Search arXiv⌕ Search

arXiv subjects

Xiaoyang Li

Publications and source records attributed to Xiaoyang Li.

At least 19 recordsLinked to original sources
arXiv2026

EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts

With the rise of Group Agent such as Claude Tag, agents increasingly serve as digital workers for long-term team collaboration. These agents operate over shared contexts that continuously accumulate through multi-user interactions. However, existing agent memory systems are mainly designed for individual users and struggle to capture group-level knowledge in shared contexts, including group relationships and collaboratively formed knowledge. Manual memory strategies further limit adaptation to diverse and evolving shared contexts. To this end, we propose \textbf{EvoGroup (EvoG)}, a self-evolving harness for group agents that starts from a minimal six-tool cold start and adapts through interaction with shared context. EvoG uses confidence and task outcomes to select informative trajectories, while also eliciting self-reflections on uncertainty in low-confidence cases. The analysis agent then examines selected trajectories through adaptive progressive disclosure, followed by bucketed analysis to synthesize high-level findings that guide the evolve agent in revising the Harness. Empirically, pass@1 on held-out split of EverMemBench improves from 71.07\% to 89.58\%, surpassing both self-evolving memory and human-designed harnesses, including Claude Code (85.83\%). To evaluate generalization, we freeze the evolved harness and evaluate it on the unseen GroupMemBench, where, with GPT-5.5, it demonstrates effective generalization and outperforms both memory baselines and human-designed harnesses.

cs.CL↗
arXiv2026

Are Textual Residuals Truly Complementary? Learning Visual Complements under Semantic Superposition for Visible-Infrared Person Re-Identification

Text-enhanced visible-infrared person re-identification (VI-ReID) exploits textual descriptions to compensate for appearance cues that are weak or unavailable under infrared imaging. Existing methods construct compensation from differences between modality-oriented textual representations, implicitly assuming that textual differences are visually complementary. We revisit this assumption through semantic superposition and show that dense textual residuals may entangle useful appearance variations with redundant, making direct residual fusion unreliable. We propose Superposition-Aware Residual Calibration, which transforms dense textual differences into selective and visually grounded complements. Low-Interference Sparse Residual Learning represents modality-oriented text embeddings as sparse activation strengths over a shared dictionary, selects positive strength differences, and suppresses both dictionary-level overlap and activation-weighted interference to reconstruct a compact, selectively controlled residual. Visual Complement and Counterfactual Calibration further calibrates the residual against identity-specific RGB-IR visual discrepancies, encouraging retained semantics to provide meaningful compensation while preserving the residual structure. Experiments on Tri-SYSU-MM01, Tri-RegDB, and Tri-LLCM show that SARC consistently improves the VI-ReID backbone and remains competitive with text-assisted methods. Mechanism analyses show that SARC produces more concentrated textual variations, reduces dictionary-level feature interference, and improves residual-visual-complement alignment for most samples. These results demonstrate that effective cross-modal compensation requires textual residuals to be selectively represented and explicitly calibrated, rather than directly treated as visual complements. Code and implementation details will be released upon publication.

cs.CV↗
arXiv2026

AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning

The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. State-dependent discounting is a natural way to adapt temporal credit assignment to local state structure, but naively learning a discount function inside deep actor--critic methods creates a self-referential target: the learned discount scales the same bootstrap term against which it is trained. Consequently, TD-error-based objectives can admit a degenerate shortcut, reducing target dependence on downstream value estimates instead of learning meaningful temporal structure. We propose \textbf{AdaGamma}, a practical framework for state-dependent discounting in deep actor--critic reinforcement learning. AdaGamma learns a bounded discount function \(γ_ϕ(s)\) and trains it using a return-consistency objective that matches a one-step adaptive bootstrap to a multi-step return computed with a lagged, stop-gradient reference discount. This removes the direct target manipulation path and encourages the discount to encode state-dependent value propagation. We analyze the Bellman operator induced by a fixed state-dependent discount in finite tabular MDPs, proving contraction, exact soft policy iteration, and Lipschitz sensitivity under standard boundedness assumptions. Empirically, AdaGamma integrates into SAC and PPO, avoids TD-collapse, improves continuous-control benchmarks, and achieves statistically significant gains in a four-week online A/B test on the JD Logistics platform.

