arXiv subjects

Chen Jiang

Publications and source records attributed to Chen Jiang.

At least 19 recordsLinked to original sources

arXiv2026

On Nonsmooth and Relatively Weakly Convex Minimization

Composite optimization plays a central role in modern machine learning and signal processing, as it offers a natural balance between data fidelity and structural properties. In this paper, we study composite optimization in the setting where both components are nonsmooth and nonconvex. We start with a deterministic Bregman proximal subgradient method that converges under subgradient upper-bound conditions. This approach relaxes the standard requirement on the convexity of the regularization term, thus accommodating a broader range of applications. To extend this to the stochastic regime, we develop a model-based minimization method under a relative Lipschitz condition and establish a convergence rate of $\mathcal{O}(\varepsilon^{-4})$. We also extend the framework with convergence guarantees to the setting where the distance generating function and its gradient are accessible only through a stochastic oracle.

math.OC↗

arXiv2026

MobileMem: Learning from a Year of Mobile Experiences

The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval toward experiential intelligence for continuous personal learning.

cs.AI↗

arXiv2026

Size Effects in the Strong-Field Ionization and Dissociation Dynamics of (H$_2$O)$_n$ (n=1-4)

The size-dependent strong-field ionization and dissociation dynamics of (H$_2$O)$_n$ (n=1-4) are investigated using real-time time-dependent density functional theory (RT-TDDFT) coupled to Ehrenfest molecular dynamics under a common few-cycle near-infrared laser pulse. It is found that the net ionization per monomer varies only weakly on cluster size, whereas the protonic and oxygen response is changed much more strongly once the cluster size grows beyond the dimer. In particular, H-ejection activity is observed to rise sharply from the dimer to the trimer/tetramer regime, while stable H-transfer is essentially absent in the dimer under the present criterion but becomes substantial in the trimer and is further amplified in the tetramer. Through timing analyses, it is shown that the dimer exhibits a weak and temporally broad response, whereas the larger clusters display a much stronger early-time protonic response concentrated within and immediately after the laser pulse window. By endpoint oxygen statistics, a systematic increase in dissociation propensity with cluster size is likewise shown. For a clean subset of direct two-body dimer breakup trajectories, the asymptotic kinetic energy release is estimated to be 4.47 $\pm$ 1.03 eV, in reasonably good agreement with the experimental value for the unprotonated two-body Coulomb-explosion channel. Overall, it is shown by the results that increasing water-cluster size primarily reshapes the strong-field response through proton-mediated and topology-level nuclear dynamics rather than through a large change in net ionization alone.

physics.chem-ph↗

arXiv2026

KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering

Recent research has explored the integration of knowledge graphs (KGs) with large language models (LLMs) to enhance their performance on downstream knowledge-intensive tasks, particularly knowledge graph question answering (KGQA). Existing approaches primarily combine LLMs with KGs through retrieval-augmented generation (RAG)-based, agent-based, and SPARQL-based methods. Although these methods have achieved notable success, they still suffer from several limitations, including structural information loss, unfaithful reasoning, and limited flexibility and generalization. To address these challenges, this paper proposes KG2Code, a novel approach that transforms knowledge graphs into a code-based representation, preserving structural semantics while naturally aligning with the code-aware pretraining of modern LLMs. Based on KG2Code, KG2Code-QA is further introduced as a KGQA framework that formulates KGQA as a code generation task. This formulation enables the generation of verifiable reasoning traces and executable code, thereby substantially mitigating the impact of hallucinations. In addition, an automated pipeline is developed to construct a large-scale, high-quality code corpus for effectively training open-source LLMs on KG2Code-QA. After training, LLMs are able to perform KGQA in zero-shot scenarios. Extensive experiments demonstrate that the proposed approach significantly outperforms existing KG-enhanced LLM methods for KGQA, while exhibiting strong generalization to unseen KGs. The code and data are available at Github.

cs.AI↗

arXiv2026

TokenPilot: Cache-Efficient Context Management for LLM Agents

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightRSI at https://github.com/zjunlp/RSI.

cs.CL↗

arXiv2026

Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents

Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume that task-appropriate tools are reliable within their intended scope. This assumption is fragile in real clinical settings, where even relevant tools may fail on challenging instances and lead to unsafe downstream decisions. To address this issue, we study medical tool use under imperfect-tool settings to correct failure instances missed by individual tools. Instance-dependent failure patterns create a gap between the best fixed single tool and an ideal instance-wise selector, which we refer to as the Single-Oracle risk gap. The core challenge is that conventional task-level tool selection cannot realize this gap, as it is inherently bounded by the performance of the best single tool. Motivated by this observation, we therefore account for instance-level heterogeneity and formulate tool use as an instance-level selection problem. Particularly, we propose a GRPO-based reinforcement learning framework with rewards for probabilistic risk minimization and disagreement-aware synergy learning, which promotes instance-level correction of erroneous tool consensus. Furthermore, an entropy-guided sampling strategy is adopted to upweight high-disagreement instances, which provide stronger signals for learning instance-specific tool synergy. These two components complement each other in mitigating instance-level heterogeneity and improving tool synergy. Experiments on two tasks and seven medical benchmarks show that our method consistently achieves robust and stable improvements over a broad range of baselines, highlighting the importance of synergy-aware tool use for reliable medical agentic systems.

