arXiv subjects

Zixuan Li

Publications and source records attributed to Zixuan Li.

At least 55 records · Page 3Linked to original sources

arXiv2026

JudgeAgent: Beyond Static Benchmarks for Knowledge-Driven and Dynamic LLM Evaluation

Current evaluation methods for large language models (LLMs) primarily rely on static benchmarks, presenting two major challenges: limited knowledge coverage and fixed difficulties that mismatch with the evaluated LLMs. These limitations lead to superficial assessments of LLM knowledge, thereby impeding the targeted model optimizations. To bridge this gap, we propose JudgeAgent, a knowledge-driven and dynamic evaluation framework for LLMs. To address the challenge of limited knowledge coverage, JudgeAgent leverages LLM agents equipped with context graphs to traverse knowledge structures systematically for question generation. Furthermore, to mitigate data contamination and difficulty mismatch, it adopts a difficulty-adaptive and multi-turn interview mechanism. Thereby, JudgeAgent can achieve comprehensive evaluations and facilitate more effective improvement of LLMs. Empirical results demonstrate that JudgeAgent enables more comprehensive evaluations and facilitates effective model iterations, highlighting the potential of this knowledge-driven and dynamic evaluation paradigm. The source code is available on https://github.com/DataArcTech/JudgeAgent.

cs.CL↗

arXiv2026

Temporal Knowledge Graph Question Answering: A Survey

Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research.

cs.CL↗

arXiv2026

LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction

Large language models (LLMs) have made significant progress in Emotional Intelligence (EI) and long-context modeling. However, existing benchmarks often overlook the fact that emotional information processing unfolds as a continuous long-context process. To address the absence of multidimensional EI evaluation in long-context inference and explore model performance under more challenging conditions, we present LongEmotion, a benchmark that encompasses a diverse suite of tasks targeting the assessment of models' capabilities in Emotion Recognition, Knowledge Application, and Empathetic Generation, with an average context length of 15,341 tokens. To enhance performance under realistic constraints, we introduce the Collaborative Emotional Modeling (CoEM) framework, which integrates Retrieval-Augmented Generation (RAG) and multi-agent collaboration to improve models' EI in long-context scenarios. We conduct a detailed analysis of various models in long-context settings, investigating how reasoning mode activation, RAG-based retrieval strategies, and context-length adaptability influence their EI performance. Our project page is: https://longemotion.github.io/

cs.CL↗

arXiv2026

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning

Recent advances in natural language processing, primarily propelled by Large Language Models (LLMs), have showcased their remarkable capabilities grounded in in-context learning. A promising avenue for guiding LLMs in intricate reasoning tasks involves the utilization of intermediate reasoning steps within the Chain-of-Thought (CoT) paradigm. Nevertheless, the central challenge lies in the effective selection of exemplars for facilitating in-context learning. In this study, we introduce a framework that leverages Dual Queries and Low-rank approximation Re-ranking (DQ-LoRe) to automatically select exemplars for in-context learning. Dual Queries first query LLM to obtain LLM-generated knowledge such as CoT, then query the retriever to obtain the final exemplars via both question and the knowledge. Moreover, for the second query, LoRe employs dimensionality reduction techniques to refine exemplar selection, ensuring close alignment with the input question's knowledge. Through extensive experiments, we demonstrate that DQ-LoRe significantly outperforms prior state-of-the-art methods in the automatic selection of exemplars for GPT-4, enhancing performance from 92.5% to 94.2%. Our comprehensive analysis further reveals that DQ-LoRe consistently outperforms retrieval-based approaches in terms of both performance and adaptability, especially in scenarios characterized by distribution shifts. DQ-LoRe pushes the boundary of in-context learning and opens up new avenues for addressing complex reasoning challenges. Our code is released at https://github.com/menik1126/DQ-LoRe

cs.CL↗

arXiv2026

Ramp Josephson junctions of Al/Ti/Sr2RuO4: Observation of single-domain quantum oscillations and the detection of chiral edge current

