Searcharxiv⌕ Search

arXiv subjects

Jie Liu

Publications and source records attributed to Jie Liu.

At least 19 recordsLinked to original sources
arXiv2026

CoLink: Global Compression and Knowledge Linking for Multi-Turn Dialogue Modeling

Extracting salient information from long-horizon dialogue histories remains a significant challenge for Large Language Models (LLMs) due to the restricted context windows and efficient retrieval challenges. Current methods typically rely on history organization or local token-level optimization, suffering from information loss, retrieval redundancy, and myopic attention. Inspired by the view in cognitive science that dialogue constitutes sense-making and memory association, we propose CoLink, a framework that enhances LLMs' global context awareness in domain-specific multi-turn dialogues through information linking and compression. CoLink first clusters historical contexts into topic graphs to establish cross-semantic associations with external knowledge. Guided by the adaptive control of thought, it then retrieves and activates knowledge via synergizing semantic relevance and graph-structural topology. Crucially, to achieve effective compression of history and knowledge, we ground multi-turn dialogues in information theory and derive a principled optimization objective for extracting the core sense-making information. Coupled with a competitive slot mechanism, CoLink condenses the global context into dedicated memory and knowledge slots, efficiently distilling lengthy, redundant inputs into an extremely compact latent representation. Extensive empirical results on both public and our MMD datasets validate CoLink's superiority and generalizability in knowledge linking and sense modeling.

cs.CL↗
arXiv2026

Field misalignment effect on the in-plane magnetoresistance in the high-temperature superconductor FeSe/SrTiO3

The azimuthal angular dependence of the in-plane magnetoresistance provides a powerful probe for detecting rotational symmetry breaking in superconductors, which has significant implications for understanding the superconducting pairing symmetry and the intertwined orders. However, in two-dimensional or layered superconductors with strong anisotropy between in-plane and out-of-plane critical fields, measuring the in-plane magnetoresistance is particularly challenging as it is extremely sensitive to the field misalignment. Here we perform systematic electrical transport measurements on ultrathin FeSe films grown on SrTiO3 substrates. By remounting the same FeSe film to change the field misalignment, two qualitatively different angular dependences of the in-plane magnetoresistance are observed in the superconducting transition region, indicating the extreme sensitivity of the measurement to field misalignment. The observed anisotropic in-plane magnetoresistance can be well captured by our geometric model considering the field misalignment effect. Our work provides a practical framework for disentangling the misalignment effect and investigating the in-plane rotational symmetry breaking in two-dimensional or layered superconductors.

cond-mat.supr-con↗
arXiv2026

IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation

In wireless sensor networks (WSNs), data augmentation is a novel method to improve sampling-frequency decision performance, thereby enabling energy optimization for IoT (Internet of Things) sensors. However, existing methods rely on a single generator and empirically determined quantities, failing to establish a mapping between dynamic information gaps and multiple generators, and overlooking the heterogeneity of generated samples. Moreover, an evaluation and a closed-loop method that jointly consider the information gap and the model performance are lacking. To address these issues, we propose an information gap-guided IoT sensor automatic data augmentation framework (IGADA-IoT) with hierarchical multi-generator collaboration and scheduling over multiple rounds. Capabilities of different generators are jointly utilized to reduce the information gaps. In the IGADA-IoT, a hierarchical multi-generator collaboration and scheduling strategy (HMGCS) is proposed to enhance the targetedness and rationality of generated sample allocation. An information gap-model performance joint evaluation and closed-loop method (IGMP-EC) is proposed to enhance the accuracy of augmentation decisions, and to mitigate the risks of under-augmentation and over-augmentation. Experimental results show that the IGADA-IoT improves the average accuracy of multiple downstream models by 7.28%. Compared with advanced data augmentation methods, the average accuracy is improved by 8.90%. Compared with the individual generators, the average accuracy is improved by 7.63%. Furthermore, public IoT sensor datasets from the UCR Archive and real-world deployments demonstrate the accuracy and deployment feasibility of the proposed method.

