Search arXiv⌕ Search

arXiv subjects

Yucheng Wang

Publications and source records attributed to Yucheng Wang.

At least 19 recordsLinked to original sources
arXiv2026

HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training

HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner requests future body-point targets, while the frozen controller handles joint-level execution. A learned decoder maps 32-dimensional actions to structured target windows, and measured-state imitation initializes the planner before reinforcement learning. Task learning then refines interaction behavior while reusing the decoder and controller, avoiding the need to relearn whole-body control. This combination keeps task optimization focused on a compact upper policy and supplies an initial behavior before reward-driven exploration. Starting from that available controller, the recipe accounts for about seven minutes of additional training, including reused representation fitting and a single-GPU task run. This excludes controller pretraining, data preparation, evaluation, and search. Simulated boxing experiments and component controls evaluate the resulting behavior and the roles of imitation initialization and the target representation.

cs.RO↗
arXiv2026

More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation

Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent. But an image can be faithful to the past and wrong for the present. Does visual memory always improve the generated story? We investigate this question through VMem-Bench, a two-track diagnostic study. Track-A measures which references are selected from 92 real films (16,548 segments), before generation and without generator confounds. Track-B compares four retrieval policies with no-memory and gold-informed last-seen controls on 30 causally generated stories (2,824 segments) using a shared generator. Retrieval increases entity recall from 0.559 to 0.628-0.693 and improves similarity to past appearances, but decreases precision from 0.977 to 0.915-0.938 and forbidden-entity avoidance from 0.968 to 0.845-0.898. It can also reinforce obsolete appearances after the story changes them. Conversely, high long-gap recall can arise without memory when the prompt itself supplies the appearance; an appearance-stripping analysis exposes this confound. These results distinguish historical fidelity from current-story correctness and show why retrieval relevance or final-video consistency alone does not establish memory utility.

cs.CV↗
arXiv2026

LiveAct: Towards Real-Time Multi-Agent World Models with Heterogeneous Action Interfaces

Interactive video world models predict how an environment evolves under user actions, but most existing systems assume one controlled agent and one task-specific action interface. We study multi-agent video world modeling, where one model generates a joint visual future for multiple controlled agents while interpreting heterogeneous controls ranging from binary game buttons to continuous robot commands. This task presents two complementary challenges. First, every agent-indexed action stream must control its intended visual entity independently. Second, the model must adapt the meaning of each control variable across different tasks, where the same tensor dimension may denote an attack, steering command, or robot command. We introduce LiveAct, centered on a Heterogeneous Action Interface (HAI) whose two components mirror this decomposition. To support independent control, Agent-Aware Spatial Modulation uses language-driven spatial gates and agent-specific attention to bind each action stream to its intended visual agent. To accommodate heterogeneous controls, Schema-Guided Action Adaptation describes each control variable in language and modulates its semantic token with the synchronized numerical value. We further transfer the complete interface to a blockwise causal generator through teacher forcing and rollout-aware distribution matching, enabling efficient streaming generation while retaining agent-specific control and action semantics. We instantiate the formulation on six multi-agent sources spanning games and multi-robot manipulation, and evaluate visual quality, action following, agent attribution, and latency. Across games and robot manipulation, LiveAct reaches 0.898 and 0.942 agent-attribution accuracy without agent locations or identity crops, and the causal generator attains 17.70 FPS at $512\times 448$.

cs.CV↗
arXiv2026

A parity obstruction to completeness of object cotorsion pairs

Fu, Guil Asensio, Herzog and Torrecillas asked whether a complete ideal cotorsion pair of object ideals in an exact category always induces a complete cotorsion pair of objects. We show that it need not, even in a Hom-finite, weakly idempotent complete Frobenius exact category. Our example consists of bounded complexes of finite-dimensional vector spaces with even total cohomology dimension. We characterize special object approximations by parity and identify the obstruction as a non-split idempotent in the stable category. For cohereditary pairs, a criterion of Saor\'ın and Šťov\'ıček gives an affirmative answer when the stable category is idempotent complete.

math.RA↗
arXiv2026

When Better Opportunities Backfire: Service Worker Responses to Parallel AI Deployment in Customer Acquisition

