Searcharxiv⌕ Search

arXiv subjects

Zhong Zhang

Publications and source records attributed to Zhong Zhang.

At least 19 recordsLinked to original sources
arXiv2026

HeteGCD: Statistics-Aware Dual-Prototype Learning for Generalized Category Discovery on Heterophilous Graphs

Heterophilous graphs are prevalent in real-world applications, where connected nodes often exhibit dissimilar attributes or belong to different classes, posing significant challenges to conventional graph learning methods based on homophily. This limitation becomes particularly pronounced in generalized category discovery (GCD), which requires models to recognize known classes and discover novel ones using labels from known classes only. However, existing graph GCD methods typically rely on aforementioned homophily-based inductive biases, which are ill-suited to heterophilous graphs. Meanwhile, although current heterophilous graph learning methods exploit diverse neighborhood signals, their selection and fusion are often guided by supervision across all classes, including novel classes whose labels are unavailable in GCD. These limitations raise a key question: how can heterogeneous neighborhood information be effectively leveraged for category discovery without any novel-class supervision? To answer this question, in this study we propose HeteGCD, a new statistics-aware dual-prototype learning perspective for generalized category discovery on heterophilous graphs. The key idea is to examine both statistics of local attribute differences and neighborhood class distribution to extract discriminative information in feature and probability spaces simultaneously. Specifically, a gated dual-stream encoder integrates both node attributes and local attribute-difference statistics to learn informative node representations. Afterwards, a dual-prototype classifier combines feature-based similarity with distribution-based consistency to support category discovery. Experiments on five heterophilous graphs show that HeteGCD achieves competitive performance against 24 baseline combinations.

cs.LG↗
arXiv2026

Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents

Large language model (LLM) agents increasingly execute tasks asynchronously: a main agent continues working while its subagents run, and the task state may change before their results arrive. The main agent must decide which work to update or preserve and which checks to repeat, while avoiding prohibited changes. Final task success alone does not reveal whether these results were handled correctly, and natural asynchronous arrivals are hard to reproduce. We introduce Async-RBench, a benchmark for asynchronous task execution in LLM agents, with 200 executable tasks covering eight scenarios. A scenario controller regulates result delivery using predefined task-state conditions, while an Event Response Contract (ERC) specifies what each response must change, preserve, avoid, and re-verify. The Dynamic Replanning Score (DRS) weights the response process and outcome equally and is reported separately from task success. We evaluate nine agents and find DRS scores of 19.2 to 45.1, with the lowest scores on duplicate reports and subagent failures. Under our execution protocol, all nine agents obtain lower task success with asynchronous than with batched delivery (26.0% vs. 29.7% on average). For three agents, prompting the main agent to rebuild its plan after every result improves DRS by only 2.6 to 3.5 points. Together, these findings highlight the challenges of reliable asynchronous task execution and the need to evaluate how agents handle incoming results alongside end-to-end task success.

cs.AI↗
arXiv2026

VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards

Reinforcement learning for computer-use agents increasingly relies on proactive reward agents that interact with the post-execution GUI environment to verify what recorded screenshots cannot reveal. The reliability of such verification hinges on two coupled decisions: what to check and when to stop. Existing methods leave these decisions to prompted foundation models. However, neither scaling up the model nor providing few-shot examples reliably improves verification: prompted Judges ranging from 4B to GPT-5.4 all plateau at 68%-70% macro-average agreement. This is because the value of a check depends on the environment rather than the task alone, and becomes apparent only through execution. Learning from execution is itself constrained, as the Actor's terminal state cannot be faithfully replicated during training, allowing only one verification attempt per state. We introduce VeriCUA, a proactive reward agent that learns its verification strategy from these single attempts. A trainable Judge decides what to check and when to stop, while a frozen Probe executes the checks in the live environment. Online reinforcement learning optimizes the Judge for both verdict correctness and efficient Probe use, with returns normalized across terminal states. Trained only on OSWorld and evaluated without further training on MobileWorld and WebArena-Verified, VeriCUA achieves the highest reward agreement across all three benchmarks and lies on the agreement-cost Pareto frontier among proactive verifiers. It surpasses few-shot GPT-5.4 by 5.36 points with 47.6%-59.8% fewer Probe tokens, and even a 1B VeriCUA exceeds every prompted Judge. As the reward for Actor RL, it raises task success by 3.21 points overall and 5.40 points on held-out multi-application tasks. These results identify the verification strategy, not verifier scale, as the key to reliable GUI rewards.