cs.LG↗
arXiv2026

D2R2: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction

Predicting single-cell transcriptomic responses to genetic perturbations is central to functional genomics and virtual-cell modeling. Existing approaches, however, typically predict an entire expression profile as a whole, leaving the order in which individual gene responses are generated unmodeled. To address this problem, we introduce \textbf{$D^{2}R^{2}$} (\textbf{D}iscrete \textbf{D}iffusion with \textbf{R}egulation \textbf{R}einforcement), which reformulates perturbation prediction as regulation-guided gene-wise progressive generation. A Masked Discrete Diffusion Model represents expression as ordinal tokens and reconstructs a fully masked profile step by step, allowing generated gene responses to condition those that remain masked. A Regulatory Policy Module initializes the generation policy from a gene regulatory network inferred from control cells and adapts it to the perturbation and current partially generated state. Then, group-relative policy optimization refines only the ordering policy using final perturbation-effect agreement as reward. Across Norman19 and VCC-H1, $D^{2}R^{2}$ achieves the best performance on all five metrics on Norman19 and remains competitive on H1. Controlled ablations holding the generator and generation budget fixed show that biological-prior ordering improves over random ordering and is more reliable than uncertainty-based heuristics, whereas reversing the biological-prior ordering degrades every metric. Biological analyses further show that the refined policy prioritizes regulatory genes early while promoting perturbation-specific transcription factors and responsive genes. These results establish gene generation order as an effective, controllable, and biologically interpretable dimension of single-cell perturbation prediction.

cs.AI↗
arXiv2026

LoCA: Local Credit Assignment for Reinforcement Learning of Autoregressive Flow-Matching TTS

Reinforcement learning can improve text-to-speech synthesis through feedback on generated speech. However, sentence-level rewards do not identify local errors, while signed regression updates can lead to excessive fitting or repulsion of sampled outputs. We propose LoCA (Local Credit Assignment) for autoregressive flow-matching text-to-speech. LoCA uses ASR-based text alignment to locate content errors in generated speech and redistribute sentence-level advantages across acoustic frames. To improve training stability, we introduce reference-relative positive and negative thresholds that limit continued fitting and repulsion. Experiments on VoxCPM2 show that LoCA reduces sample-weighted content error on a multilingual CV3 evaluation subset by 20.5% and 14.3% relative to the pretrained backbone and GROW, respectively, while improving speaker similarity. LoCA also improves content accuracy on the Seed-TTS-Eval hard subset. Ablation results support the contributions of local credit and threshold-based regression control.

cs.SD↗
arXiv2026

HistoLoop: Iterative Contextual Inference with a Looped Transformer for Histology-Based Spatial Gene Expression Prediction

Predicting spatial gene expression from H&E images offers a scalable complement to experimental spatial transcriptomics. However, despite progress in spatial context modeling, how to construct subsequent context from spot states updated by earlier contextual interactions remains underexplored. We introduce HistoLoop, a looped Transformer that formulates prediction as iterative contextual inference. At each refinement step, HistoLoop aggregates the current spot states into context tokens at the corresponding resolution, processes them with a shared spatial Transformer, and retrieves spot-specific contextual information through cross-attention. A memory-mediated update integrates this information into persistent spot states, which are then used to construct context at the next, finer resolution. Under the HEST-Bench HVG50 evaluation protocol, HistoLoop achieves the highest macro-averaged gene-wise Pearson correlation among the compared methods across six cancer-specific tasks spanning five organs in HEST-1K. Ablation studies support the importance of recurrent state refinement and reconstructing context from updated spot states at progressively finer resolutions. Expression-derived clustering further suggests that HistoLoop better captures spatially organized multigene patterns.