As AI voice agents get deployed in high-volume contact centers, firms can route low-intent leads to AI and allocate high-intent leads to human workers. Drawing on sequential search theory, we posit that AI-induced task allocation reshapes work, enriching opportunities facing human workers but also raising their reservation value for continuing with the lead in hand, making them less willing to persist. We study the effects of an AI voice-agent deployment at a Chinese online health-insurance brokerage using more than a half million customer outreach records surrounding the rollout. Adopting a regression-discontinuity-in-time design, we trace how worker behavior changes across the workday. Results show that the enrichment of human-facing opportunities concentrates early in the workday, raising the probability that a call is a high-intent lead by about 23 percentage points on the first three calls and fading to zero later. However, customer acquisition by human workers declines precisely where the enrichment is greatest, falling about 5 percentage points on the first three calls and flattening over the day. Consistent with the theorized reservation value mechanism, workers reallocate their earliest leads about 8 percentage points more often and persist less with them, shortening those calls by about 13%. A calibrated decomposition analysis further shows that the modest gain from improved lead ordering is outweighed by a much larger negative behavioral response. By reshaping the quality and within-workday distribution of opportunities, parallel AI deployment alters how workers pursue tasks, highlighting opportunity distribution as an important service operations state variable beyond workload and congestion.

econ.GN↗
arXiv2026

From Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for Classification

Time series foundation models (TSFMs) have achieved notable progress in classification tasks through large-scale pretraining. However, their post-training practice mainly focuses on implicit parameter fine-tuning, where task-relevant information is entangled with abundant irrelevant knowledge in vast parameter spaces. This may hinder TSFMs from precisely activating useful knowledge for downstream classification. To this end, we propose Retrieval-to-Recognition (R2R), a plug-and-play post-training paradigm that adapts pretrained TSFMs to time series classification. Rather than pretraining a new foundation model, R2R improves how existing TSFMs are post-trained: it introduces a decoupled query encoder to extract discriminative patterns and retrieve instance-level numerical knowledge from a constructed knowledge base. The retrieved explicit knowledge is then fused with the TSFM's implicit parametric embeddings, enabling joint knowledge transfer at both the parameter and feature levels. In this way, R2R allows TSFMs to recall task-relevant patterns learned during pretraining, improving the efficiency of knowledge utilization in downstream classification transfer. Experiments on 158 time series datasets show that R2R consistently improves the classification performance of state-of-the-art TSFMs. Ablation and knowledge-enhanced studies further validate the effectiveness of the proposed framework.

cs.LG↗
arXiv2026

DIAL: Dynamic and Informed Adjustment of the Native Stochastic Law for Reliable Weather Ensembles

Ensemble weather forecasts can look reliable in global averages while hiding too little spread in some cases and too much in others. These errors vary across variables, spatial scales, lead times, and weather states. Adapting randomness during forecasting can correct these errors, but training fixes stochastic behavior beforehand and output calibration acts afterward. Inference guidance also acts during forecasting, but typically scores ensemble members separately rather than the ensemble as a whole. Reliability feedback arrives at the end, and tracing it backward through many chaotic forecast steps is expensive and unstable. We therefore introduce Dynamic and Informed Adjustment of the Native Stochastic Law (DIAL), which controls a frozen model's native stochasticity. DIAL learns from past forecasts to predict whether each variable and scale needs more or less spread. As a forecast develops, it estimates how possible noise changes will affect later forecast accuracy and reliability. It combines these predictions to make small noise updates at each step. This loop avoids retraining the weather model and full backpropagation through the forecast. We evaluate DIAL on FourCastNet 3 (FCN3) using later ERA5 years unseen during training. DIAL provides better scale-resolved reliability than learned postprocessing and reward-based control baselines. Relative to the unmodified Native FCN3 reference, DIAL achieves an 8.27% improvement in the primary multiscale continuous ranked probability score (CRPS).

