arXiv subjects

Jianhui Yang

Publications and source records attributed to Jianhui Yang.

14 recordsLinked to original sources

arXiv2026

Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning

While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must match the temporal context of each case, as retroactive application of statutes violates core legal principles and leads to erroneous conclusions. Our observations reveal that current legal LLMs suffer from temporal bias anchored to their training cutoff, while search agents rarely incorporate temporal constraints into queries, and that web search alone cannot provide the precise statute and precedent citations that legal reasoning demands. To address these challenges, we propose LegalSearch-R1, an end-to-end reinforcement learning framework that pairs local statute RAG for precise article matching with online web search for broader legal knowledge, trained on temporally-indexed data spanning multiple amendment periods to enforce temporal consistency. Extensive experiments on our benchmark covering 13 legal tasks demonstrate that our 7B-parameter agent outperforms state-of-the-art deep research frameworks and specialized legal LLMs by 12.9% to 29.8%, surpasses baselines by 57.7% to 80.3% on temporal consistency, and exhibits robust out-of-domain generalization. The code and data are available at https://github.com/AlexFanw/LegalSearch-R1.

cs.CL↗

arXiv2025

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance

Query-product relevance prediction is vital for AI-driven e-commerce, yet current LLM-based approaches face a dilemma: SFT and DPO struggle with long-tail generalization due to coarse supervision, while traditional RLVR suffers from sparse feedback that fails to correct intermediate reasoning errors. We propose Stepwise Hybrid Examination (SHE), an RL framework that ensures logical consistency through Stepwise Reward Policy Optimization (SRPO). SRPO utilizes a hybrid reward mechanism-combining generative reward models with human-annotated verifiers-to provide fine-grained, step-level signals. To further enhance stability, SHE incorporates diversified data filtering to maintain policy entropy and a multi-stage curriculum learning protocol for progressive skill acquisition. Extensive experiments on real-world search benchmarks show that SHE improves both reasoning quality and relevance-prediction accuracy in large-scale e-commerce settings, outperforming SFT, DPO, GRPO, and other baselines, while also enhancing interpretability and robustness.

cs.AI↗

arXiv2025

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of business rules and user queries exposes the inability of existing methods to endow models with robust reasoning capacity for long-tail and challenging cases. Efforts to address this via reinforcement learning strategies like Group Relative Policy Optimization (GRPO) often suffer from sparse terminal rewards, offering insufficient guidance for multi-step reasoning and slowing convergence. To address these challenges, we propose TaoSR-AGRL, an Adaptive Guided Reinforcement Learning framework for LLM-based relevance prediction in Taobao Search Relevance. TaoSR-AGRL introduces two key innovations: (1) Rule-aware Reward Shaping, which decomposes the final relevance judgment into dense, structured rewards aligned with domain-specific relevance criteria; and (2) Adaptive Guided Replay, which identifies low-accuracy rollouts during training and injects targeted ground-truth guidance to steer the policy away from stagnant, rule-violating reasoning patterns toward compliant trajectories. TaoSR-AGRL was evaluated on large-scale real-world datasets and through online side-by-side human evaluations on Taobao Search. It consistently outperforms DPO and standard GRPO baselines in offline experiments, improving relevance accuracy, rule adherence, and training stability. The model trained with TaoSR-AGRL has been successfully deployed in the main search scenario on Taobao, serving hundreds of millions of users.

cs.IR↗

arXiv2025

MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning

Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MAS with legal tasks is a crucial step. While previous studies have developed legal benchmarks for LLM agents, none are specifically designed to consider the unique advantages of MAS, such as task decomposition, agent specialization, and flexible training. In fact, the lack of evaluation methods limits the potential of MAS in the legal domain. To address this gap, we propose MASLegalBench, a legal benchmark tailored for MAS and designed with a deductive reasoning approach. Our benchmark uses GDPR as the application scenario, encompassing extensive background knowledge and covering complex reasoning processes that effectively reflect the intricacies of real-world legal situations. Furthermore, we manually design various role-based MAS and conduct extensive experiments using different state-of-the-art LLMs. Our results highlight the strengths, limitations, and potential areas for improvement of existing models and MAS architectures.