cs.AI↗

arXiv2026

Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging

Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or masked reconstruction. They often do not adequately capitalize on a key characteristic of physiological features: anatomical structures maintain consistent spatial relationships across individuals (instances), such as the thalamus being medial to the basal ganglia, regardless of variations in brain size, shape, or pathology. We propose leveraging this cross-instance topological consistency as a supervisory signal. The challenge arises from the inherent variability in medical imaging, which can differ significantly across instances and modalities. To tackle this, we focus on two alignment regimes. (i) Intra-instance: with pixel-level correspondences available, a cross-modal triplet objective explicitly preserves local neighborhood topology. (ii) Inter-instance: without such supervision, we derive pseudo-correspondences to control partial neighborhood alignment and prevent topology collapse across modalities. We validate our approach across 7 downstream multi-modal tasks, achieving average improvements of 1.1% and 5.94% in segmentation and classification tasks, respectively, and demonstrating significantly better robustness when modalities are missing at test time.

cs.CV↗

arXiv2026

A lower bound for polynomial volume growth of automorphisms of zero entropy

Let $X$ be a normal projective variety of dimension $d$, and let $f$ be a zero-entropy automorphism of $X$. Denote by $k$ the first-degree growth rate of $f$, so that $\deg_1(f^n) \asymp n^{k}$. We prove the sharp lower bound for the polynomial volume growth $\mathrm{plov}(f)$ of $f$: \[ \mathrm{plov}(f) \ge d+\frac{k(k+2)}{4}, \] equivalently giving a sharp lower bound on the Gelfand--Kirillov dimension of the associated twisted homogeneous coordinate ring. This improves previous lower bounds of Keeler and of Lin--Oguiso--Zhang. In the proof, we introduce the notion of dynamical intersection polynomials and give a new characterization of $\mathrm{plov}(f)$ in terms of non-vanishing of intersection numbers. We also establish a gap principle for polynomial volume growth: for every fixed dimension $d\ge 4$, either $\mathrm{plov}(f)=d^2$, or $\mathrm{plov}(f)\le d(d-2) + 2\lfloor d/4 \rfloor$. This reveals a new rigidity phenomenon for zero-entropy automorphisms. As an application, in dimension $4$ we determine all possible values of $\mathrm{plov}$, thereby extending the results of Artin--Van den Bergh for surfaces and Lin--Oguiso--Zhang for threefolds.

math.AG↗

arXiv2026

The PLATO Science Calibration and Validation Plan: Targets for the First Long-pointing Field

In order to meet the science goals of the PLATO space mission, an extensive science calibration and validation plan has been designed. This paper describes this plan, as well as the methodology adopted to select the science calibration and validation stars that have entered its input catalogue. This is the so-called {\tt scvPIC}, which is part of the general PLATO Input Catalogue (PIC) for the first selected long pointing field in the Southern Hemisphere known as LOPS2. While many of PLATO's science requirements needed dedicated stars as calibrators as discussed here, its most stringent requirement is the delivery of the age of the host stars of exoplanetary systems with an accuracy better than 10\% for a G0V star of {\it V} = 10 mag, i.e. a nearby Sun-like star. This is presently not within reach for large populations of dwarfs and subgiants in the Milky Way as it requires the models of their stellar interiors to be improved. We discuss how this ambitious age requirement led to the selection of tens of thousands of red giants, and of thousands of main-sequence early F-type gravity-mode pulsators in order to deduce their internal rotation profile across stellar evolution. This asteroseismic observable will then be imported as key information into improved models of dwarfs and subgiants in the Milky Way as optimal modelling tools for ever better age-dating of the exoplanet hosts as the PLATO mission moves along. Additional calibrators and validators included in the {\tt scvPIC} are a few thousands of binaries, a few hundreds of legacy and benchmark stars, a few hundred photometrically stable stars, and six transiting brown dwarfs.