cs.CV↗
arXiv2026

GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases

Retrieval over semi-structured knowledge bases (SKBs) must handle both textual descriptions and relational constraints. Text-based retrievers capture the overall semantics of a query but struggle with multi-hop relations, whereas graph-based retrievers follow relational paths precisely but miss the broader meaning. We propose GRASP, a hybrid retriever that learns to fuse the two. A small LLM planner translates the query into an executable graph plan in a single call, its graph ranking is fused with a text ranking, and a fine-tuned reranker reorders the fused candidates. Instead of training the planner to be accurate on its own, we optimize it with reinforcement learning to maximize the gain its graph ranking brings to the fused ranking. On three STaRK benchmarks, GRASP achieves the best results on all metrics, improving the average Hit@1 by 18.6 points over the strongest baseline, while taking only 2.47 seconds per query.

cs.IR↗
arXiv2026

KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a single terminal reward shared across an entire trajectory. Recent process-supervision methods aim to assign credit at finer granularity, but they typically anchor credit to either surface-level trajectory states or model-internal signals, both of which become unreliable in deep search where observations are heterogeneous and retrieved contexts are long and noisy. We propose KnowGPO, a reinforcement learning framework that aligns trajectories by the task-relevant knowledge they have acquired rather than by their surface observations. For each query, KnowGPO decomposes the information required to derive the answer into atomic knowledge conditions, and represents the state of a trajectory at each step by the subset of conditions it has satisfied. Trajectories sharing the same knowledge state are grouped for within-group comparison, and the incremental knowledge gain between consecutive steps serves as an environment-grounded process reward. Experiments on Xbench, BrowseComp-ZH, and GAIA show KnowGPO consistently outperforms outcome-only (GRPO) and process-supervision baselines (GiGPO, IGPO) by 3.8 to 4.2 points, with our 8B model rivaling or exceeding most 32B open-source systems.

cs.AI↗
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

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promis- ing alternative, yet they often treat reasoning as uniformly compressible, causing precision-critical intermediate steps to be overly compressed and thereby degrading reasoning accuracy. In this work, we propose Selective Latent Thinking (SLT), a reasoning paradigm that selectively compresses redundant reasoning spans into latent representations while preserving precision-critical spans as explicit CoT within the same reasoning trajectory. Our primary instantiation uses a lightweight decoder to anticipate a short upcoming reasoning span and applies confidence- based gating to determine the longest span that can be reliably compressed; the resulting selective compression policy is further optimized with trajectory-level reinforcement learning to balance answer correctness against reasoning cost. Ex- periments across four mathematical reasoning benchmarks show that which spans are compressed is critical: with the same compressor, compressing arbitrary spans reduces the GSM-Hard accuracy of Qwen3-4B from 54.7% to 17.3%, whereas keeping numerical tokens explicit retains 51.8%. SLT reduces explicit reasoning length by 58.4% with only a 2.8-point accuracy drop compared to explicit CoT on Llama-3.2-1B. Notably, the principle extends beyond this design: instantiated within existing latent reasoning models via a learned compression gate, it improves accuracy at equal reasoning length (+2.6 points over Latent-SFT) and at shorter length (+5.6 points over Latent-GRPO with 13% fewer tokens).

cs.CL↗
arXiv2026

Efficient Test-Time Adaptation through Latent Subspace Coefficients Search

Real-world deployment often exposes vision models to distribution shifts, making test-time adaptation (TTA) important for reliable prediction. Existing TTA methods can be difficult to deploy on edge devices because they require backpropagation, activation storage, or test-time batches, which increase computation, memory, and state. We propose \textbf{ELaTTA} (\textit{Efficient Latent Test-Time Adaptation}), a forward-only, gradient-free framework for single-instance TTA. ELaTTA freezes the pretrained model and adapts each test input by searching a low-dimensional coefficient vector in a principal latent subspace computed offline from a source-domain cache. The basis is stored once and source data are discarded before deployment. At test time, CMA-ES performs covariance-adaptive Gaussian search, ranks candidate corrections by prediction entropy, and selects the best candidate within a fixed evaluation budget. On five visual benchmarks spanning corruption, natural, rendition, sketch, and cross-domain shifts, ELaTTA provides strong accuracy under strict and continual single-instance protocols. In the strict single-instance comparison, MEMO requires \emph{64.7$\times$} the computation and \emph{12.4$\times$} the peak memory of ELaTTA. A complementary keyword-spotting experiment shows that the same coefficient-search design transfers beyond vision. We further demonstrate ViT-Base adaptation on a Raspberry Pi 5, confirming the feasibility of deploying ELaTTA on an edge device.