cs.CV↗
arXiv2026

REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. Distillation and latent communication typically require target-model training or access to source-model internals. We study how textual frontier-model trajectories can provide reusable local controls for a frozen agent. Inspired by protocol reverse engineering, we introduce $\textit{Agentic Latents}$, comprising anchored states and dynamic profiles of feedback--response cycles elicited by replay in the target model. Our training-free framework, $\textbf{REVEAL}$ ($\textbf{REV}$erse $\textbf{E}$ngineering $\textbf{A}$gentic $\textbf{L}$atents), uses these profiles and trajectory outcomes to match and select local events from successful and failed rollouts of the same task and source model. Their response-transition contrasts yield a target-specific steering direction, applied before each response. Within-benchmark evaluations on Terminal-Bench 2.1 and Humanity's Last Exam with tools report higher accuracy than unmodified agents across three targets. Representation analyses and behavioral case studies support reusing frontier-model experience as local activation control.

cs.AI↗
arXiv2026

Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications

System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution. However, this paradigm introduces a new security risk, which we term Jev Program Decision Hijacking (JPDH): attacker-controlled contexts can redirect program decisions through schema-valid Jev judgments. Existing evaluations focus primarily on model-level attacks or predefined injection channels, leaving attack reachability and downstream security consequences in real-world Jev applications underexplored. In this paper, we present JevProbe, the first automated framework to evaluate JPDH by tracing adversarial influence from reachable context surfaces through program-consumed decisions to downstream security consequences in real-world Jev applications. Our key insight is that application logic maps diverse Jev judgments to observable decisions, enabling systematic, program-grounded attack evaluation. Across 228 popular real-world Jev applications and 2,273 test cases, 81.5% exhibit decision flips, of which 98.6% lead to potential downstream security impacts. Compared with the strongest adapted baseline, JevProbe improves macro-average Decision Flip Rate (DFR) by 50.4 percentage points, while existing defenses offer limited protection. We further construct JevProbeBench to support systematic evaluation of JPDH in real-world Jev applications. We have responsibly disclosed our findings to Jev application maintainers, pending their responses. The source code of JevProbe and the JevProbeBench dataset are publicly available on GitHub (https://github.com/xiaoxiaohg8d/JevProbe-).

cs.CR↗
arXiv2026

SURE-EVAL: A Systematic and Unified Agentic Framework for Reproducible Evaluation

Audio and speech models are released rapidly, but reported scores often conflate model capability with deployment and evaluation choices. The same checkpoint can produce different predictions under different runtimes, hardware, decoding settings, or fallback policies. Even fixed predictions can receive different scores under different normalization and metric implementations. Existing speech benchmarks standardize selected datasets or scoring procedures, but rarely connect heterogeneous model onboarding, controlled inference, and versioned scoring in one executable workflow. We introduce SURE-EVAL, a Systematic and Unified Agentic framework for Reproducible Evaluation of audio and speech systems. A Tool Agent Workflow converts model releases into isolated, verified callable tools. A Main Agent Workflow commits task-specific inference and scoring protocols, then delegates all score-bearing operations to versioned deterministic programs. Each result retains its runtime, protocol, pipeline nodes, predictions, and audit artifacts. Across 18 public releases covering automatic speech recognition, text-to-speech, voice conversion, speaker diarization, speaker-attributed recognition, and multi-task audio understanding, a Codex-only baseline completes 12 models in one shot, while the same agent with the SURE-EVAL Tool Agent Workflow completes all 18. We also conduct unified evaluations over seven ASR test conditions and two TTS subsets. A protocol analysis of three TTS systems finds absolute differences of 0.02-0.52 points between paper-reported and unified results, with the direction varying by model and language. These results show that reproducible evaluation requires controlling both model execution and output scoring.

eess.AS↗
arXiv2026

CogEvol: Towards Efficient and Reliable Learning Environment Generation

We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or self-contained interactive HTML pages) in a single pass. Across 220k production requests, CogEvol completes a slide in a median of 17 seconds and an interactive page in 59, replacing minutes-long multi-turn agent scaffolding. Reliability is enforced rather than hoped for: a production-grounded data pipeline turns real failures into 53,687 verified SFT samples, and a hybrid rule-plus-VLM reward drives GRPO-based RL, hardened after we caught and fixed a reward-hacking episode that produced visually convincing but unplayable games. CogEvol-27B scores 83.7 on slide quality and 63.7 on a 500-case interactive-HTML benchmark with 26.9x fewer parameters than flagship coding models, and, in collaboration with the OpenMAIC team, serves their live production traffic. CogEvol-4B is released openly under the Apache 2.0 license at https://github.com/CogEvol/CogEvol-4B; external flagships are measured on the same suites under the identical harness. Scaffold editing cuts interactive-page generation cost by a further ~76%, and the full stack runs on domestic Ascend accelerators at application-level parity with A800 GPUs, lowering the unit cost of AI-native education at scale.

