arXiv subjects

Jingyi Chen

Publications and source records attributed to Jingyi Chen.

At least 19 recordsLinked to original sources

arXiv2026

Bridging Language and Physics: Automated Design of Continuum Robots with Large Language Models

Large language models (LLMs) have recently emerged as a promising tool for automating robot design from high-level specifications, yet they remain ineffective for robots operating under complex physical interactions. This limitation stems from the gap between language-based reasoning and the physical consequences of embodiment, often resulting in designs with low physical validity. In this work, we propose a multi-layered framework, AID-SR, that establishes a closed loop by translating simulator-observed physical states into structured feedback for the LLM designer. Combined with semantic critique, human feedback, and iterative refinement, the framework promotes the generation of physically feasible and functionally meaningful robot designs. We evaluate our approach on tendon-driven continuum robots across a benchmark of 14 tasks spanning reaching, grasping, locomotion, and manipulation. The proposed framework achieves 96.2% rate for passing the simulation feasibility check and by applying a common reinforcement learning training, 26.7% robots can successfully fulfill the corresponding task. We then fabricate three designed robots of AID-SR that successfully complete the task in real-world. These extensive experiments across simulation and real-world environments demonstrate and break the wall of utilizing the LLMs for automated design of continuum robots. The source code and experimental resources are publicly available at https://github.com/UNITES-Lab/AID-SR.

cs.RO↗

arXiv2026

A Regulatory Placebo? The Systemic Failure of Mandatory GenAI Labeling

We examine the worldwide trend of mandatory labeling of generative artificial intelligence(GenAI) as a reactive, symbolic form of legislation triggered by technological panic and institutional responses. From a technical perspective, this study demonstrates that current mandatory labeling not only creates implementation dilemmas but also risks hindering the evolutionary trajectory of AI technology. We then systematically analyze the three dominant theoretical strands of this regime, the value dilution theory, the information authenticity theory, and the proactive regulation theory, and find that they are products of regulators' cognitive limitations in understanding the logic of modern technology. Not only do such formalistic compliance requirements become a regulatory placebo, but they also obscure the genuine legal demands of the technological era. This challenges the current governance paradigm and suggests a shift from identity-label governance to content governance, with an urgent need to address the complex problems associated with GenAI.

cs.CY↗

arXiv2026

Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production

Deployed LLM safety guardrails are predominantly static: trained once and frozen at release, while new jailbreak techniques and previously un-addressed harmful categories emerge within days, leaving the defense perpetually a step behind. We present SESG (Self-Evolving Safety Guardrails), a multi-agent system running in production. SESG monitors the live traffic behind a deployed guardrail and surfaces two classes of failure: jailbreaks novel in form and harmful categories novel in content. Once a failure is confirmed, a generation agent synthesizes paired training data targeted at it; a validation agent rebalances the batch toward the direction in which the deployed model errs, so that the model's own mistakes steer its training set; and a routing agent matches the training action to the diagnosed gap and returns the next version to production. Over six rounds of live evolution (V0 to V6), a 1.7B guardrail adapts to a new threat in 16-24 hours, with about 2 hours of human effort, versus the 40-90 hours of the manual process it replaces. On six emerging threats, it outperforms static guardrails from 0.6B to 9B and an adaptive baseline while preserving its general screening competence. Since April 2026, SESG has been the primary update pipeline of Sangfor's guardrail, autonomously closing 14 of 15 new threat scenarios in two months. We release 9 test sets for the 6 new threats at https://github.com/Trams1017/SESG. Warning: This paper contains examples that may be harmful or offensive.

