arXiv subjects

Kun Zhang

Publications and source records attributed to Kun Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Negative quasiprobability trajectories for Bell-diagonal states under local decoherence

The fluctuation theorem (FT) relates microscopic trajectory distributions to macroscopic averages. Using quasiprobability trajectories, this framework has recently been extended to quantum information dynamics. Despite sharing the form of conventional thermodynamic FTs, information FTs involve quasiprobabilities whose negativity and statistical properties remain poorly understood. We analytically determine the properties of negative distributions based on the two-qubit Bell-diagonal states evolving under local dephasing, depolarizing, and amplitude-damping channels. We show that the occurrence of negative quasiprobabilities is not determined by the entanglement or Bell nonlocality of the initial state. Instead, a diagonal-interference decomposition of the transition quasiprobability provides a sufficient condition for negativity. More importantly, we prove that quasiprobability distributions containing negative weights can violate Horváth's necessary and sufficient criterion for the Jensen-Steffensen inequality to hold for every continuous convex function, even though the specific exponential Jensen-like relation enforced by the FT and the quantum data-processing inequality remains valid. This trajectory-level contrast with classical stochastic descriptions reveals a distinctive feature of quantum information dynamics that is invisible when only the corresponding average-level information inequalities are considered.

quant-ph↗

arXiv2026

CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization

Graph Neural Networks (GNNs) deliver strong performance on graph tasks, but their accuracy drops significantly under out-of-distribution (OOD) scenarios. Under distribution shifts, GNNs often fit environmental noise and spurious correlations instead of stable causal mechanisms, leading to weak OOD robustness and unstable predictive representations. Existing solutions based on environment invariance or causal reasoning are insufficient for node classification, as they do not explicitly model the fine-grained latent geometry required by the task. We further observe a training instability named Info-Jitter, where the mutual information between predictive representations and ground-truth labels fluctuates throughout training. To address these issues, we construct a node-classification-specific causal graph derived from the task's geometric objective. Using do-calculus to block non-causal paths caused by environmental noise, we derive a deconfounded interventional objective and a variational lower bound to disentangle representations into intra-class and inter-class components. We then propose Causal-Guided Representation Learning (CGRL), a framework with two core modules. First, a multi-branch re-weighted representation learning (RRL) module learns a causal modulation matrix to amplify causal signals and suppress environmental noise during message passing. Second, an optimization strategy combining intra-class aggregation, inter-class separation, energy-based reconstruction and supervised prediction regularizes the latent space for robust node-level generalization. Experiments on multiple benchmark datasets show that CGRL outperforms strong baselines across various distribution shifts and effectively mitigates the Info-Jitter phenomenon.

stat.ML↗

arXiv2026

DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents

Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM agents. Existing studies mainly focus on improving the tool-use capabilities of LLM agents, while largely treating tool documentation as a fixed input. Although several recent works attempt to optimize tool documentation through rewriting or compression, little is known about how the information contained in tool documentation affects agent performance across different settings. To bridge this gap, we conduct a large-scale empirical study on tool documentation for LLM agents. Our study reveals substantial heterogeneity in the information fields provided by existing tool documentation. Moreover, the effectiveness of different information fields is highly dependent on the task domain, LLM backbone, and agent paradigm, indicating that no fixed tool documentation can consistently generalize across diverse agent settings. Motivated by these findings, we propose DocsChisel, an adaptive tool documentation optimization framework for LLM agents. DocsChisel analyzes failed execution traces of a target LLM agent to identify documentation-related issues, and iteratively optimizes tool documentation by adding, removing, and refining information fields for each tool. We evaluate DocsChisel against two state-of-the-art baselines, i.e., EasyTool and DRAFT. Experimental results show that DocsChisel improves the task success rate of LLM agents by 95.89% over the original tool documentation and by 75.15%, on average, over existing baselines, while incurring limited optimization time and token overhead

cs.LG↗

arXiv2026

Asymptotic optimality of Grover-Radhakrishnan-Korepin algorithm

Grover's algorithm is a cornerstone of quantum algorithms and is strictly optimal in oracle-query complexity. While the full search problem admits no further improvement, one may trade accuracy for speed in the partial search problem, where the task is to identify only the block containing the target item. The best known quantum algorithm for the partial search problem is the Grover-Radhakrishnan-Korepin (GRK) algorithm, whose optimality has long been conjectured but not proved. In this work, we prove the optimality of GRK in the large-block limit. We formulate partial search as a time-optimal control problem and apply the Pontryagin maximum principle to derive the switching-function dynamics, establish the bang-bang structure of regular extremals, and exclude non-optimal switching patterns. As a result, we show that the optimal regular extremal has the global-local-global form, which yields a control-theoretic proof of the asymptotic optimality of the GRK algorithm in oracle-query complexity.