cs.AI↗
arXiv2026

Synergizing Large Language Models and Theory for Human-like Causal Reasoning

Performing causal reasoning akin to humans is fundamental to achieving strong artificial intelligence. However, existing studies on causal reasoning and large language models (LLMs) often underestimate the role of human causal cognition. Human causal reasoning is far more than recognizing causes and effects. Humans often factor in many other considerations when establishing a causal link between two events, such as norm violations, intentionality, morality, counterfactual scenarios, etc. To simulate such reasoning, it is intuitive to identify cause-effect pairs using token causality formalisms while modeling the factors that influence human causal judgment using findings from cognitive science experiments. To support the evaluation and modeling of human-like causal reasoning in LLMs, we introduce HCR-Bench, a challenging benchmark with 1,093 instances and detailed human causal reasoning step annotations, and HCR-Reasoner, an approach that systematically integrates theories of token causality and cognitive science into LLMs for human-like causal reasoning. Results suggest that HCR-Reasoner consistently improves LLMs' causal alignment with humans, and that theory-guided reasoning is highly effective.

cs.CL↗
arXiv2026

Probing Neutrinophilic Scalars in Muon Decays

The non-standard self-interactions of neutrinos could be induced by (light) scalars that couple primarily to neutrinos. In this work, we investigate the effects of neutrinophilic scalars $ϕ$ on muon decays at the tree, 1-loop and 2-loop levels, considering both Dirac and Majorana neutrinos. The most phenomenologically interesting processes are the 1-loop decay $μ\to e ϕϕ$ and $ϕ$-induced decay $μ\to e γ$ at the 2-loop order from the same coupling $g_{\rm eff}$, and the 1-loop corrections of $ϕ$ to the SM muon decay and the four-body muon decays $μ^- \to e^- ν_μν_μϕ,\, e^- \barν_e \barν_e ϕ$, both induced by the coupling $h_{eμ}$ of $ϕ$ to Majorana neutrinos. The current experimental bounds on $μ\to e γ$ provide the most stringent limits on the coupling $g_{\rm eff}$, up to roughly 0.064, for the scalar mass $m_ϕ\gtrsim 8.7$ MeV. The precise $G_F$ measurements constrain the coupling $|h_{eμ}|$ down to roughly $0.027$, with the scalar mass $m_ϕ$ constrained up to roughly $5.9$ TeV. For $m_ϕ\gtrsim {\cal O}({\rm GeV})$, the $G_F$ measurements are more stringent than other existing laboratory, astrophysical and cosmological constraints. Some other $ϕ$-induced processes are also possible, which are, however, heavily suppressed by the tiny neutrino masses and/or the loop factor.

hep-ph↗
arXiv2026

Inducing Process Supervision from Outcome-Only Reinforcement Learning

Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training strong PRMs remains costly: human step annotation is difficult to scale, while Monte Carlo estimation is computationally expensive and can drift from the intrinsic correctness of steps. To get effective PRMs at low cost, we introduce TIPS (Thinking-Induced Process Supervision), an outcome-only reinforcement learning (RL) framework for training generative PRMs. In TIPS, the model generates a chain-of-thought (CoT) followed by step-level labels and an outcome label. The reward depends solely on whether the predicted outcome matches the ground truth, and the resulting group-relative advantage is used to optimize the entire generated response. Intuitively, when checking intermediate steps helps determine the outcome, more accurate checks can lead to better outcome judgments and higher rewards. Outcome-only RL can therefore reinforce step-level verification without explicit process supervision. We validate the effectiveness of TIPS across math and agent benchmarks and four backbone families. Notably, TIPS-Qwen3-4B-Thinking-2507 reaches 85.2 F1 on ProcessBench with only 3.2K outcome-labeled trajectories, surpassing all evaluated trained PRMs and strong prompt-only judges such as GPT-5.4-Instruct and Claude-4.7-Opus, while still trailing o1-mini. Code and data are available at https://github.com/RUCBM/TIPS.