cs.AI↗

arXiv2026

Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports

LLM agents span command-line interfaces (e.g., Codex) and agent frameworks (e.g., LangChain), integrating backend LLMs with harness code that parses model outputs, controls agent loops, and manages context. Both the harness and LLM-generated responses jointly shape an agent's execution. This architecture gives rise to bugs that cannot be readily understood by inspecting either component alone, because some bugs occur only when a particular LLM response elicits an abnormal reaction from the agent. Prior empirical studies of agent bugs have largely attributed failures either to limited model capabilities or to harness-side defects, such as outdated APIs and configuration misalignment, without characterizing these AR bugs. We conduct the first empirical study focused on agent-reactive (AR) bugs. Through manual analysis of 255 bug reports from Codex, Gemini-CLI, LangChain, and CrewAI, we construct a two-axis taxonomy covering observable symptoms and the LLM behaviors that trigger them. Our findings show that many AR bugs manifest as silent errors without well-defined test oracles, which makes detection difficult. The stochasticity of LLM responses further complicates bug reproduction. We additionally examine fixes proposed by users and implemented by developers. This analysis exposes a mismatch: users frequently advocate harness-side guardrails, whereas developers may attribute the issue to the LLM or respond slowly to user-proposed fixes. These findings point to the need for mechanisms that help users and developers understand the root causes and resolutions of AR bugs. Overall, the study highlights challenges specific to LLM agents and motivates the design of test oracles, reproduction support, and fault-localization techniques for AR bugs.

cs.SE↗

arXiv2026

Neural Certificate Pricing for Combinatorial Optimization Problems

Combinatorial optimization (CO) problems are difficult because certifiable discrete structure induces exponential search. One needs to search over the set exponentially many candidates to certify optimality, however, the structural feasibility of a path, packing, or cover can be verified in polynomial time once supplied. In this study, we introduce Neural Certificate Pricing (NCP) that exploits this asymmetry under an unsupervised learning framework. A neural network is trained to predict certificate-level dual prices, while a structured recovery layer constructs the induced primal marginal. NCP can be viewed as amortized separation: instead of enumerating violated inequalities, it learns the residual prices through which their aggregate effect enters recovery. When the certificate-consistency condition holds, the recovered marginal is globally feasible, and a local theory shows that first-order errors in the predicted price induce only second-order loss in objective value. Across three classes of CO problems, NCP either outperforms state-of-the-art neural baselines by large margins or matches them at a fraction of the computation time, and shows stronger out-of-distribution generalization.

cs.LG↗

arXiv2026

OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing

Reinforcement learning for multimodal large language models (MLLMs) is often hindered by severe reward sparsity in complex reasoning tasks. This challenge is particularly pronounced in human-centered scenarios involving states, emotions, intentions, and behaviors, where heterogeneous multimodal signals and subjective human factors make high-quality chain-of-thought (CoT) annotations expensive and difficult to obtain. Although many multimodal datasets provide expert-annotated ground-truth labels, directly using these labels for supervised fine-tuning may encourage shortcut learning in multimodal perception and provides limited transparency for safety-critical human--AI interaction. To address these limitations, we propose OmniOPSD, a Rationale-Privileged On-Policy Self-Distillation framework that uses frontier-generated rationales as teacher-side privileged evidence rather than student imitation targets. OmniOPSD uses frontier-generated evidence-aware rationales only as training-time privileged evidence context for a local teacher. The student samples its own rollout from the original multimodal input, while the rationale-privileged teacher scores the same tokens and provides dense token-level supervision. Thus, the student learns on its own trajectory distribution without directly imitating frontier-model completions, and inference requires no labels, rationales, CoT annotations, or closed-source model access. Experiments on MER-UniBench show that OmniOPSD achieves state-of-the-art performance with an average score of $84.19$, and ablations further support the value of rationale-privileged teacher guidance.