quant-ph↗

arXiv2026

Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce

In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives and distinct authority. We introduce Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions. Through its Vibe Commerce Protocol (VCP), ACWorld validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible. The ACWorld Benchmark contains a 200-task capability-coverage track and a 60-task large-catalog track that searches 785,022 transactable listings. Across ten models, mean scores range from 65.9% to 85.6% and from 56.1% to 91.4%, respectively. Our analysis shows that process-level evidence is necessary: final state alone can miss evaluated errors, incomplete trajectories still retain useful process signals, and large-catalog tasks expose bottlenecks across stages.

cs.AI↗

arXiv2026

Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions

Bridging the gap between visual realism and physical understanding is a core challenge for video-based world models. We study the structural identifiability of continuous-time physical laws from raw pixels, focusing on whether an encoder-only pipeline can uniquely recover the parameters of second-order linear ODEs. We prove that a level-set slope-coverage condition ensures the learned latent space is locally affine to the true physical state, enabling exact parameter recovery. Our theory provides the first characterization of minimal data requirements across damping regimes, establishing that underdamped systems are identifiable from a single video clip, whereas other regimes require three diverse trajectories. We further introduce a variance-floor regularizer to stabilize the decoder-free objective and prevent latent collapse. Validated on synthetic and real-world data, our approach demonstrates that interpretable physical constants can be reliably estimated from video without the need for compute-intensive pixel reconstruction, ensuring both physical correctness and transparency. Code is available at https://github.com/wenjiewang3/PhysicsFromVideo.

cs.CV↗

arXiv2026

Uncharted Waters: Selling a New Product Robustly

New products often involve uncertainty about product fit, while sellers may also be unsure about what alternatives buyers face. I study a seller of a new product who sets a price and provides product-fit information before the buyer decides whether to search for an outside option. The buyer knows the outside-option distribution; the seller knows only its mean and bounds and maximizes guaranteed profit across compatible distributions. Information provision has two roles: it can hedge against uncertainty about the outside-option distribution and deter search by making buying without search attractive. Price governs their relative value: a higher price raises revenue per sale but makes search deterrence harder. The results help explain why new products differ in product-fit information and show that lower search costs can raise prices and make information noisier, challenging the presumption that easier search necessarily benefits consumers.

econ.TH↗

arXiv2026

Concept Concentration for Faithful Representation Intervention

Representation intervention aims to localize and modify the representations that encode the underlying concepts in large language models (LLMs) to elicit the aligned and expected behaviors. Despite the empirical success, it has never been examined whether one could localize the faithful concepts for intervention. In this work, we explore the question in safety alignment. If the interventions are faithful, the intervened LLMs should erase the harmful concepts and be robust to both in-distribution adversarial prompts and the out-of-distribution (OOD) jailbreaks. While it is feasible to erase harmful concepts without degrading the benign utility of LLMs in linear settings, we show that it is infeasible in the general non-linear setting. To tackle the issue, we propose COncept ConcentrAtion (COCA). COCA refactors the training data with an explicit reasoning process, which first identifies the potential unsafe concepts and then decides the responses. Essentially, COCA simplifies the decision boundary between harmful and benign representations, enabling more effective linear erasure. Extensive experiments with multiple representation intervention methods and model architectures demonstrate that COCA significantly reduces both in-distribution and OOD jailbreak success rates, and meanwhile maintaining strong performance on regular tasks such as math and code generation. Our code is publicly available at: https://github.com/tmlr-group/COCA .

cs.LG↗

arXiv2026

Local Causal Structure Learning in the Presence of Latent Variables and Selection Bias

Discovering the direct causes and effects of a target variable from observational data is a fundamental problem in causal discovery, with broad applications in domains such as gene regulatory analysis and biomedical research. Existing causal discovery methods either learn a global causal structure, which incurs substantial computational cost, or assume the absence of latent variables and selection bias, assumptions that are often violated in real-world settings. Motivated by these challenges, we study local causal structure learning in the presence of latent variables and selection bias. Specifically, we first characterize a local region that enables target-specific causal discovery without recovering the entire global structure. We then establish a theoretical bridge between causal information learned from the observed distribution induced on this local region and the corresponding information in the global causal structure. Building on these foundations, we propose LoCaLS, a local causal structure learning algorithm that is sound and complete under standard assumptions and identifies the same direct causes and effects of a target variable as those identifiable by global causal discovery methods, while allowing for latent variables and selection bias. Extensive experiments on random and real-world structures demonstrate that the proposed method consistently achieves higher structural accuracy than existing local methods while requiring substantially less computational effort than state-of-the-art global methods. Furthermore, applications to two real-world gene expression datasets reveal biologically plausible target-specific causal structures, demonstrating its practical applicability in large-scale biological data analysis.