cs.LG↗
arXiv2026

IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models

Open robot policies increasingly follow two paradigms: vision-language-action models (VLAs) directly map observations and instructions to actions, whereas world-action models (WAMs) incorporate learned video or world dynamics into policy learning or action generation. Although both target the same manipulation tasks and represent alternative design choices, they are commonly reported under different evaluation protocols, leaving their capability, robustness, language sensitivity, and deployment-cost trade-offs unclear. We present IndustrialVLA-Bench, an evidence-aware evaluation of six released VLA and WAM systems under a unified reporting schema. It separately evaluates clean capability on LIBERO, non-language robustness on LIBERO-Plus, instruction sensitivity on LIBERO-Para, and observed execution cost. Reported task scores aggregate three complete evaluations with distinct random seeds under a fixed checkpoint and inference configuration. Across all six systems, clean LIBERO averages differ by only 1.58 points, whereas robustness and paraphrase summaries span 14.62 and 31.08 points. Restricting every comparison to the three protocol-faithful systems preserves the effect (1.36, 14.62 and 23.10 points), so the diagnostic separation reported here does not depend on the weaker evidence tiers. We additionally report observed inference latency, peak memory, runtime mode, and an evidence status for every system. Protocol-faithful, near-reproduction, and pending-verification entries remain visibly separated; only protocol-faithful entries support strict comparisons. Rather than claiming universal superiority of either paradigm, IndustrialVLA-Bench provides traceable evidence for comparing released robot policies on shared practical criteria. Code and evaluation records are available at https://github.com/xiaoqi-7/IndustrialVLA-Bench.

cs.RO↗
arXiv2026

A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory

Evaluating claim admission in shared agent memory is challenging because repeated claims may be mistaken for independent evidence. An agent may copy or paraphrase a retrieved belief, while admitting a false claim exposes subsequent agents to it. To study this problem, we introduce the Correlated Promotion Benchmark (CPB), which evaluates whether candidate claims should be admitted to shared memory.CPB-Static constructs a frozen test split from publicly annotated sources with fixed gold actions. CPB-Live runs multi-agent teams over a shared store, records all writes and retrievals, and tracks source lineage defined by each scenario. A separate consumer answers from the store alone. We evaluate eight admission policies across four agent families. Our results show that policies which deduplicate sources reject many true claims alongside false ones, whereas policies preserving answer coverage admit nearly as many false claims as unrestricted sharing. Gating on declared source type reduces false adoption to 0.06--0.09, compared with 0.22--0.47 for other answering policies. Once an uncontested false belief enters memory, the consumer asserts it in 0.97--0.99 of probes across all families. No non-oracle policy consistently rejects false claims across verbatim copies, paraphrases, and paraphrases declared authoritative. These findings reveal the limitations of admission policies without access to source lineage.

cs.AI↗
arXiv2026

NSP: Accelerating Variable-Length LLM Training via Nested Sequence Parallelism

Long-context LLM training on long-tailed corpora faces a central communication--balance tradeoff. Such sequence-length heterogeneity makes any single sequence-parallelism (SP) degree a poor fit for the workload: a small degree leaves the few long sequences badly imbalanced, while a large degree forces the many short sequences that dominate the workload to pay excessive communication. Existing dynamic-SP systems mix SP degrees within a batch, but to run several groups at once they partition the GPUs into disjoint groups, which reintroduces imbalance across groups and forces costly micro-batch workarounds. We present NSP, a sequence-parallel training system that resolves this tradeoff by nesting differently sized SP groups on shared GPUs within a single training iteration. This lets long sequences use larger SP groups while keeping short sequences on smaller ones, so communication is incurred only where needed and load is balanced per GPU rather than per group. NSP realizes this idea with a tree-structured routing planner that assigns sequences under memory constraints and an executor that exploits the resulting hierarchy through inter-level phase streaming and tree-level recomputation. NSP supports common SP backends and requires no model changes. We evaluate NSP on Qwen3-MoE workloads with up to 384K-token contexts across multiple long-tail datasets on an internal production GPU cluster. Across these settings, NSP consistently improves end-to-end training throughput, outperforming Static SP by up to 1.48x and FlexSP by up to 1.16x.

cs.DC↗
arXiv2026

RFS-UNet: Decoder-Conditioned High-Resolution Skip Recalibration for Bone-Selective DRR Synthesis

Bone-selective synthesis from digitally reconstructed radiographs (DRRs) requires separating skeletal signal from overlying tissue while preserving anatomical detail. U-Net skip connections supply fine encoder features, but their transfer is independent of decoder context. We introduce RFS-UNet, which lets the decoder participate in high-resolution channel recalibration. Pooled encoder and decoder features jointly predict a bounded residual scale, initialized to preserve the original skip transfer. The module operates at the two finest resolutions and integrates directly into the backbone. On a rebuilt patient-unique cohort, RFS improves test PSNR over U-Net-64 by 0.10 dB. A three-seed comparison with encoder-only recalibration supports the contribution of decoder context. RFS also offers a lower-latency alternative to CBAM, with 2.25 times faster inference in matched profiling. Decoder-conditioned reuse thus improves bone-selective synthesis through a compact architectural change.