cs.CV↗

arXiv2026

Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding

Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their capabilities in emotional reasoning remain limited. The field currently suffers from a scarcity of large-scale datasets with high-quality, descriptive emotion annotations and lacks standardized benchmarks for evaluation. Our preliminary framework, Emotion-LLaMA, pioneered instruction-tuned multimodal learning for emotion reasoning but was restricted by explicit face detectors, implicit fusion strategies, and low-quality training data with limited scale. To address these limitations, we present Emotion-LLaMAv2 and the MMEVerse benchmark, establishing an end-to-end pipeline together with a standardized evaluation setting for emotion recognition and reasoning. Emotion-LLaMAv2 introduces three key advances. First, an end-to-end multiview encoder eliminates external face detection and captures nuanced emotional cues via richer spatial and temporal multiview tokens. Second, a Conv Attention pre-fusion module is designed to enable simultaneous local and global multimodal feature interactions external to the LLM backbone. Third, a perception-to-cognition curriculum instruction tuning scheme within the LLaMA2 backbone unifies emotion recognition and free-form emotion reasoning. To support large-scale training and reproducible evaluation, MMEVerse aggregates twelve publicly available emotion datasets, including IEMOCAP, MELD, DFEW, and MAFW, into a unified multimodal instruction format. The data are re-annotated via a multi-agent pipeline involving Qwen2 Audio, Qwen2.5 VL, and GPT 4o, producing 130k training clips and 36k testing clips across 18 evaluation benchmarks.

cs.CV↗

arXiv2025

Climate change impacts on supra-permafrost soil and aquifer hydrology: broader, deeper, and longer activity

The thermal dynamics and hydrology of active layer soils and supra-permafrost aquifers determine the fate of the vast pool of carbon that they hold. In permafrost watersheds of Arctic Alaska, air temperature has warmed by up to 3.5 {\deg}C and snowfall has increased by up to ~40 mm from 1981 to 2020. How these changes impact the seasonal to decadal hydrological activity of the carbon-rich aquifers is mostly unknown. Observation-informed thermal hydrology modeling of a hillslope drained by a headwater stream (Imnavait Creek) within continuous permafrost showed profound changes from 1981 to 2020. Warmer summer temperatures deepened annual thaw depths. Steadily warming winter air temperatures, heavier snowfall, and stored energy from summer increased annual water outflow from the hillslope aquifer to the stream, warmed soil temperatures, and expanded and prolonged zero-curtain (stable at 0 {\deg}C) zones. In 2017-2018, zero-curtain areas with liquid water persisted through winter. Our findings reveal that both summer and winter warming drive year-round aquifer dynamics, creating conditions that amplify the permafrost-carbon-climate feedback.

physics.geo-ph↗

arXiv2025

Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions

Automating the adaptation of software engineering (SE) research artifacts across datasets is essential for scalability and reproducibility, yet it remains largely unstudied. Recent advances in large language model (LLM)-based multi-agent systems, such as GitHub Copilot's agent mode, promise to automate complex development workflows through coordinated reasoning, code generation, and tool interaction. This paper presents the first empirical study on how state-of-the-art multi-agent systems perform in dataset adaptation tasks. We evaluate Copilot, backed by GPT-4.1 and Claude Sonnet 4, on adapting SE research artifacts from benchmark repositories including ROCODE and LogHub2.0. Through a five-stage evaluation pipeline (file comprehension, code editing, command generation, validation, and final execution), we measure success rates, analyze failure patterns, and assess prompt-based interventions designed to enhance agent performance. Results show that current systems can identify key files and generate partial adaptations but rarely produce functionally correct implementations. Prompt-level interventions, especially providing execution error messages and reference code, substantially improve structural similarity to ground truth (from 7.25% to 67.14%), highlighting the importance of contextual and feedback-driven guidance. Our findings reveal both the promise and limitations of today's multi-agent LLM systems for dataset adaptation, and suggest concrete directions for building more reliable, self-correcting agents in future SE research.

cs.SE↗

arXiv2025

Geometric Bound for Trade-off Relation in Quantum Tricycle

We establish a finite-time quantum tricycle driven by an external field and investigate its thermodynamic performance in the slow-driving regime. By developing a perturbative expansion of heat with respect to operation time, we capture the dynamics of heat exchange processes beyond the quasistatic limit. Within a geometric framework, we derive fundamental bounds on trade-offs between the cooling rate, coefficient of performance, and dissipation, governed by the thermodynamic length and trajectory geometry in control space. Our findings unveil intrinsic limits to the performance of quantum thermal machines and highlight the role of geometry in shaping finite-time thermodynamics. This work advances the fundamental understanding of quantum thermodynamic processes and offers guiding principles for the design of next-generation quantum technologies.