cs.AI↗

arXiv2025

Image-based modelling of rock non-linear deformation under low-stress levels

Rock geophysical properties are widely reported to exhibit non-linear behaviours under low-stress conditions (below 10-20 MPa) before transitioning to the linear elastic stage, primarily due to the closure of microcracks and grain interfaces. Image-based modelling of rock deformation struggles to effectively characterise the microcrack closure effect because of the partial-volume effect, where image voxels are larger than microcracks and contain both pore and solid phases. This study presents a novel method to simulate non-linear rock deformation under elevated stress conditions. The method reconstructs digital rock models by treating partial-volume voxels as transitional phases that incorporate microcracks. By assigning intermediate elastic moduli and assuming that the pore portion within each partial-volume voxel deforms before the remaining solid content, the method employs the finite element method to simulate rock deformation and calculate the porosity of the deformed model. The method is tested on two Bentheimer sandstone models, and the results demonstrate its ability to predict the non-linear changes in porosity and elastic properties as the effective stress increases. This work provides a new pathway for image-based modelling of non-linear rock deformation considering the microcrack closure effect, offering valuable insights into the complex mechanical behaviour of rocks under confinement.

physics.geo-ph↗

arXiv2025

Image-based modelling of elastic properties using unresolved rock images

The trade-off between image resolution and model field-of-view has long been a limitation for numerical simulations in digital rock models. A significant amount of sub-resolution pore space cannot be captured in the unresolved digital rock images, which hinders the accuracy of numerical simulations, especially those predicting the rock effective elastic properties. This work uses paired digital rock images at multiple resolutions to investigate the sub-resolution solid and pore fraction distributions. It demonstrates that the cumulative Beta distribution function can effectively represent the solid and pore fractions in unresolved rock images. Based on this finding, we propose a novel methodology to predict the sub-resolution pore fractions. Compared to the pore fractions extracted from paired Bentheimer sandstone images at resolutions of 2, 6, and 18um, the proposed method yields double-weighted mean absolute percentage errors (WWMAPE) of 3.67% (6um) and 13.78% (18um), significantly lower than the SLOT technique's errors of 24.55% (6um) and 59.33% (18um). By incorporating the modelled solid and pore fractions with effective medium theory, this work achieves improved predictions of effective elastic moduli and wave velocities across various rock types. This method has significant implications for conducting enhanced simulations of geophysical properties in unresolved rock models.

physics.geo-ph↗

arXiv2025

TaoSR1: The Thinking Model for E-commerce Relevance Search

Query-product relevance prediction is a core task in e-commerce search. BERT-based models excel at semantic matching but lack complex reasoning capabilities. While Large Language Models (LLMs) are explored, most still use discriminative fine-tuning or distill to smaller models for deployment. We propose a framework to directly deploy LLMs for this task, addressing key challenges: Chain-of-Thought (CoT) error accumulation, discriminative hallucination, and deployment feasibility. Our framework, TaoSR1, involves three stages: (1) Supervised Fine-Tuning (SFT) with CoT to instill reasoning; (2) Offline sampling with a pass@N strategy and Direct Preference Optimization (DPO) to improve generation quality; and (3) Difficulty-based dynamic sampling with Group Relative Policy Optimization (GRPO) to mitigate discriminative hallucination. Additionally, post-CoT processing and a cumulative probability-based partitioning method enable efficient online deployment. TaoSR1 significantly outperforms baselines on offline datasets and achieves substantial gains in online side-by-side human evaluations, introducing a novel paradigm for applying CoT reasoning to relevance classification.