cs.CV↗
arXiv2026

Evaluator-Dependent Patient-Adaptive ECG Lead-Channel Allocation

The diagnostic value of an ECG channel depends on the model that interprets it. We test whether adaptive acquisition retains its advantage over fixed protocols when that model changes. Two policies developed with a logistic evaluator are frozen and assessed with a masked waveform ResNet1D, using exhaustive, metric-matched fixed comparators. On PTB-XL, replacing the evaluator reverses the mean adaptive advantage in negative log-likelihood and Brier score across the tested budgets, while calibration responds less uniformly. The shift persists with common fixed references and broader training-mask exposure. Training a policy against the stronger evaluator partly recovers the lost advantage. These retrospective exploratory results show that acquisition quality cannot be assessed independently of the downstream evaluator and motivate validating adaptive policies with the model intended for diagnosis.

cs.CV↗
arXiv2026

Branch Geometry and Finite-Radius Sensitivity of Hard-ReLU Training

Outer-learning algorithms use infinitesimal sensitivities to propose finite changes to initialization or training parameters. For hard-ReLU training, the derivative of the finite program and the derivative of its flow limit do not by themselves specify the response at a chosen radius. We characterize the intervening regime in which the perturbation radius is proportional to the GD step. Integer event rounding then survives at leading order: smooth Euler bias shifts each discrete phase, and upstream rounding moves downstream branch boundaries. We derive the crossing indices and a uniform endpoint expansion for finitely many separated transverse events in piecewise-$C^2$ dynamics, away from recursive phase boundaries. In contractive affine regions, an explicit remainder and complete branch verification certify finite candidate comparisons. Scalar phase frequencies and a coupled feedback ablation test the mechanism; frozen nonlinear-network experiments show radius-dependent prediction accuracy, including incomplete branch matches and failed-word tails. Together with local AD and uniform flow consistency, the result identifies sufficient response regimes: differentiating training is a choice of perturbation resolution as well as a choice of derivative.

cs.LG↗
arXiv2026

Exploring the Initial Performance of NB-IoT NTN over GEO: Measurement and Analysis

With the standardization of Non-Terrestrial Networks (NTN) to provide direct satellite connectivity to massive, low-power Internet of Things (IoT) devices, 3GPP IoT-NTN bridges the worlds of cellular and satellite communications. While holding great potential for global connectivity with IoT devices, there exist several concerns about the system performance of IoT-NTN over Geostationary Earth Orbit (GEO), which covers multiple dimensions such as end-to-end delay and energy consumption considering the ultra-long transmission distance from ground IoT terminals to GEO satellite. To answer these concerns, we have conducted the first comprehensive and in depth measurement for NB-IoT NTN over GEO. Based on real NB-IoT NTN testbeds including both Skylo and Tiantong, measurements covering more than six months confirm that the available implementation of NB-IoT NTN remains in the initial stage. Amplified by ultra-long Round-Trip Time (RTT) between ground IoT terminals and GEO satellite, there exists plenty of time and energy consumption during the access process. Interestingly, it also reveals that as an energy-saving mechanism, Power Saving Mode (PSM) fundamentally reshapes NB-IoT NTN traffic into a bursty and access-driven communication pattern and thus has a considerable influence on the end-to-end delay and energy consumption. Finally, we propose corresponding optimization schemes to reduce the delay and energy, which lays a good foundation for the implementation of NB-IoT NTN in the near future.

cs.NI↗
arXiv2026

Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding

We tested whether auditory-evoked EEG supports subject-independent five-vowel perception decoding when trial identity, model identity, prediction provenance, and participant-level inference are controlled within a single benchmark. We reconstructed Study 2 event tables from OpenNeuro ds006104 version 1.0.1 and analysed the consonant-vowel pair task. One-to-one marker-stimulus pairing yielded 3,840 independent trials; control-condition selection and artifact rejection retained 1,094 epochs from 16 participants and 61 EEG channels. Thirteen unique implementations were evaluated using leave-one-subject-out testing, with participant metrics reconstructed from 36,102 trial predictions across 33 complete prediction replicas. Random Forest was numerically highest at 21.474% balanced accuracy (95% participant-bootstrap interval, 19.526-23.482%; chance, 20%), but neither its participant-level tests nor any implementation survived correction across the 13-model family. Deep-model performance was close to chance, and several architectures showed substantial seed-dependent variation and low trial-label agreement. An exploratory MDM analysis comprising 9,616 genuine refits across training cohorts of 3-15 participants showed no monotonic performance gain. Within this dataset and protocol, evidence for reliable cross-subject five-vowel decoding is limited. The benchmark provides a reproducible chain from source rows to retained epochs, predictions, participant-level metrics, multiplicity-adjusted inference, and bounded diagnostic analyses.