cs.LG↗
arXiv2026

SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation

Humanoid foundation models are advancing faster than we can evaluate them. While real-world testing is expensive and difficult to reproduce, existing simulation benchmarks focus primarily on table-top or wheeled robots. A scalable and reproducible benchmark for whole-body humanoid loco-manipulation remains an open problem. To this end, we present SIMPLE, a unified simulation testbed for humanoid policy learning and evaluation. SIMPLE couples the accurate contact-rich dynamics of MuJoCo with the photorealistic rendering of IsaacSim. It provides a large-scale environment comprising 16 diverse whole-body tasks, 50 indoor scenes, and over 1,000 object assets. To facilitate scalable data collection, the framework integrates two data generation pipelines: automated trajectory generation via motion planning and a low-latency VR teleoperation interface. We further integrate and benchmark mainstream humanoid policies at scale in SIMPLE, including lightweight imitation networks, large vision-language-action (VLA) models, and recent world action models (WAMs). Our experiments reveal a strong correlation between policy performance in simulation and the real world. Furthermore, we demonstrate that policies trained on data collected in SIMPLE can be transferred zero-shot to physical humanoid robots under similar settings, providing a robust and reproducible foundation for humanoid robotics research.

cs.RO↗
arXiv2026

KV-Skill: Forging Expertise in the Model's Native Language

Task knowledge is commonly stored either as text in the prompt or as an update to model weights. Text is modular but must be interpreted on every use, while weight adaptation makes the resulting capability difficult to load, remove, or share independently. We introduce KV-Skill, a design space of external factorized operators that a frozen language model reads through a lightweight interface. KV-Skill supports two complementary paths. Registration converts an authored text skill into a text-derived operator and trains a shared per-backbone interface. Reward learning develops a compact latent operator directly from task outcomes, with or without an authored skill. Neither path adds positions to the prompt. Across ten benchmarks and four backbones from three model families, converting text to a KV-Skill consistently makes the same procedural knowledge more effective on mathematical reasoning and retrieval tasks. On Qwen3.5-4B LiveMath, registration reaches 77.2 accuracy, compared with 52.0 for the same skill as text (SkillOpt) and 64.5 for SoftSkill. Under matched reward training and parameter budgets, KV-Skill gives the best result in seven of eight matched settings against soft prefixes, prefix tuning, and LoRA. A post-hoc rank analysis further shows that text-derived operators retain nearly all of their benefit with one task-aligned direction per injection layer, while matched random directions fail. Finally, a single shared interface serves eleven diverse skills at once with no loss in average accuracy. These results show that task knowledge can be acquired from text or experience, compressed into an external operator, and deployed separately from the backbone. Code is available at: https://github.com/shawnzhg/KV-Skill

cs.LG↗
arXiv2026

Nonequilibrium framework for first-order phase transitions

The first-order phase transition is central to electroweak baryogenesis and gravitational wave generation, yet thermal equilibrium effective potential analyses cannot describe the real-time non-equilibrium dynamics of the phase transition process. We use the Schwinger-Keldysh closed-time-path formalism of real-time finite-temperature field theory to study these effects. For the $ϕ^6$ model, we derive the effective action and the corresponding Langevin equation. We further extend the formalism to the two scalar fields case, obtaining the coupled Langevin equations. These results provide a theoretical framework for the bubble nucleation simulation of the non-equilibrium phase transition process, laying the foundation for reliable predictions of baryogenesis and gravitational wave signals.