cs.IR↗

arXiv2025

LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation

Retrieval-augmented generation (RAG) has proven highly effective in improving large language models (LLMs) across various domains. However, there is no benchmark specifically designed to assess the effectiveness of RAG in the legal domain, which restricts progress in this area. To fill this gap, we propose LexRAG, the first benchmark to evaluate RAG systems for multi-turn legal consultations. LexRAG consists of 1,013 multi-turn dialogue samples and 17,228 candidate legal articles. Each sample is annotated by legal experts and consists of five rounds of progressive questioning. LexRAG includes two key tasks: (1) Conversational knowledge retrieval, requiring accurate retrieval of relevant legal articles based on multi-turn context. (2) Response generation, focusing on producing legally sound answers. To ensure reliable reproducibility, we develop LexiT, a legal RAG toolkit that provides a comprehensive implementation of RAG system components tailored for the legal domain. Additionally, we introduce an LLM-as-a-judge evaluation pipeline to enable detailed and effective assessment. Through experimental analysis of various LLMs and retrieval methods, we reveal the key limitations of existing RAG systems in handling legal consultation conversations. LexRAG establishes a new benchmark for the practical application of RAG systems in the legal domain, with its code and data available at https://github.com/CSHaitao/LexRAG.

cs.CL↗

arXiv2024

FePd2Te2: An Anisotropic Two-Dimensional Ferromagnet with One-Dimensional Fe Chains

Two-dimensional (2D) magnets have attracted significant attentions in recent years due to their importance in the research on both fundamental physics and spintronic applications. Here, we report the discovery of a new ternary compound FePd2Te2. It features a layered quasi-2D crystal structure with one-dimensional Fe zigzag chains extending along the b-axis in the cleavage plane. Single crystals of FePd2Te2 with centimeter-size could be grown. Density functional theory calculations, mechanical exfoliation and atomic force microscopy on these crystals reveal that they are 2D materialsthat can be thinned down to 5 nm. Magnetic characterization shows that FePd2Te2 is an easy-plane ferromagnet with Tc 183 K and strong in-plane uniaxial magnetic anisotropy. Magnetoresistance and anomalous Hall effect demonstrate that ferromagnetism could maintain in FePd2Te2 flakes with large coercivity. A crystal twinning effect is observed by scanning tunneling microscopy which makes the Fe chains right-angle bent in the cleavage plane and creates an intriguing spin texture. Our results show that FePd2Te2 is a correlated anisotropic 2D magnets that may attract multidisciplinary research interests.

cond-mat.mtrl-sci↗

arXiv2022

Wave induced thrust on a submerged hydrofoil: pitch stiffness effects

Submerged flapping foils can convert wave energy directly into thrust, which could be potentially utilised for green marine propulsion. This study analyses the wave-induced flapping hydrofoil propulsion using an in-house developed, new computational fluid dynamics (CFD) framework. The numerical model was initially validated against a few benchmarked problems and then used for the numerical investigation of wave-induced flapping hydrofoil propulsion. The transition between drag and thrust can be observed from the vortex flow pattern. The pitch stiffness and other physical parameter were non-dimensionalised for the first time. The optimal wave conditions and the optimal pitch stiffness are given for the future green marine system design.

physics.flu-dyn↗

arXiv2022

Predicted high-temperature superconductivity in rare earth hydride ErH2 at moderate pressure

Hydrides offer an opportunity to study high-temperature (Tc) superconductivity at experimentally achievable pressures. However, they remained extremely high. Using density functional theory calculations, herein we demonstrated that a newly rare earth hydride, namely bulk ErH2, could be superconducting with a Tc around 80 K at 14.5 GPa. To date, the drived pressure is the lowest reported value for compressed hydrides. Besides superconductivity, Fermi Surface nesting and Kondo effect were manifested at this pressure. Intriguingly, due to Kondo destruction, superconductivity was prone to exist at 15 GPa. Under the rest of applied pressures, we also revealed a gap of band structure at 20 GPa on the background of normal metallic states. At 20 GPa, this compressed system could act as a host of superconductor being judged from a sharp jump of spontaneous magnetic susceptibility with an evanescent spin density of state at Fermi level along with the competition between spin density wave and superconductivity. Finally, electron pairing glue for ErH2 at these three typical pressures was attributed to the antiferromagnetic spin fluctuation.