The determination of how the phase of the superconducting order parameter in a superconductor varies with the spatial direction, which can be done only through the Josephson-effect-based phase-sensitive measurements, is crucial for the establishment of the precise pairing symmetry of the superconductor. So far, such measurements have been done on high-Tc cuprate superconductors but only at a couple of directions for Sr2RuO4 because of the difficulty in preparing Josephson junctions between Sr2RuO4 and an s-wave superconductor with a chosen mutual orientation. Another long-standing issue in Sr2RuO4, which was shown previously to feature a spontaneously broken time-reversal symmetry by muon spin rotation and other measurements, is that the expected presence of chiral surface currents, domains, and domain walls is yet to be explicitly shown experimentally. To address these issues, we have long sought the preparation of high-quality Josephson junctions between Sr2RuO4 and a conventional s-wave with a controllable orientation relative to symmetry axes in Sr2RuO4. We report in this article the successful fabrication of ramp Josephson junctions of Al/Ti/Sr2RuO4 on thin single crystals of Sr2RuO4 obtained by mechanical exfoliation. These junctions were found to show high-quality quantum oscillations consistent with a single-domain Josephson coupling. The normal junction resistance was found to depend extremely sensitively on the supercurrent flowing in the Sr2RuO4 crystal on which the Josephson junction was made. This finding was used in the present work to provide an estimate of the size of the chiral surface current, which is shown to agree with its upper bound established previously.

cond-mat.supr-con↗

arXiv2025

Graph-theoretical search for integrable multistate Landau-Zener models

The search for exactly solvable models is an evergreen topic in theoretical physics. In the context of multistate Landau-Zener models -- $N$-state quantum systems with linearly time-dependent Hamiltonians -- the theory of integrability provides a framework for identifying new solvable cases. In particular, it was proved that the integrability of a specific class known as the multitime Landau-Zener (MTLZ) models guarantees their exact solvability. A key finding was that an $N$-state MTLZ model can be represented by data defined on an $N$-vertex graph. While known host graphs for MTLZ models include hypercubes, fans, and their Cartesian products, no other families have been discovered, leading to the conjecture that these are the only possibilities. In this work, we conduct a systematic graph-theoretical search for integrable models within the MTLZ class. By first identifying minimal structures that a graph must contain to host an MTLZ model, we formulate an efficient algorithm to systematically search for candidate graphs for MTLZ models. Implementing this algorithm using computational software, we enumerate all candidate graphs with up to $N = 13$ vertices and perform an in-depth analysis of those with $N \le 11$. Our results corroborate the aforementioned conjecture for graphs up to $11$ vertices. For even larger graphs, we propose a specific family, termed descendants of ``$(0,2)$-graphs'', as promising candidates that may violate the conjecture above. Our work can serve as a guideline to identify new exactly solvable multistate Landau-Zener models in the future.

quant-ph↗

arXiv2025

KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA

Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB). Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Models (LLMs) iteratively decompose a question, generate its corresponding logical queries, and interact with the KB to derive the answer. However, these methods typically fine-tune LLMs on reasoning trajectories synthesized via process supervision, which offers weak incentives for exploration and thus fails to strengthen the agentic reasoning ability. In this paper, we propose KnowCoder-A1, an LLM that can autonomously perform agentic reasoning on KBs to obtain answers. To incentivize autonomous exploration, KnowCoder-A1 trains the LLM under outcome-only supervision via a multi-stage curriculum reinforcement learning with an easy-to-hard curriculum. To establish foundational agentic capabilities, KnowCoder-A1 first fine-tunes the LLM on a small set of high-quality trajectories obtained through outcome-based rejection sampling. Then, to alleviate the reward sparsity inherent in outcome-only supervision, it applies multi-stage curriculum RL with reward schedules that progress from easy to hard. Trained with outcome-only supervision, KnowCoder-A1 exhibits powerful reasoning behaviors and consistently outperforms prior approaches across three mainstream datasets. Notably, on the zero-shot subset of GrailQA, KnowCoder-A1 achieves up to an 11.1% relative improvement while using only one-twelfth of the training data, demonstrating strong agentic reasoning capabilities.