eess.SP↗
arXiv2026

When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition

Task arithmetic composes skills by adding weight displacements, and merged models are then judged on benchmark suites. We measure when that composition is functionally additive, and find that the answer depends as much on how the model is prompted as on which tasks are merged. Across two-dimensional composition surfaces -- five model settings from 0.5B to 8B, two families, LoRA and full fine-tuning -- pairwise non-additivity is real, seed-stable, and transfers in coarse order to unseen task pairs: all eight preregistered sign predictions held. But it is input-conditioned everywhere we measured: the same merged model that shows a six-point interaction contrast on code prompts shows none on math prompts, and wrapping the identical code prompts in the instruction template the adapters were trained on collapses the contrast twenty-fold, from +6.9 to +0.3 points -- while re-serializing them in an untrained chat template leaves it intact (+12.5), falsifying our own preregistered prediction. Execution benchmarks (pass@1) inherit the training-format wrapper's blindness. Weight-space composition therefore supports coarse, input- and format-conditioned functional statements -- not a universal merging-performance predictor, and not one that training-format evaluations can see.

cs.LG↗
arXiv2026

SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data

Smartphone personal assistants reason over longitudinal personal data, yet evaluating them requires context-rich evaluation data whose correct answers are known, and real device traces are too privacy-sensitive to share. To address this challenge, we present SenWorld, a physically grounded, deterministic, event-sourced digital-twin simulation that generates such data with ground truth fixed by construction. In SenWorld, personas live through a full day in a world built from real map, weather, holiday, and network data; every observable signal is archived in full-system snapshots; and each evaluation case is labeled by a pointer to an existing record rather than by post-hoc annotation or a large language model (LLM) judge. We evaluate this method with 16 personas in Beijing. The generated data closely matches the held-out real-user benchmark in category distribution (Jensen--Shannon divergence (JSD) 0.070) and in the daily rhythm of communication records (JSD below 0.1), though generated records remain shorter than real ones. Without scripted interaction, personas form a fully reciprocated dialogue subgraph and differentiated behavioral repertoires. Projected into 717 evaluation cases, the generated data exposes 78 failures in a production smartphone assistant, concentrating on call and Short Message Service (SMS) records while contacts, schedules, and alarms never fail. The snapshot pointer confirms each failure as an assistant-side retrieval error, with no LLM judge involved. Overall, SenWorld offers a privacy-safe, reproducible, and distribution-checked path to evaluation data whose labels are fixed by construction.

cs.AI↗
arXiv2026

MemTX: Transactional Belief Commit for Stateful Agent Memory

LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current agent memory systems treat every accepted write as immediately actionable truth, so a polluted tool result, a stale update, or a teammate's half-finished note can silently drive an irreversible action. We argue that a memory write is not a belief commit. We present MemTX, a transactional belief-commit protocol. Each record carries evidence, permissions, provenance, and validity. Writes are staged inside snapshot-isolated transactions and admitted by a validate-and-commit pipeline, irreversible tool calls are gated on in-flight belief state, and retracting a belief triggers typed cascading repair of its derived records and tool side effects. Two invariants, action-safety gating and cascade-repair completeness, are machine-checked by property-based testing and bounded exhaustive enumeration of 5.5 million protocol states, with zero violations. Across five backbones from three model families, MemTX leads all eight baselines with paired-McNemar significance on four backbones and statistically ties the best baseline on the fifth and strongest, while remaining the only method with zero downstream harm on every backbone. Backbone capability does not substitute for commit discipline.

cs.AI↗
arXiv2026

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-scenario agentic scaling and present AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications. An extensible Domain x Capability x Atomic Difficulty taxonomy aligns these stages and enables fine-grained diagnosis with OmniaBench. AgentOmnia combines bidirectional environment-task synthesis with tool-dependency, program-structured, and solver-based pipelines, constructing 5,018 stateful environments with 255,375 tools and 52,361 tasks. Programs, solvers, and verifiers provide correctness signals, while supervised fine-tuning, online agentic reinforcement learning, and a rollback curriculum support post-training. Evaluation failures translate into Product Requirement Documents (PRDs) for targeted self-evolution. Starting from Qwen3-30B-A3B-Thinking-2507, AgentOmnia raises the pass rate on the OmniaBench challenging subset from 9.16% to 37.11% and the macro-average across OmniaBench, $τ^2$-Bench, DeepPlanning, and VitaBench from 22.86% to 41.69%. Under a unified protocol,it leads the evaluated agentic post-trained baselines on OmniaBench and retains the highest four-benchmark macro-average. It also surpasses Qwen3-235B-A22B-Thinking-2507 on all four benchmarks and exceeds Qwen3.5-35B-A3B on the macro-average. Gains span three application splits, ten capability dimensions, eight atomic-difficulty factors, and 76 of 90 level-1 domains, indicating broad rather than category-specific improvement. A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings.