quant-ph↗

arXiv2025

Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance

Understanding emotion from speech requires sensitivity to both lexical and acoustic cues. However, it remains unclear whether large audio language models (LALMs) genuinely process acoustic information or rely primarily on lexical content. We present LISTEN (Lexical vs. Acoustic Speech Test for Emotion in Narratives), a controlled benchmark designed to disentangle lexical reliance from acoustic sensitivity in emotion understanding. Across evaluations of six state-of-the-art LALMs, we observe a consistent lexical dominance. Models predict "neutral" when lexical cues are neutral or absent, show limited gains under cue alignment, and fail to classify distinct emotions under cue conflict. In paralinguistic settings, performance approaches chance. These results indicate that current LALMs largely "transcribe" rather than "listen," relying heavily on lexical semantics while underutilizing acoustic cues. LISTEN offers a principled framework for assessing emotion understanding in multimodal models.

cs.CL↗

arXiv2025

Can Emulating Semantic Translation Help LLMs with Code Translation? A Study Based on Pseudocode

Although large language models (LLMs) show promising potential in code translation, they still struggle to generate accurate translations using the commonly adopted direct code-to-code translation approach, which converts an original program into the target programming language (PL) in a single step. Inspired by the success of incorporating intermediate steps to guide LLMs in resolving challenging tasks, in this study, we explore pseudocode-based code translation. This approach emulates human semantic translation by first interpreting the original program's intent and logic into pseudocode and then implementing it in the target PL. To understand the effectiveness of this underexplored approach, we present a systematic empirical study on pseudocode-based code translation, aiming to investigate its helpfulness in enhancing the direct translation approach, illuminate its effective usage, and identify its limitations. By comparing direct and pseudocode-based translation on 9,690 translation tasks across six PLs with five popular LLMs, we found that pseudocode-based translation can effectively complement direct translation, particularly when translating from flexible to rigid PLs and handling a low-training-resource PL. Based on the findings, we suggest combining the translation results of both approaches for test-based selection to leverage their complementary strengths. We also reveal the advantages of pseudocode-based translation in decoupling the code understanding and generation burden on complicated programs and mitigating distractions from PL-specific implementations in original programs, as well as its limitations due to incorrect, incomplete, or ambiguous pseudocode. Our study sheds light on the effective use of pseudocode-based translation and provides evidence to help enhance LLMs in code translation.

cs.SE↗

arXiv2025

On Hamiltonian stationarity of twisted Lagrangian tori in ${\mathbb{C}}^2$

Chekanov's exotic tori have been playing an important role in symplectic geometry as they are the only known examples of Lagrangian tori in ${\mathbb{C}}^2$ that are not Hamiltonian isotopic to a product torus. In this paper, we explore the differential geometry of a wider range of tori constructed by twisting simple closed planar curves, which include both certain product tori and Chekanov's exotic tori. In particular, we investigate the minimality of area of such twisted tori under Hamiltonian deformations and show that the only minimal twisted tori are the product ones. This tells us that Chekanov's exotic tori are not area minimal in their Hamiltonian isotopy classes.

math.DG↗

arXiv2025

Equinox: Holistic Fair Scheduling in Serving Large Language Models

We address the limitations of current LLM serving with a dual-counter framework separating user and operator perspectives. The User Fairness Counter measures quality of service via weighted tokens and latency; the Resource Fairness Counter measures operational efficiency through throughput and GPU utilization. Since these metrics are only available post-execution, creating a scheduling paradox, we introduce a deterministic Mixture of Prediction Experts (MoPE) framework to predict user-perceived latency, output tokens, throughput, and GPU utilization. These predictions enable calculation of a unified Holistic Fairness score that balances both counters through tunable parameters for proactive fairness-aware scheduling. We implement this in Equinox, an open-source system with other optimizations like adaptive batching, and stall-free scheduling. Evaluations on production traces (ShareGPT, LMSYS) and synthetic workloads demonstrate Equinox achieves up to $1.3\times$ higher throughput, 60\% lower time-to-first-token latency, and 13\% higher fairness versus VTC while maintaining 94\% GPU utilization, proving fairness under bounded discrepancy across heterogeneous platforms.