cs.AI↗

arXiv2025

Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection

Stickers are widely used in online communication to convey emotions and implicit intentions. The Sticker Response Selection (SRS) task aims to select the most contextually appropriate sticker based on the dialogue. However, existing methods typically rely on semantic matching and model emotional and intentional cues separately, which can lead to mismatches when emotions and intentions are misaligned. To address this issue, we propose Emotion and Intention Guided Multi-Modal Learning (EIGML). This framework is the first to jointly model emotion and intention, effectively reducing the bias caused by isolated modeling and significantly improving selection accuracy. Specifically, we introduce Dual-Level Contrastive Framework to perform both intra-modality and inter-modality alignment, ensuring consistent representation of emotional and intentional features within and across modalities. In addition, we design an Intention-Emotion Guided Multi-Modal Fusion module that integrates emotional and intentional information progressively through three components: Emotion-Guided Intention Knowledge Selection, Intention-Emotion Guided Attention Fusion, and Similarity-Adjusted Matching Mechanism. This design injects rich, effective information into the model and enables a deeper understanding of the dialogue, ultimately enhancing sticker selection performance. Experimental results on two public SRS datasets show that EIGML consistently outperforms state-of-the-art baselines, achieving higher accuracy and a better understanding of emotional and intentional features. Code is provided in the supplementary materials.

cs.LG↗

arXiv2025

Two-stage Audio-Visual Target Speaker Extraction System for Real-Time Processing On Edge Device

Audio-Visual Target Speaker Extraction (AVTSE) aims to isolate a target speaker's voice in a multi-speaker environment with visual cues as auxiliary. Most of the existing AVTSE methods encode visual and audio features simultaneously, resulting in extremely high computational complexity and making it impractical for real-time processing on edge devices. To tackle this issue, we proposed a two-stage ultra-compact AVTSE system. Specifically, in the first stage, a compact network is employed for voice activity detection (VAD) using visual information. In the second stage, the VAD results are combined with audio inputs to isolate the target speaker's voice. Experiments show that the proposed system effectively suppresses background noise and interfering voices while spending little computational resources.

cs.SD↗

arXiv2025

MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts

LLMs hold great promise for healthcare applications, but the rapid evolution of medical knowledge and errors in training data often cause them to generate outdated or inaccurate information, limiting their applicability in high-stakes clinical practice. Model editing has emerged as a potential remedy without full retraining. While parameter-based editing often compromises locality and is thus ill-suited for the medical domain, retrieval-based editing offers a more viable alternative. However, it still faces two critical challenges: (1) representation overlap within the medical knowledge space often causes inaccurate retrieval and reduces editing accuracy; (2) existing methods are restricted to single-sample edits, while batch-editing remains largely unexplored despite its importance for real-world medical applications. To address these challenges, we first construct MedVersa, an enhanced benchmark with broader coverage of medical subjects, designed to evaluate both single and batch edits under strict locality constraints. We then propose MedREK, a retrieval-based editing framework that integrates a shared query-key module for precise matching with an attention-based prompt encoder for informative guidance. Experimental results on various medical benchmarks demonstrate that our MedREK achieves superior performance across different core metrics and provides the first validated solution for batch-editing in medical LLMs. Our code and dataset are available at https://github.com/mylittleriver/MedREK.

cs.CL↗

arXiv2025

Probing Hidden Symmetry and Altermagnetism with Sub-Picometer Sensitivity via Nonlinear Transport

X-ray and neutron diffraction are foundational tools for determining crystal structures, but their resolution limits can lead to misassignments, especially in materials with subtle distortions or competing phases. Here, we demonstrate the use of nonlinear transport as a complementary approach to uncover hidden crystal symmetries, using the strongly correlated Ca$_3$Ru$_2$O$_7$ as a case study. Below 48 K (T$_S$), where the magnetic moments of the antiferromagnetic phase reorient from the a- to the b-axis, leading to a pseudogap opening, our measurements, with support of DFT, reveal a previously overlooked lower-symmetry phase. This is manifested by the emergence of longitudinal nonlinear resistance (NLR) along the b-axis below T$_S$, providing direct evidence of combined translational and time-reversal symmetry breaking. This response also suggests a transformation from a conventional antiferromagnet into an altermagnet. The lower-symmetry phase arises from a subtle lattice distortion (~0.1 pm) associated with the magnetic transition at T$_S$, below the detection limit of conventional diffraction. Moreover, this NLR below T$_S$ is accompanied by a nonlinear Hall effect, both of which are enhanced by the large quantum metric associated with Weyl chains near the Fermi surface. Our findings demonstrate nonlinear transport as a sensitive probe of hidden symmetry breaking and altermagnetism, complementing and extending beyond the reach of traditional diffraction and spectroscopic techniques.