cs.LG↗
arXiv2026

What is Missing from AI Post-Training AI: An Empirical Analysis

Large language model (LLM) agents can now post-train an LLM end-to-end, raising the prospect of recursive self-improvement (RSI). Yet this progress is measured by aggregate benchmark scores, which cannot tell whether an agent executes a fixed plan well or strategically revises the plan when it fails. We separate these two capabilities: execution-level capability, iterating within an established training strategy, and strategy-level capability, revising that strategy as experimental evidence accumulates. Analyzing 1,338 post-training trajectories of frontier agents, we find that agents reliably execute post-training but lock into a default strategy, which follows the agent rather than the task, and only 2.1% of transitions between adjacent training runs ever change strategy. We then test whether the agent lacks experience, reasoning, or the decision to switch. (1) Experience improves execution but not the strategy. (2) Additional reasoning compute yields front-loaded gains on easier tasks but refines, rather than revises, the committed strategy. (3) Human review before training changes which strategy the agent locks into, not whether it locks in, whereas a single mid-run instruction outperforms the agent's own continuation by up to 17.44 points under the same budget. In conclusion, what the agent lacks is the decision to reopen a committed strategy and try another one. Realizing RSI therefore calls for interaction protocols and training signals that make strategy revision an explicit, rewarded decision.

cs.AI↗
arXiv2026

AgentRM: Enhancing Agent Generalization with Reward Modeling

Existing LLM-based agents have achieved strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. Hence, some recent work focus on fine-tuning the policy model with more diverse tasks to improve the generalizability. In this work, we find that finetuning a reward model to guide the policy model is more robust than directly finetuning the policy model. Based on this finding, we propose AgentRM, a generalizable reward model, to guide the policy model for effective test-time search. We comprehensively investigate three approaches to construct the reward model, including explicit reward modeling, implicit reward modeling and LLM-as-a-judge. We then use AgentRM to guide the answer generation with Best-of-N sampling and step-level beam search. On four types of nine agent tasks, AgentRM enhances the base policy model by $8.8$ points on average, surpassing the top general agent by $4.0$. Moreover, it demonstrates weak-to-strong generalization, yielding greater improvement of $12.6$ on LLaMA-3-70B policy model. As for the specializability, AgentRM can also boost a finetuned policy model and outperform the top specialized agent by $11.4$ on three held-in tasks. Further analysis verifies its effectiveness in test-time scaling. Codes will be released to facilitate the research in this area.

cs.CL↗
arXiv2026

Parallel-in-Time Nonlinear Optimal Control via GPU-native Sequential Convex Programming

Real-time solution of nonlinear optimal control problems remains challenging on embedded robotic hardware, where conventional solvers often rely on global sparse linear algebra or sequential recursions that are difficult to map efficiently to massively parallel processors. This paper presents ucenter, a GPU-native Sequential Convex Programming (SCP) framework for nonlinear optimal control. At each SCP iteration, nonlinear dynamics are linearized around a nominal trajectory, and the resulting convexified subproblem is solved by a consensus Alternating Direction Method of Multipliers (ADMM) scheme. The temporal splitting replaces global sparse Karush-Kuhn-Tucker factorizations with independent per-node dense solves, closed-form dynamic consistency updates, and analytical projections onto convex constraint sets. Both the outer SCP loop and the inner ADMM subproblem are executed entirely on the GPU, enabling efficient optimization. The proposed solver is evaluated on quadrotor obstacle avoidance and Mars powered descent problems using an NVIDIA Jetson AGX Orin edge platform. Benchmarking against a CPU-parallel iLQR baseline in randomized environments reveals that the GPU implementation achieves over 100 Hz batched planning throughput, a 4.1x speedup, and a 51% reduction in energy consumption, while consistently maintaining low nonlinear dynamics defects. The framework exposes reusable GPU-parallel optimization primitives that can be specialized to a wide variety of complex nonlinear optimal control settings, as demonstrated by the scenario-based robust MPC and batched Monte Carlo generation tasks.

cs.RO↗
arXiv2026

Same-sign dimuon probe of charged lepton flavor violation at electron-photon colliders

Observation of charged lepton flavor violation would constitute unambiguous evidence for physics beyond the Standard Model (SM). We identify a previously unexplored same-sign dimuon signature in electron--photon collisions, $γe^- \to e^+μ^-μ^-$, mediated by an axionlike particle (ALP) with flavor-violating $e$--$μ$ couplings. The absence of irreducible SM backgrounds and the on-shell production of the ALP render this channel intrinsically clean and highly sensitive, with only small residual backgrounds arising from detector effects. Such collisions can be realized via laser Compton backscattering at $e^+e^-$ colliders including BEPC-II with the BESIII detector, STCF, CEPC, and ILC. We find that STCF, CEPC, and ILC can probe couplings one to two orders of magnitude below existing bounds. This combination of resonant production, vanishing irreducible background, and same-sign topology would be difficult to achieve in conventional $e^+e^-$ or hadron-collider environments, establishing electron--photon collisions as a uniquely powerful probe of charged lepton flavor violation.