cs.AI↗
arXiv2026

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. One vital cause is training-inference mismatch: LLM adopts separate inference and training engines for generation efficiency and training precision, which in practice exhibits inconsistent probabilities for the same trajectories on training and inference sides, even with synchronized model parameters. This naturally induces a special type of off-policyness ever existing and poisoning the training. Prior works have made various efforts in addressing the off-policyness to stabilize the training policies under the mismatch. In this paper, we point out the objective misalignment neglected by existing works that an effective update to the policy in the training engine not necessarily ensures the improvement of the inference policy, i.e., the one used in deployment. To this end, we propose a new policy optimization objective for LLM RL, named Monotonic Inference Policy Improvement (MIPI). Following this principle, we introduce Monotonic Inference Policy Update (MIPU), a two-step LLM RL framework that constructs sampler-referenced candidate updates and selectively accepts synchronized candidates using an inference-side gap proxy. Experiments conducted on two model scales under high mismatch show that MIPU improves average reasoning performance and training stability.

cs.LG↗
arXiv2026

Performance Analysis for Heterogeneous Air-Ground ISAC in Coordinated Multipoint Networks

The emergence of the \textit{low-altitude economy} (LAE) calls for highly integrated and reliable wireless systems that can simultaneously support \textit{communication and sensing} (C\&S) functions. Although \textit{integrated sensing and communication} (ISAC) has been widely studied, most existing works focused on link-level or single-cell architectures in terrestrial environments, leaving the potential of network-level cooperative air-ground ISAC largely unexplored. To bridge this gap, a heterogeneous air-ground ISAC network architecture based on \textit{coordinated multipoint} (CoMP) is proposed, which incorporates a cooperative hybrid mono/bi-static sensing scheme to enhance spatial diversity and sensing capability. In the proposed architecture, a two-tier \textit{base station} (BS) deployment is adopted: master BSs are arranged in a hexagonal lattice, while slave BSs follow a Poisson point process distribution. This structure concurrently supports communication for terrestrial users and sensing for aerial targets. A holistic performance analysis framework for both C\&S is further developed, accounting for key channel and network parameters. Simulation results reveal inherent trade-offs between C\&S performance, especially under multi-BS cooperation and varying network density. These findings provide practical guidance for the deployment of scalable and efficient ISAC networks in LAE scenarios.

cs.IT↗
arXiv2026

A Stochastic Hybrid Automaton for Smartphone Battery Dynamics: Electro-Thermal Coupling and First-Passage Time-to-Empty Estimation

Smartphone time-to-empty (TTE) is difficult to predict because shutdown is governed not only by remaining charge, but also by instantaneous power capability under temperature-, aging-, and load-dependent voltage sag. We develop a stochastic hybrid automaton for smartphone battery dynamics that couples a first-order Thevenin equivalent-circuit model with a lumped thermal model and a stochastic user-activity process. The continuous state includes state of charge, polarization voltage, and battery temperature; user behavior is represented as a piecewise deterministic Markov process switching among idle, social/web, video, gaming, and weak-signal modes. Shutdown is formulated as a first-passage event when terminal voltage crosses a cutoff threshold or when requested power exceeds the instantaneous feasibility envelope. The model captures a voltage-collapse mechanism that simple Coulomb-counting or linear discharge models miss: cold temperature or battery aging increases internal resistance, so high-power bursts can drive terminal voltage below cutoff even when substantial charge remains. Monte Carlo simulation yields a full TTE distribution rather than a single countdown, allowing lower-tail risk to be quantified by the 5th percentile. Sensitivity analysis identifies ambient temperature, internal resistance, weak-signal radio penalty, and screen brightness as major drivers of premature shutdown risk. These results motivate practical user guidance and an operating-system-level resistance-aware throttling policy that limits peak power in the power-limited regime. The framework provides a physically grounded, risk-aware approach for explaining and extending usable smartphone battery life under real-world uncertainty.

eess.SY↗