cond-mat.str-el↗

arXiv2025

SKYLENAGE Technical Report: Mathematical Reasoning and Contest-Innovation Benchmarks for Multi-Level Math Evaluation

Large language models (LLMs) now perform strongly on many public math suites, yet frontier separation within mathematics increasingly suffers from ceiling effects. We present two complementary benchmarks: SKYLENAGE-ReasoningMATH, a 100-item, structure-aware diagnostic set with per-item metadata on length, numeric density, and symbolic complexity; and SKYLENAGE-MATH, a 150-item contest-style suite spanning four stages from high school to doctoral under a seven-subject taxonomy. We evaluate fifteen contemporary LLM variants under a single setup and analyze subject x model and grade x model performance. On the contest suite, the strongest model reaches 44% while the runner-up reaches 37%; accuracy declines from high school to doctoral, and top systems exhibit a doctoral-to-high-school retention near 79%. On the reasoning set, the best model attains 81% overall, and hardest-slice results reveal clear robustness gaps between leaders and the mid-tier. In summary, we release SKYLENAGE-ReasoningMATH and report aggregate results for SKYLENAGE-MATH; together, SKYLENAGE provides a hard, reasoning-centered and broadly covering math benchmark with calibrated difficulty and rich metadata, serving as a reference benchmark for future evaluations of mathematical reasoning.

cs.CL↗

arXiv2025

Shift-Left Techniques in Electronic Design Automation: A Survey

The chip design process involves numerous steps, beginning with defining product requirements and progressing through architectural planning, system-level design, and the physical layout of individual circuit blocks. As the enablers of large-scale chip development, Electronic Design Automation (EDA) tools play a vital role in helping designers achieve high-quality results. The Shift-Left methodology introduces a pathway toward creating digital twins and fusing multiple design steps, thereby transitioning traditionally sequential, physically-aware processes into virtual design environments. This shift allows designers to establish stronger correlations earlier and optimize designs more effectively. However, challenges remain, especially in accurately replicating downstream behaviors and determining the right scope and timing for adoption. These challenges, in turn, have revealed new opportunities for EDA vendors, physical designers, and logic designers alike. As the industry advances toward intelligent EDA tools and techniques, it is timely to reflect on Shift-Left progress made and the challenges that remain. The rise of AI techniques and the momentum of open-source design flows have significantly strengthened prediction and modeling capabilities, making data-driven methods increasingly relevant to the EDA community. This, in turn, enhances the ''Shift-Left'' features embedded in current tools. In this paper, we present a comprehensive survey of existing and emerging paradigms in Shift-Left research within EDA and the broader design ecosystem. Our goal is to provide a unique perspective on the state of the field and its future directions. Relevant papers mentioned are organized in https://github.com/iCAS-SJTU/Shift-Left-EDA-Papers.

cs.AR↗

arXiv2025

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation methods and (2) oversimplified simulation environments. We present RoboTwin 2.0, a scalable framework for automated, large-scale generation of diverse and realistic data, together with unified evaluation protocols for dual-arm manipulation. At its core is RoboTwin-OD, an object library of 731 instances across 147 categories with semantic and manipulation-relevant annotations. Building on this, we design an expert data synthesis pipeline that leverages multimodal language models (MLLMs) and simulation-in-the-loop refinement to automatically generate task-level execution code. To improve sim-to-real transfer, RoboTwin 2.0 applies structured domain randomization along five axes: clutter, lighting, background, tabletop height, and language, enhancing data diversity and policy robustness. The framework is instantiated across 50 dual-arm tasks and five robot embodiments. Empirically, it yields a 10.9% gain in code generation success rate. For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain. These results highlight the effectiveness of RoboTwin 2.0 in strengthening sim-to-real transfer and robustness to environmental variations. We release the data generator, benchmark, dataset, and code to support scalable research in robust bimanual manipulation. Project Page: https://robotwin-platform.github.io/, Code: https://github.com/robotwin-Platform/robotwin/.