astro-ph.SR↗

arXiv2026

PLATO input catalogs for technical calibration and fine guidance

A few weeks after launch, the PLATO spacecraft is expected to start its payload commissioning, which will be completed within the first three months of the mission. This phase includes the in-orbit verification, calibration, and configuration of the instrument prior to nominal science operations. During this mission-critical period, and again later during regular spacecraft rotations and re-pointings, a set of reference stars is required to complete various calibration steps. This set, referred to as the calibration PLATO Input Catalog (cPIC), is part of the PIC. The cPIC comprises various stellar samples, each serving a dedicated technical calibration purpose, and it contains 71671 unique stellar targets across PLATO's entire field of view (FoV). Once the spacecraft commences science observations, the on-board Fine Guidance System (FGS) will rely on a small set of guide stars. These stars must be particularly bright and will be observed with the two fast cameras, which cover only a smaller central region of PLATO's FoV. This target list, referred to as the fine-guidance PLATO Input Catalog (fgPIC), contains 2640 unique targets, of which about 30 are used by the FGS at any given time. In this paper, we present the selection criteria for both the cPIC and the fgPIC, and asses their impact on the construction of these calibration catalogs for PLATO.

astro-ph.IM↗

arXiv2026

MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation

Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing reinforcement learning approaches typically rely on a single monolithic policy to acquire multiple skills, which often leads to cross-skill gradient interference and motion pattern conflicts in high-degree-of-freedom systems. As a result, generated behaviors frequently exhibit unnatural movements, limited stability, and poor generalization to complex task compositions. To address these limitations, we propose MetaWorld-X, a hierarchical world model framework for humanoid control. Guided by a divide-and-conquer principle, our method decomposes complex control problems into a set of specialized expert policies (Specialized Expert Policies, SEP). Each expert is trained under human motion priors through imitation-constrained reinforcement learning, introducing biomechanically consistent inductive biases that ensure natural and physically plausible motion generation. Building upon this foundation, we further develop an Intelligent Routing Mechanism (IRM) supervised by a Vision-Language Model (VLM), enabling semantic-driven expert composition. The VLM-guided router dynamically integrates expert policies according to high-level task semantics, facilitating compositional generalization and adaptive execution in multi-stage loco-manipulation tasks.

cs.RO↗

arXiv2026

KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation

Code evolution is inevitable in modern software development. Changes to third-party APIs frequently break existing code and complicate maintenance, posing practical challenges for developers. While large language models (LLMs) have shown promise in code generation, they struggle to reason without a structured representation of these evolving relationships, often leading them to produce outdated APIs or invalid outputs. In this work, we propose a knowledge graph-augmented framework that decomposes the migration task into two synergistic stages: evolution path retrieval and path-informed code generation. Our approach constructs static and dynamic API graphs to model intra-version structures and cross-version transitions, enabling structured reasoning over API evolution. Both modules are trained with synthetic supervision automatically derived from real-world API diffs, ensuring scalability and minimal human effort. Extensive experiments across single-package and multi-package benchmarks demonstrate that our framework significantly improves migration accuracy, controllability, and execution success over standard LLM baselines. The source code and datasets are available at: https://github.com/kangjz1203/KCoEvo.

cs.SE↗

arXiv2026

CARD: Towards Conditional Design of Multi-agent Topological Structures

Large language model (LLM)-based multi-agent systems have shown strong capabilities in tasks such as code generation and collaborative reasoning. However, the effectiveness and robustness of these systems critically depend on their communication topology, which is often fixed or statically learned, ignoring real-world dynamics such as model upgrades, API (or tool) changes, or knowledge source variability. To address this limitation, we propose CARD (Conditional Agentic Graph Designer), a conditional graph-generation framework that instantiates AMACP, a protocol for adaptive multi-agent communication. CARD explicitly incorporates dynamic environmental signals into graph construction, enabling topology adaptation at both training and runtime. Through a conditional variational graph encoder and environment-aware optimization, CARD produces communication structures that are both effective and resilient to shifts in model capability or resource availability. Empirical results on HumanEval, MATH, and MMLU demonstrate that CARD consistently outperforms static and prompt-based baselines, achieving higher accuracy and robustness across diverse conditions. The source code is available at: https://github.com/Warma10032/CARD.

cs.CL↗

arXiv2026

SkillNet: Create, Evaluate, and Connect AI Skills

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 600,000 skills, an interactive platform, and a versatile Python toolkit. Experiments on ALFWorld, WebShop, and ScienceWorld show 40% higher average rewards and 30% fewer execution steps across multiple backbone models. Furthermore, SkillNet-Gym benchmarks skill retrieval, utilization, and composition, while SkillNet-Fabric enables task-specific skill routing through lightweight Wikis. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.