cs.CL↗
arXiv2026

AutoDRI: Bridging the Semantic Gap for Automated Design Rule Integration in CP-SAT-Based Cell Synthesis under Multi-Patterning

Design-rule integration (DRI) remains a major bottleneck for scalable (Constraint Programming with SAT) CP-SAT-based standard cell synthesis and rapid technology enablement at advanced nodes. It still depends heavily on manual effort and domain expertise. Moreover, existing low-level rule encodings are not expressive enough for emerging constraints such as cut-based rules under multi-patterning technology. This paper presents \textbf{AutoDRI}, a multi-agent framework for automated design-rule integration in standard cell synthesis. AutoDRI combines a geometric semantic library, a standardized conflict-set encoding, a constructive multicolor-cut modeling method, and a feedback-driven multi-agent flow to bridge the semantic gap between natural-language design rules and executable CP-SAT constraints. In the reported experiments, AutoDRI achieves near-perfect rule-integration correctness across 41 cell benchmarks under 10+ complex rules, including colored cut-mask spacing rules, reaching 33/33 correct integrations with Gemini-3-pro and 32/33 with GPT-5.4, while maintaining runtime comparable to manual hard-coding and passing KLayout DRC and Cadence LVS.

eess.SY↗
arXiv2026

The Illusion of $\textit{What If}$: Evaluating the Breakdown of Counterfactual Reasoning in LLMs

Counterfactual reasoning requires models to reason beyond the observed world and explain how altered conditions propagate through downstream consequences. Existing benchmarks largely target bounded settings with fixed variables or single gold outcomes, overlooking open-domain scenarios requiring causal-process evaluation. To this end, we present $\textbf{WhatIfBench}$, a diagnostic benchmark for open-domain, open-form, long-horizon counterfactual causal reasoning, containing 220 what-if questions across STEM, HSS, and Hybrid scenarios. To evaluate free-form responses, we further propose $\textbf{PRISM}$, which first converts each natural-language explanation into a Response-Derived Semantic Causal Graph of events, states, and mechanisms. On top of this graph, PRISM then jointly applies a Process Metric assessing graph-level causal validity and a Rubric Metric assessing answer-level explanatory adequacy. Evaluating six frontier LLMs with this framework, we find that WhatIfBench remains far from saturated: even the strongest model reaches only a 64.62% final score. Further analysis reveals persistent causal gaps, premise drift, and topology fragmentation, suggesting that fluent counterfactual narratives often mask fragile causal processes. The benchmark, code, and evaluation scripts are available at $\href{https://github.com/zju-gt/WhatIfBench}{WhatIfBench}$.

cs.AI↗
arXiv2026

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment

Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks. However, their performance remains constrained by two fundamental challenges: the inherent heterogeneity of temporal patterns and the modality gap between continuous numerical signals and discrete language representations. In this work, we propose \textbf{TALON} (Temporal-heterogeneity And Language-Oriented Network), a unified framework that enhances LLM-based forecasting by modeling temporal heterogeneity and promoting representation alignment. Specifically, we design a Heterogeneous Temporal Encoder that partitions multivariate time series into structurally coherent segments, enabling localized expert modeling across diverse temporal patterns. To bridge the modality gap, we introduce a Representation Alignment Module that projects temporal features toward LLM-compatible representations, making time series more amenable to LLMs and thereby unlocking their modeling potential, while eliminating the need for handcrafted prompts during inference. Extensive experiments on seven real-world benchmarks demonstrate that TALON achieves superior performance across all datasets, with average MSE improvements of up to 11% over recent state-of-the-art methods, while maintaining higher efficiency. These results underscore the effectiveness of incorporating both pattern-aware modeling and representation-level alignment when adapting LLMs for time series forecasting. The code is available at: https://github.com/syrGitHub/TALON.