cs.DC↗

arXiv2025

Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback

Diffusion models produce high-fidelity speech but are inefficient for real-time use due to long denoising steps and challenges in modeling intonation and rhythm. To improve this, we propose Diffusion Loss-Guided Policy Optimization (DLPO), an RLHF framework for TTS diffusion models. DLPO integrates the original training loss into the reward function, preserving generative capabilities while reducing inefficiencies. Using naturalness scores as feedback, DLPO aligns reward optimization with the diffusion model's structure, improving speech quality. We evaluate DLPO on WaveGrad 2, a non-autoregressive diffusion-based TTS model. Results show significant improvements in objective metrics (UTMOS 3.65, NISQA 4.02) and subjective evaluations, with DLPO audio preferred 67\% of the time. These findings demonstrate DLPO's potential for efficient, high-quality diffusion TTS in real-time, resource-limited settings.

cs.SD↗

arXiv2025

Unsupervised Learning for the Elementary Shortest Path Problem

The Elementary Shortest-Path Problem(ESPP) seeks a minimum cost path from s to t that visits each vertex at most once. The presence of negative-cost cycles renders the problem NP-hard. We present a probabilistic method for finding near-optimal ESPP, enabled by an unsupervised graph neural network that jointly learns node value estimates and edge-selection probabilities via a surrogate loss function. The loss provides a high probability certificate of finding near-optimal ESPP solutions by simultaneously reducing negative-cost cycles and embedding the desired algorithmic alignment. At inference time, a decoding algorithm transforms the learned edge probabilities into an elementary path. Experiments on graphs of up to 100 nodes show that the proposed method surpasses both unsupervised baselines and classical heuristics, while exhibiting high performance in cross-size and cross-topology generalization on unseen synthetic graphs.

cs.LG↗

arXiv2025

Holomorphic disks with boundary on compact Lagrangian surface

Let $L$ be a compact oriented Lagrangian surface in a K\"ahler surface endowed with a complete Riemannian metric (compatible with the symplectic structure and the complex structure) with bounded sectional curvatures and a positive lower bound on injectivity radius. We show that for every nontrivial class $[\gamma]$ of the fundamental group $\pi_1(L)$ such that $\gamma$ bounds a topological disk in $M$, there exists a holomorphic disk whose boundary belongs to $L$ and is freely homotopic to $\gamma$ on $L$. This answers a question of Bennequin on existence of $J$-holomorphic disks. Nonexistence of exact Lagrangian embeddings of certain surfaces is established in such K\"ahler surface if the fundamental form is exact. In the almost K\"ahler setting, especially, the cotangent bundles of compact manifolds, results on nonexistence of $J$-holomorphic disks and existence of minimizers of the partial energies in the sense of A. Lichnerowicz are obtained.

math.DG↗

arXiv2025

When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?

Retrieval-augmented generation (RAG) has increasingly shown its power in extending large language models' (LLMs') capability beyond their pre-trained knowledge. Existing works have shown that RAG can help with software development tasks such as code generation, code update, and test generation. Yet, the effectiveness of adapting LLMs to fast-evolving or less common API libraries using RAG remains unknown. To bridge this gap, we take an initial step to study this unexplored yet practical setting - when developers code with a less common library, they often refer to its API documentation; likewise, when LLMs are allowed to look up API documentation via RAG, to what extent can LLMs be advanced? To mimic such a setting, we select four less common open-source Python libraries with a total of 1017 eligible APIs. We study the factors that affect the effectiveness of using the documentation of less common API libraries as additional knowledge for retrieval and generation. Our intensive study yields interesting findings: (1) RAG helps improve LLMs' performance by 83%-220%. (2) Example code contributes the most to advance LLMs, instead of the descriptive texts and parameter lists in the API documentation. (3) LLMs could sometimes tolerate mild noises (typos in description or incorrect parameters) by referencing their pre-trained knowledge or document context. Finally, we suggest that developers pay more attention to the quality and diversity of the code examples in the API documentation. The study sheds light on future low-code software development workflows.

cs.SE↗