cond-mat.supr-con↗

arXiv2021

DyOCl: a rare-earth based two-dimensional van der Waals material with strong magnetic anisotropy

Comparing with the widely known transitional metal based van der Waals (vdW) materials, rare-earth based ones are rarely explored in the research of intrinsic two-dimensional (2D) magnetism. In this work, we report the physical properties of DyOCl, a rare-earth based vdW magnetic insulator with direct band gap of $\sim 5.72~eV$. The magnetic order of bulk DyOCl is determined by neutron scattering as the $A$-type antiferromagnetic structure below the Néel temperature $T_N=10~$K. The large magnetic moment near 10.1 $ μ_{B} $/Dy lies parallel to the $a$-axis with strong uniaxial magnetic anisotropy. At $2~K$, a moderate magnetic field ($\sim 2~T$) applied along the easy axis generates spin-flip transitions and polarizes DyOCl to a ferromagnetic state. Density functional theory calculations reveal an extremely large magnetic anisotropy energy ($-5850~μeV/Dy$) for DyOCl, indicating the great potentials to realize magnetism in 2D limit. Furthermore, the mechanical exfoliation of bulk DyOCl single crystals down to seven layers is demonstrated. Our findings suggest DyOCl is a promising material playground to investigate 2D $f$-electron magnetism and spintronic applications at the nanoscale.

cond-mat.mtrl-sci↗

arXiv2021

Simulating volume-controlled invasion of a non-wetting fluid in volumetric images using basic image processing tools

A new algorithm is presented for simulating volume-controlled invasion of a non-wetting phase into voxel images. This method is complementary to the traditional morphological image opening method which mimics pressure-based invasion. A key advantage of the volume-based approach is that all saturations between 0 and 1 can obtained rather than the irregularly and widely spaced saturation steps obtained by pressure-based methods. Because of the incremental increases in saturation, it becomes possible to correctly predict defending phase trapping, which is not the case when pressure-based steps are applied. The algorithm is validated against morphological image opening and obtains near perfect agreement at equal saturations as expected from theory. It is also demonstrated that a volume-controlled capillary pressure curve can be obtained that displays the characteristic jumps in capillary pressure, and moreover, the envelop of peak pressures yields the pressure-based capillary pressure obtained by morphological opening, so in fact the results of the proposed algorithm are a superset of the morphological approach. Finally, results are compared to multiphase lattice Boltzmann and qualitatively similar results were achieved in substantially less time. The lattice Boltzmann method is more flexible in terms of variable contact angle and inclusion of viscous effects, but for quasi-static volume-based injection of a non-wetting fluid, the proposed method is viable alternative.

physics.flu-dyn↗

arXiv2020

Insights into thermal transport property of monolayer C$_4$N$_3$H: a first-principles study

The electronic and thermal transport properties have been systematically investigated in monolayer C$_4$N$_3$H with first-principles calculations. The intrinsic thermal conductivity of monolayer C$_4$N$_3$H was calculated coupling with phonons Boltzmann transport equation. For monolayer C$_4$N$_3$H, the thermal conductivity (\k{appa}) (175.74 and 157.90 W m-1K-1 with a and b-plane, respectively) is significantly lower than that of graphene (3500 Wm$^{-1}$K$^{-1}$) and C3N(380 Wm$^{-1}$K$^{-1}$). Moreover, it is more than the second time higher than C$_2$N (82.88 Wm$^{-1}$K$^{-1}$) at 300 K. Furthermore, the group velocities, relax time, anharmonicity, as well as the contribution from different phonon branches, were thoroughly discussed in detail. A comparison of the thermal transport characters among 2D structure for monolayer C$_4$N$_3$H, graphene, C$_2$N and C$_3$N has been discussed. This work highlights the essence of phonon transport in new monolayer material.

cond-mat.mtrl-sci↗