scaling through two mechanisms: (1) a Ranked Reasoning Memory that persistently stores and ranks reasoning traces from all layers using a comparative Reviewer Agent, and (2) a Curated Diversified Memory Routing scheme that exposes different agents to distinct combinations of successful and failed traces, preserving exploration diversity while propagating high-quality reasoning. We further introduce an optional multi-domain Reviewer distillation pipeline that improves ranking quality through frontier-model supervision. Across five reasoning benchmarks spanning math, formal logic, code, knowledge, and commonsense, ReM-MoA consistently outperforms prior MoA variants across both depth and width scaling, and its advantage widens with depth, establishing structured cross-layer reasoning memory as a key missing mechanism for scalable multi-agent inference.

cs.AI↗

arXiv2026

VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation

Automation of Register Transfer Level (RTL) design can help developers meet increasing computational demands. Large Language Models (LLMs) show promise for Hardware Description Language (HDL) generation, but face challenges due to limited parametric knowledge and domain-specific constraints. While prompt engineering and fine-tuning have limitations in knowledge coverage and training costs, multi-agent architectures offer a training-free paradigm to enhance reasoning through collaborative generation. However, current multi-agent approaches suffer from two critical deficiencies: susceptibility to noise propagation and constrained reasoning space exploration. We propose VeriMoA, a training-free mixture-of-agents (MoA) framework with two synergistic innovations. First, a quality-guided caching mechanism to maintain all intermediate HDL outputs and enables quality-based ranking and selection across the entire generation process, encouraging knowledge accumulation over layers of reasoning. Second, a multi-path generation strategy that leverages C++ and Python as intermediate representations, decomposing specification-to-HDL translation into two-stage processes that exploit LLM fluency in high-resource languages while promoting solution diversity. Comprehensive experiments on VerilogEval 2.0 and RTLLM 2.0 benchmarks demonstrate that VeriMoA achieves 15--30% improvements in Pass@1 across diverse LLM backbones, especially enabling smaller models to match larger models and fine-tuned alternatives without requiring costly training.

cs.AI↗

arXiv2026

COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation

LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches universally decouple the two objectives, optimizing PPA only after correctness is fully achieved. Whether through sequential multi-agent pipelines, evolutionary search with binary correctness gates, or hierarchical reward dependencies, partially correct but architecturally promising candidates are systematically discarded. Moreover, existing methods reduce the multi-objective PPA space to a single scalar fitness, obscuring the trade-offs among area, delay, and power. To address these limitations, we propose COEVO, a co-evolutionary framework that unifies correctness and PPA optimization within a single evolutionary loop. COEVO formulates correctness as a continuous co-optimization dimension alongside area, delay, and power, enabled by an enhanced testbench that provides fine-grained scoring and detailed diagnostic feedback. An adaptive correctness gate with annealing allows PPA-promising but partially correct candidates to guide the search toward jointly optimal solutions. To preserve the full PPA trade-off structure, COEVO employs four-dimensional Pareto-based non-dominated sorting with configurable intra-level sorting, replacing scalar fitness without manual weight tuning. Evaluated on VerilogEval 2.0 and RTLLM 2.0, COEVO achieves 97.5\% and 94.5\% Pass@1 with GPT-5.4-mini, surpassing all agentic baselines across four LLM backbones, while attaining the best PPA on 43 out of 49 synthesizable RTLLM designs.

cs.AI↗

arXiv2026

POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization

Applying large language models (LLMs) to RTL code optimization for improved power, performance, and area (PPA) faces two key challenges: ensuring functional correctness of optimized designs despite LLM hallucination, and systematically prioritizing power reduction within the multi-objective PPA trade-off space. We propose POET (Power-Oriented Evolutionary Tuning), a framework that addresses both challenges. For functional correctness, POET introduces a differential-testing-based testbench generation pipeline that treats the original design as a functional oracle, using deterministic simulation to produce golden references and eliminating LLM hallucination from the verification process. For PPA optimization, POET employs an LLM-driven evolutionary mechanism with non-dominated sorting, power-first intra-level ranking, and proportional survivor selection to steer the search toward the low-power region of the Pareto front without manual weight tuning. Evaluated on the RTL-OPT benchmark across 40 diverse RTL designs, POET achieves 100% functional correctness, the best power on all 40 designs, and competitive area and delay improvements.

cs.AR↗

arXiv2025

End-to-End Learning Framework for Solving Non-Markovian Optimal Control

Integer-order calculus often falls short in capturing the long-range dependencies and memory effects found in many real-world processes. Fractional calculus addresses these gaps via fractional-order integrals and derivatives, but fractional-order dynamical systems pose substantial challenges in system identification and optimal control due to the lack of standard control methodologies. In this paper, we theoretically derive the optimal control via linear quadratic regulator (LQR) for fractional-order linear time-invariant (FOLTI) systems and develop an end-to-end deep learning framework based on this theoretical foundation. Our approach establishes a rigorous mathematical model, derives analytical solutions, and incorporates deep learning to achieve data-driven optimal control of FOLTI systems. Our key contributions include: (i) proposing an innovative system identification method control strategy for FOLTI systems, (ii) developing the first end-to-end data-driven learning framework, Fractional-Order Learning for Optimal Control (FOLOC), that learns control policies from observed trajectories, and (iii) deriving a theoretical analysis of sample complexity to quantify the number of samples required for accurate optimal control in complex real-world problems. Experimental results indicate that our method accurately approximates fractional-order system behaviors without relying on Gaussian noise assumptions, pointing to promising avenues for advanced optimal control.

eess.SY↗

arXiv2025

H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs

The growing interests and applications of graph learning in diverse domains have propelled the development of a unified model generalizing well across different graphs and tasks, known as the Graph Foundation Model (GFM). Existing research has leveraged text-attributed graphs (TAGs) to tackle the heterogeneity in node features among graphs. However, they primarily focus on homogeneous TAGs (HoTAGs), leaving heterogeneous TAGs (HeTAGs), where multiple types of nodes/edges reside, underexplored. To enhance the capabilities and applications of GFM, we introduce H$^2$GFM, a novel framework designed to generalize across both HoTAGs and HeTAGs. Our model projects diverse meta-relations among graphs under a unified textual space, and employs a context encoding to capture spatial and higher-order semantic relationships. To achieve robust node representations, we propose a novel context-adaptive graph transformer (CGT), effectively capturing information from both context neighbors and their relationships. Furthermore, we employ a mixture of CGT experts to capture the heterogeneity in structural patterns among graph types. Comprehensive experiments on a wide range of HoTAGs and HeTAGs as well as learning scenarios demonstrate the effectiveness of our model.

cs.LG↗