hep-ph↗
arXiv2026

Dual-Difficulty Curriculum Learning for Direct Preference Optimization

Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dimensional view of difficulty. In this work, we reframe alignment difficulty as a two-dimensional space spanned by Prompt Complexity (PC) and Pairwise Distinguishability (PD), providing a more principled foundation for alignment. We first demonstrate the efficacy of this space by developing DM-Curri-DPO, a framework of static curricula that already achieves significant gains over baseline methods. Moving beyond these handcrafted paths, we introduce our primary contribution: GSP-Curri-DPO, a novel Group-wise Self-Paced Learning framework. This advanced method empowers the model to navigate the difficulty grid, discovering an optimal learning trajectory based on its own evolving capabilities. Extensive experiments show our self-paced approach not only sets a new state-of-the-art on key benchmarks but, more importantly, demonstrates superior data efficiency and robustness to preference noise. Our work establishes a new paradigm for LLM alignment, offering both a structured difficulty space and an intelligent, model-driven methodology for navigating it.

cs.AI↗
arXiv2026

Pretrained Approximators for Low-Thrust Trajectory Cost and Reachability

Low-thrust trajectory design relies heavily on repeated evaluations of fuel consumption and transfer feasibility, which require expensive optimal control solutions. In this work, we show these quantities can be accurately approximated by machine learning surrogates, enabling fast and scalable evaluation across a wide range of scenarios. By increasing both dataset size and model capacity, we observe that low-thrust trajectory optimization follows a scaling law, with performance improving linearly with the logarithm of training data and network parameters, and no evidence of saturation within the explored regime. Guided by this observation, we construct a large-scale dataset using the proposed homotopy-ray strategy tailored to mission design requirements. A key is the introduction of a self-similar transformation, which allows generalization across semi-major axes, inclinations, and central bodies avoiding retraining. As a result, the same neural approximator can be applied to diverse orbital environments and mission classes. The proposed models accurately predict optimal fuel consumption and minimum transfer time for single- and multi-revolution transfers. Their performance and generalization are demonstrated on a public dataset, a multi-asteroid flyby problem from the Global Trajectory Optimization Competition, and an asteroid rendezvous mission design. The models and datasets are released as open-source to support the space community.

cs.LG↗
arXiv2026

Reachability for Low-Thrust Trajectories via Maximum Initial Mass

Reachability analysis plays a central role in low-thrust spacecraft trajectory optimization by identifying which target states can be achieved under constraints on time, thrust, and propellant. Classical approaches construct reachable sets by solving many optimal control problems over grids of terminal states, requiring extensive forward simulations with fixed initial conditions. While effective, this approach is computationally expensive and becomes impractical for high-dimensional systems or strongly nonlinear dynamics, such as those encountered in cislunar environments or solar sail missions. This work introduces a dual formulation of the reachability problem. Instead of computing reachable sets directly, we determine, for fixed transfer time and boundary conditions, the maximum allowable initial mass (or, for solar sails, a scalar sail-strength parameter) that permits a successful transfer. A target is reachable if the spacecraft's initial mass does not exceed this threshold. This reformulation reduces reachability assessment to a scalar optimization problem for each target, producing a smooth scalar field that encodes equivalent feasibility information to classical reachable sets. We develop indirect maximum-initial-mass (MIM) formulations for both electric low-thrust and solar-sail dynamics and show how they can serve as efficient reachability oracles. Building on this formulation, we construct data-driven surrogate models to approximate the MIM-based reachability indicator. We investigate fully connected neural networks and demonstrate that residual networks provide the best trade-off between accuracy, training stability, and model complexity. The resulting surrogates enable rapid reachability evaluation while preserving the numerical advantages of the dual formulation, offering a practical tool for preliminary mission design and feasibility assessment.

eess.SY↗
arXiv2026

Linear representations of the mapping class group of dimension at most $3g-3$

We classify representations of the mapping class group of a surface of genus $g$ (with at most one puncture or boundary component) up to dimension $3g-3$. Any such representation is the direct sum of a representation in dimension $2g$ or $2g+1$ (given as the action on the (co)homology of the surface or its unit tangent bundle) with a trivial representation. As a corollary, any linear system on the moduli space of Riemann surfaces of genus $g$ in this range is of algebro-geometric origin.