cs.CL↗
arXiv2026

Unified Symmetry Classification of Many-Body Localized Phases

The Altland--Zirnbauer (AZ) tenfold way classifies disordered non-interacting systems by symmetry, but a unified symmetry classification of interacting many-body localized (MBL) phases has been lacking. Here we develop such a classification directly from the emergent local integrals of motion (LIOMs). Our scheme rests on two complementary criteria: whether a symmetry is compatible with a complete LIOM algebra, and whether it enforces many-body degeneracies. These criteria partition MBL phases into stable, fragile, symmetry-protected topological, and unstable classes, and unify AZ classes, onsite Abelian symmetries, and continuous non-Abelian symmetries within a single operator-algebraic framework. Our results provide a systematic foundation for understanding how symmetry constrains the stability and structure of MBL phases.

cond-mat.dis-nn↗
arXiv2026

A General Strategy for Realizing Mpemba Effects in Open Quantum Systems

The Mpemba effect, where a state farther from equilibrium relaxes faster than one closer to it, is a striking phenomenon in both classical and quantum systems. In open quantum systems, however, the quantum Mpemba effect (QME) typically occurs only for specifically chosen initial states, which limits its universality. Here we present a general and experimentally feasible strategy to realize both QME and anti-QME. By applying a temporary bond-dissipation quench, we selectively suppresses or enhances slow relaxation modes, thereby reshaping relaxation pathways independently of both the system and the initial state. We demonstrate this mechanism in systems with dephasing and boundary dissipation, and outline feasible cold-atom implementations. Our results establish controllable dissipation as a versatile tool for quantum control, accelerated relaxation, and efficient nonequilibrium protocols.

quant-ph↗
arXiv2026

Living-Harness Is an Interactive-Agent Evolver

Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions. Static harnesses improve reliability through fixed tools, context, memory, and workflow structures, but remain unchanged after deployment. We propose $\textbf{Living-Harness}$, a self-evolving agent harness that converts each completed trajectory and its evaluator signals into posterior evidence for bounded harness updates. Guided by a domain-level $\textbf{Evolution-SOP}$ ($\textbf{S}$tandard $\textbf{O}$perating $\textbf{P}$rocedure), Living-Harness extracts an episode abstraction and structured update evidence, and writes two complementary forms of procedural knowledge: episodic memory that records trigger conditions, failure patterns, and recovery actions, and a state graph that records state nodes, repair edges, and transition rules. The updated harness state is retrieved to guide future interactions, while tools and base context remain frozen, allowing procedural repairs to accumulate across evolution cycles. On eight interactive environments derived from $τ^2$-Bench and MultiWOZ-2.4, Living-Harness improves average Pass@1 over the strongest interactive baseline by 10.07 and 9.91 percentage points, respectively, and supports retrieval-only reuse of the evolved harness state across model backbones. Our code will be made publicly available soon at https://github.com/anotherbricki/Living-Harness.

cs.MA↗
arXiv2026

CARE: Confidence-Aware Reasoning for Reliable Medical VQA

Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these models suffer from $\textit{confidence miscalibration}$---a systematic gap between expressed certainty and actual diagnostic accuracy that undermines clinical trust. We propose $\textbf{CARE}$, a $\textbf{C}$onfidence-$\textbf{A}$ware medical $\textbf{RE}$asoning framework that jointly optimizes accuracy and calibration through a dual-stage pipeline. First, a scalable Medical-CoT synthesis provides structured cold-start data for Supervised Fine-Tuning. Second, Group Relative Policy Optimization (GRPO) with a novel $\textbf{Confidence-Aware Reward (CAR)}$ mechanism ties the model's confidence to diagnostic correctness within the reward signal. Across three Medical VQA benchmarks, $\textbf{CARE}$ achieves the highest diagnostic accuracy while obtaining the lowest Expected Calibration Error and Hallucination Rate, establishing a foundation for trustworthy clinical decision support. Our code is available at https://github.com/anotherbricki/CARE.

cs.CV↗