cs.LG↗

arXiv2026

Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis

Systematic comparisons between current situations and structurally similar past events in the historical, i.e., historical analogies, is among the most powerful tools for foresight analysis. In this work, we present a new task called Analogical Deep Research (ADR) to Large Language Model (LLM) agents and construct the first ADR benchmark ADR-bench to study whether LLM agents are able to find and leverage historical analogies when doing foresight analysis. Our investigation reveals a key obstacle: LLM agents are poor at finding analogies because they match on surface features rather than underlying mechanisms. We argue that ADR is inherently a causal question as it requires understanding why the event occurred. Based on our theoretical analysis, we propose two principles required for ADR, including the mechanism alignment and cross-analogy confirmation. Built upon our theoretical results, we propose a new agentic framework called Causal Analogical Researcher (CANA) that guides LLMs to find and integrate historical analogies. CANA incorporates a simple yet effective structural decomposition representation, and integrates structural feedback for reflective improvements of historical analogy identification and integration. We show that CANA brings up to 10% improvements in historical analogy generation, and surpasses the state-of-the-art deep research agents in the ADR-bench. Case studies with the ongoing events confirm the effectiveness of CANA in leveraging historical analogies.

cs.CL↗

arXiv2026

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networks may learn functions far simpler than their parameter counts suggest, but it is challenging to construct codes that realize this simplicity. Parameter-based methods such as quantization produce code lengths that scale with model size, insensitive to how much information the parameters store. Prequential coding bypasses this issue by compressing the training trajectory, but codes the exact data sequence regardless of how much the model learns, yielding large codes when the data has high entropy. We introduce requential coding, where a teacher model selects training samples drawn from the student's own distribution. The student's code records only these selections, which cost bits only where teacher and student disagree. The resulting code length is independent of parameter count and data entropy, and often orders of magnitude shorter than the prequential counterpart, with an advantage that grows with scale. This compression sheds light on phenomena inaccessible to prior compressors. Holding loss fixed, larger models and ensembles compress to much smaller sizes despite more parameters. Plugged into a PAC-Bayes bound, the requential code yields state-of-the-art generalization guarantees for billion-parameter LLMs, outperforming bounds built on aggressive post-training quantization even granted zero error. The bound tightens with scale in the compute-optimal regime, as models become increasingly compressible relative to dataset size. The same code predicts that models gradually overfit when trained for multiple epochs. It also isolates the learnable information in a dataset from its unpredictable, random content, revealing that lower-entropy text holds far more learnable structure than higher-entropy image data.

cs.LG↗

arXiv2026

Dzyaloshinskii-Moriya Gradients Unlock Topological Dimensional Reduction in Magnetic Hopfions

Three-dimensional magnetic solitons retain topological protection only while their spin field remains continuous. Here we show that chemical inhomogeneity can break this protection in a controlled way, converting a hopfion-like toroidal texture into an effectively two-dimensional skyrmion string. Tilt-dependent Lorentz transmission electron microscopy, electron energy-loss spectroscopy, and micromagnetic simulations of pristine, uniformly Y-doped, and nonuniformly Y-doped disordered TiO2 nanoparticles embedded in a FeCrNiMn host reveal two regimes. Uniform Y doping enriches Ti3+/oxygen-vacancy localization centers and stabilizes closed rings with Hopf invariant QH approximately 1. Nonuniform Y doping forms a Ti4+-rich, vacancy-depleted boundary that creates a sharp q=D/(2A) gradient and a weak-moment leakage channel. This coupled mismatch torque and continuity leakage split the ring, leaving a skyrmion-string remnant and a field-sensitive helicity texture.

cond-mat.other↗

arXiv2026

TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

Temporal causal representation learning methods assume that causal mechanisms switch instantaneously between discrete domains, yet real-world systems often exhibit continuous mechanism transitions. For example, a vehicle's dynamics evolve gradually through a turning maneuver, and human gait shifts smoothly from walking to running. We formalize this setting by modeling transitional mechanisms as convex combinations of finitely many atomic mechanisms, governed by time-varying mixing coefficients. Our theoretical contributions establish that both the latent causal variables and the continuous mixing trajectory are jointly identifiable. We further propose TRACE, a Mixture-of-Experts framework where each expert learns one atomic mechanism during training, enabling recovery of mechanism trajectories at test time. This formulation generalizes to intermediate mechanism states never observed during training. Experiments on synthetic and real-world data demonstrate that TRACE recovers mixing trajectories with up to 0.99 correlation, substantially outperforming discrete-switching baselines.