math.GT↗
arXiv2026

Test-Time Deep Thinking to Explore Implicit Rules

With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed directly and must be inferred through interaction. This causes agents to fall into repetitive trial-and-error loops, ultimately leading to task failure. To address this challenge, we propose Test-Time Exploration (TTExplore), a framework where a thinker component analyzes interaction history to infer these implicit rules and guide an actor. Effective exploration in this setting critically depends on the reasoning ability of the thinker. However, evaluating deep reasoning trajectories is inherently unstable and difficult, which poses a major obstacle to effective training. To overcome this issue, we introduce a novel and stable reinforcement learning pipeline. The core idea is to use accurate task-level scores as indirect rewards to bypass the difficulty of evaluating intermediate reasoning, and to retain only a single thinking node per trajectory to alleviate reward sparsity. Using this pipeline, we train a specialized 7B model, Exp-Thinker. Experiments on five text-based embodied tasks show that TTExplore equipped with Exp-Thinker improves baseline agent performance by an average of $14$-$19$ points, demonstrating the effectiveness of explicitly reasoning about implicit rules.

cs.AI↗
arXiv2026

MSDformer: Multi-scale Discrete Transformer For Time Series Generation

Discrete Token Modeling (DTM), which employs vector quantization techniques, has demonstrated remarkable success in modeling non-natural language modalities, particularly in time series generation. While our prior work SDformer established the first DTM-based framework to achieve state-of-the-art performance in this domain, two critical limitations persist in existing DTM approaches: 1) their inability to capture multi-scale temporal patterns inherent to complex time series data, and 2) the absence of theoretical foundations to guide model optimization. To address these challenges, we proposes a novel multi-scale DTM-based time series generation method, called Multi-Scale Discrete Transformer (MSDformer). MSDformer employs a multi-scale time series tokenizer to learn discrete token representations at multiple scales, which jointly characterize the complex nature of time series data. Subsequently, MSDformer applies a multi-scale autoregressive token modeling technique to capture the multi-scale patterns of time series within the discrete latent space. Theoretically, we validate the effectiveness of the DTM method and the rationality of MSDformer through the rate-distortion theorem. Comprehensive experiments demonstrate that MSDformer significantly outperforms state-of-the-art methods. Both theoretical analysis and experimental results demonstrate that incorporating multi-scale information and modeling multi-scale patterns can substantially enhance the quality of generated time series in DTM-based approaches. Code is available at this repository:https://github.com/kkking-kk/MSDformer.

cs.LG↗
arXiv2026

The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal interchangeability, such as captioning and joint clustering. Existing post-processing approaches can partially improve cross-modal compatibility; however, we show through geometric analysis that they primarily reduce the global centroid offset while leaving the underlying distributional mismatch intact. We decompose the modality gap into a Centroid Gap and a Distribution Gap, and demonstrate that the Distribution Gap is the true predictor of cross-modal task quality ($R^2 = 0.986$), whereas the commonly used Raw Gap is misleading ($R^2 = 0.691$). Motivated by this observation, we propose TPC-CMA (Three-Phase Curriculum for Cross-Modal Alignment), a fine-tuning framework that explicitly reduces both components. The proposed CMA jointly mitigates centroid offsets and reshapes the distributional structure, while a three-phase curriculum with gradient-aware scheduling progressively introduces alignment during training to enable stable optimization. Experiments demonstrate that our method significantly improves cross-modal alignment. With $α_{\text{target}}{=}0.05$, the modality gap is reduced by 66.6\% with only 4.84\% accuracy drop. Under stronger alignment ($α_{\text{target}}{=}0.5$), the gap is reduced by 82.3\%, clustering ARI improves from 0.318 to 0.516, and captioning CIDEr increases by 57.1\% over the original model. Our code and pre-trained models will be made publicly available upon acceptance.

cs.CV↗
arXiv2026

AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation

Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generalization ability of these memory designs, which highlights the need for a more flexible, learning-based memory framework. In this paper, we propose AtomMem, which reframes memory management as a dynamic decision-making problem. We deconstruct high-level memory processes into fundamental atomic CRUD (Create, Read, Update, Delete) operations, transforming the memory workflow into a learnable decision process. By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors tailored to specific task demands. Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods. Further analysis of training dynamics shows that our learning-based formulation enables the agent to discover structured, task-aligned memory management strategies, highlighting a key advantage over predefined routines.

cs.AI↗