cs.AI↗

arXiv2026

Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring

Accurate cell instance segmentation is foundational for digital pathology analysis. Existing methods based on contour detection and distance mapping still face significant challenges in processing complex and dense cellular regions. Graph coloring-based methods provide a new paradigm for this task, yet the effectiveness of this paradigm in real-world scenarios with dense overlaps and complex topologies has not been verified. Addressing this issue, we release a large-scale dataset GBC-FS 2025, which contains highly complex and dense sub-cellular nuclear arrangements. We conduct the first systematic analysis of the chromatic properties of cell adjacency graphs across four diverse datasets and reveal an important discovery: most real-world cell graphs are non-bipartite, with a high prevalence of odd-length cycles (predominantly triangles). This makes simple 2-coloring theory insufficient for handling complex tissues, while higher-chromaticity models would cause representational redundancy and optimization difficulties. Building on this observation of complex real-world contexts, we propose Disco (Densely-overlapping Cell Instance Segmentation via Adjacency-aware COllaborative Coloring), an adjacency-aware framework based on the "divide and conquer" principle. It uniquely combines a data-driven topological labeling strategy with a constrained deep learning system to resolve complex adjacency conflicts. First, "Explicit Marking" strategy transforms the topological challenge into a learnable classification task by recursively decomposing the cell graph and isolating a "conflict set." Second, "Implicit Disambiguation" mechanism resolves ambiguities in conflict regions by enforcing feature dissimilarity between different instances, enabling the model to learn separable feature representations.

cs.CV↗

arXiv2026

Time-dependent density functional theory study of strong-field laser-induced coulomb explosion of the HCl dimer

We present a channel-resolved interpretation of laser-driven Coulomb explosion of the HCl dimer from an ensemble of trajectories. Three dominant outcomes are identified: a minor three-body channel and two four-body channels (sequential and near-simultaneous dissociation of both molecules). The key result is that pathway selection is strongly correlated with the degree of ionization during the laser interaction, which is in turn strongly modulated by laser-molecule orientation. Higher early-time ionization predisposes the system toward near-simultaneous four-body breakup, whereas lower ionization favors sequential and three-body fragmentation; for low-ionization cases, a fragment-resolved charge metric further differentiates three-body and sequential behavior. These charge-dependent trends consistently map onto experimentally accessible observables: the simultaneous mechanism dominates the high-energy tail of the kinetic energy release (KER) spectrum and populate distinct regions of the emission-angle distributions, while sequential events concentrate at lower KER. Overall, early-time charge evolution provides a unifying explanation for channel branching and for the channel-resolved fragmentation signatures.

physics.chem-ph↗

arXiv2026

PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for intermediate reasoning . While Process Reward Models (PRMs) offer dense feedback, they risk premature collapse when used alone, as early low-reward tokens can drive policies toward truncated outputs. We introduce Process Relative Policy Optimization (PRPO), which combines outcome reliability with process-level guidance in a critic-free framework. PRPO segments reasoning sequences based on semantic clues, normalizes PRM scores into token-level advantages, and aligns their distribution with outcome advantages through location-parameter shift. On MATH500, PRPO improves Qwen2.5-Math-1.5B accuracy from 61.2% to 64.4% over GRPO using only eight rollouts and no value network, demonstrating efficient fine-grained credit assignment within critic-free optimization. Code is available at: https://github.com/SchumiDing/srpocode

cs.LG↗

arXiv2025

Tracing the Heart's Pathways: ECG Representation Learning from a Cardiac Conduction Perspective

The multi-lead electrocardiogram (ECG) stands as a cornerstone of cardiac diagnosis. Recent strides in electrocardiogram self-supervised learning (eSSL) have brightened prospects for enhancing representation learning without relying on high-quality annotations. Yet earlier eSSL methods suffer a key limitation: they focus on consistent patterns across leads and beats, overlooking the inherent differences in heartbeats rooted in cardiac conduction processes, while subtle but significant variations carry unique physiological signatures. Moreover, representation learning for ECG analysis should align with ECG diagnostic guidelines, which progress from individual heartbeats to single leads and ultimately to lead combinations. This sequential logic, however, is often neglected when applying pre-trained models to downstream tasks. To address these gaps, we propose CLEAR-HUG, a two-stage framework designed to capture subtle variations in cardiac conduction across leads while adhering to ECG diagnostic guidelines. In the first stage, we introduce an eSSL model termed Conduction-LEAd Reconstructor (CLEAR), which captures both specific variations and general commonalities across heartbeats. Treating each heartbeat as a distinct entity, CLEAR employs a simple yet effective sparse attention mechanism to reconstruct signals without interference from other heartbeats. In the second stage, we implement a Hierarchical lead-Unified Group head (HUG) for disease diagnosis, mirroring clinical workflow. Experimental results across six tasks show a 6.84% improvement, validating the effectiveness of CLEAR-HUG. This highlights its ability to enhance representations of cardiac conduction and align patterns with expert diagnostic guidelines.

cs.LG↗