cs.LG↗

arXiv2026

Asymptotic bounds on quantum partial search algorithm and its applications to parallel search

Grover's algorithm provides a quadratic speedup over classical algorithms for searching an unstructured database and is known to be strictly optimal in oracle query complexity, with tight bounds on its success probability. Although the standard Grover search cannot be further accelerated in the full-search setting, a trade-off between accuracy and query complexity gives rise to the partial search problem. The Grover-Radhakrishnan-Korepin (GRK) algorithm is the standard and most extensively studied protocol for this task. In this work, we provide systematic numerical evidence that the GRK operator sequence gives the highest success probability in all examined cases, supporting it as the optimal ansatz among admissible compositions of global and local Grover operators. Guided by this numerically supported GRK ansatz, we derive an asymptotically tight upper bound on the maximal success probability within the GRK family and establish the corresponding lower bound on the minimal expected number of oracle queries. Furthermore, we investigate parallel quantum search within the partial-search framework. While a direct GRK-based parallelization does not outperform established parallel Grover schemes, we demonstrate that a hybrid strategy combining partial and full search protocols yields a strict, though subleading, improvement over the outer parallel Grover scheme. Our results clarify the fundamental limits of quantum partial search and its role in optimizing parallel quantum search algorithms.

quant-ph↗

arXiv2026

Emergent mirror symmetry in the optimization of the central-spin quantum battery

Quantum batteries provide a useful setting for exploring nonequilibrium many-body effects in energy storage. Here we investigate the optimization of a quantum battery based on the central-spin model. We identify two complementary structural indicators associated with the effective charging dynamics: one yields an upper bound on the average charging power, while the other characterizes the buildup of stored energy. We show that these two indicators are jointly optimized at a distinguished initial charger excitation number, which selects a particular Dicke sector of the model. At this common optimal point, the effective charging Hamiltonian becomes exactly mirror symmetric, suggesting mirror symmetry as a useful structural indicator for optimizing the performance of quantum batteries in terms of both charging power and energy storage. We further show that the corresponding optimal dynamics can be closely approximated by product initial states, in particular by spin coherent states whose excitation-number distribution is centered at the symmetry-selected point. Our results establish a direct connection between charging performance, optimal-state structure, and emergent symmetry in the central-spin quantum battery, and suggest symmetry as a useful organizing principle for efficient charging in interacting many-body quantum systems.

quant-ph↗

arXiv2026

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

cs.LG↗

arXiv2026

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention. Since scientific discovery fundamentally relies on uncovering causal relationships from observations, the capability of causal thinking, i.e., distinguishing causation from correlation and recognizing hidden biases, is essential to LLM agents. Although a number of benchmarks exist for AI Scientists, none explicitly incorporate challenges from selection bias, measurement error, and hidden confounders that widely exist in real-world scientific discovery. To this end, we present CausalGame, a benchmark that evaluates the causal thinking capabilities of LLM agents through interactive games. CausalGame asks LLM agents to actively design experimental protocols, collect observation data, and derive a final solution with an explanation report. To emulate realistic scientific discovery challenges, we design 14 scenarios that incorporate selection bias, measurement error, and hidden confounders. Across 30 LLM agents, none demonstrates reliable causal thinking: the best model reaches only 68.0% survival against analytical optima of 78-85%, and merely 5-7% of sessions receive credits on the causal-reasoning rubrics. CausalGame provides a scalable and controlled testbed for evaluating the causal thinking of AI Scientist agents.

cs.CL↗

arXiv2026

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approaches often rely on high-dimensional latent spaces or generic visual embeddings that retain many factors irrelevant to control, limiting efficiency and generalization across tasks. To this end, we study how agents can learn world models with representations that are task-specific, minimal, and sufficient for decision-making. We achieve this via a closed-loop synergy between the agent and the world model, in which structured world-model learning distills task-sufficient representations from informative interaction data. On the agent side, agents actively probe the environment to collect informative trajectories that expose task-relevant latent factors, guided by an adaptive curriculum. On the world-model side, we learn structured representations over observations to distill compact, task-sufficient latent states from the collected interaction data. This synergy enables the empirical recovery of task-sufficient latent representations that capture all control-relevant factors. Leveraging these representations, the resulting policies achieve improved sample efficiency and generalization, including generalization across skills, object-skill compositions, and previously unseen tasks on standard continuous-control and robotic-manipulation benchmarks.

cs.LG↗