cs.RO↗

arXiv2025

Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop

Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/.

cs.RO↗

arXiv2025

"How can we learn and use AI at the same time?": Participatory Design of GenAI with High School Students

As generative AI (GenAI) emerges as a transformative force, clear understanding of high school students' perspectives is essential for GenAI's meaningful integration in high school environments. In this work, we draw insights from a participatory design workshop where we engaged 17 high school students -- a group rarely involved in prior research in this area -- through the design of novel GenAI tools and school policies addressing their key concerns. Students identified challenges and developed solutions outlining their ideal features in GenAI tools, appropriate school use, and regulations. These centered around the problem spaces of combating bias & misinformation, tackling crime & plagiarism, preventing over-reliance on AI, and handling false accusations of academic dishonesty. Building on our participants' underrepresented perspectives, we propose new guidelines targeted at educational technology designers for development of GenAI technologies in high schools. We also argue for further incorporation of student voices in development of AI policies in their schools.

cs.HC↗

arXiv2025

AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents

Current research in LLM-based simulation systems lacks comprehensive solutions for modeling real-world court proceedings, while existing legal language models struggle with dynamic courtroom interactions. We present AgentCourt, a comprehensive legal simulation framework that addresses these challenges through adversarial evolution of LLM-based agents. Our AgentCourt introduces a new adversarial evolutionary approach for agents called AdvEvol, which performs dynamic knowledge learning and evolution through structured adversarial interactions in a simulated courtroom program, breaking the limitations of the traditional reliance on static knowledge bases or manual annotations. By simulating 1,000 civil cases, we construct an evolving knowledge base that enhances the agents' legal reasoning abilities. The evolved lawyer agents demonstrated outstanding performance on our newly introduced CourtBench benchmark, achieving a 12.1% improvement in performance compared to the original lawyer agents. Evaluations by professional lawyers confirm the effectiveness of our approach across three critical dimensions: cognitive agility, professional knowledge, and logical rigor. Beyond outperforming specialized legal models in interactive reasoning tasks, our findings emphasize the importance of adversarial learning in legal AI and suggest promising directions for extending simulation-based legal reasoning to broader judicial and regulatory contexts. The project's code is available at: https://github.com/relic-yuexi/AgentCourt

cs.CL↗

arXiv2025

KnowCoder-V2: Deep Knowledge Analysis

Deep knowledge analysis tasks always involve the systematic extraction and association of knowledge from large volumes of data, followed by logical reasoning to discover insights. However, to solve such complex tasks, existing deep research frameworks face three major challenges: 1) They lack systematic organization and management of knowledge; 2) They operate purely online, making it inefficient for tasks that rely on shared and large-scale knowledge; 3) They cannot perform complex knowledge computation, limiting their abilities to produce insightful analytical results. Motivated by these, in this paper, we propose a \textbf{K}nowledgeable \textbf{D}eep \textbf{R}esearch (\textbf{KDR}) framework that empowers deep research with deep knowledge analysis capability. Specifically, it introduces an independent knowledge organization phase to preprocess large-scale, domain-relevant data into systematic knowledge offline. Based on this knowledge, it extends deep research with an additional kind of reasoning steps that perform complex knowledge computation in an online manner. To enhance the abilities of LLMs to solve knowledge analysis tasks in the above framework, we further introduce \textbf{\KCII}, an LLM that bridges knowledge organization and reasoning via unified code generation. For knowledge organization, it generates instantiation code for predefined classes, transforming data into knowledge objects. For knowledge computation, it generates analysis code and executes on the above knowledge objects to obtain deep analysis results. Experimental results on more than thirty datasets across six knowledge analysis tasks demonstrate the effectiveness of \KCII. Moreover, when integrated into the KDR framework, \KCII can generate high-quality reports with insightful analytical results compared to the mainstream deep research framework.

cs.AI↗