hep-ph↗
arXiv2026

UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation

Enterprise data agents must preserve organization specific semantics, not just translate questions into queries. We present ChinaUnicom DataAgent (UniDataAgent), an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution. Ontology Acquisition and Validation stage (OAV) builds versioned enterprise ontologies from metadata, business knowledge, and supporting materials through expert authored business skills, constrained generation, question verification, and selected expert review. Question-to-Report Execution (QRE) stage retrieves semantic contracts for each question, coordinates skills and data tools, validates results, and produces evidence linked reports. Across 27 enterprise tables and roughly thousands of metric types, ontology construction took a few hours instead of about one week manually. It took just a few minutes to generate the reports, instead of several working days. Ontology grounding achieved 95.0\% strict accuracy on real business questions, versus 72.5\% for document RAG, especially on structured and compositional tasks. The system has already been deployed to generate cost savings and has the potential to be replicated in other enterprises.

cs.CL↗
arXiv2026

Asymptotic Safety in Gauge Theories beyond Four Dimensions: Perturbative Tests and Fixed-Point Mergers

Non-Abelian gauge theories above four dimensions may admit an interacting ultraviolet fixed point through the competition between canonical scaling and gauge-field antiscreening. Using the four-loop $\overline{\mathrm{MS}}$ beta function continued to $D=4+2ε$, we determine the largest dimension $D_{\mathrm{pt}}=4+2ε_{\mathrm{pt}}$ below which successive loop corrections to the fixed point remain hierarchically ordered under a specified ratio criterion, and map $D_{\mathrm{pt}}$ over color and flavor numbers for fermions in the fundamental representation of $SU(N)$. At $D=5$, we construct rational anomalous dimensions with a fixed, pole-regularized denominator inspired by the functional renormalization group (fRG). Matching to the $\overline{\mathrm{MS}}$ series through one, two, and three loops produces progressively smaller shifts in the critical flavor number and coupling at the ultraviolet--infrared merger (the point where the infrared and ultraviolet fixed points coincide), yielding $N_f^{\mathrm{cr}}\simeq 2.09 \, N$ at large $N$ in the three-loop construction. This low-order stabilization, together with qualitative evidence from fRG flows including higher gauge operators, suggests a potential merger scenario that bounds the candidate asymptotically safe region in flavor number. The resulting color--flavor map provides guidance for five-dimensional model building by displaying both the baseline perturbative-control boundary and the candidate three-loop merger boundary. Four-loop matching, however, retains an interacting ultraviolet fixed point beyond the three-loop merger boundary, with no merger found for integer $2\le N\le15$ and $0\le N_f/N\le11/2$. The sensitivity of the fixed-point structure to higher-order terms leaves both scenarios open, highlighting fixed-point annihilation as a potential constraint on five-dimensional asymptotic safety.

hep-th↗
arXiv2026

Accurate Molecular Property Regression Using Simple Fusion of Complementary Classical and Graph Predictors

Accurate prediction of continuous molecular properties supports chemical discovery and design. Many recent approaches combine multiple molecular representations within increasingly complex neural architectures, aiming to achieve higher accuracy. However, classical machine-learning models remain competitive when trained on chemically meaningful molecular representations. We therefore constructed a chemistry-guided classical branch from Morgan fingerprints, RDKit molecular descriptors, and conformer-derived geometric features selected to provide complementary views of molecular structure. We combined four tree learners trained on these representations with a CoMPT graph predictor and integrated their out-of-fold predictions using Ridge regression. Across ESOL, FreeSolv, and Lipophilicity datasets, the fused model achieved lower mean root-mean-square error (RMSE) than Chemprop and competitive graph and multimodal methods, including CoMPT, MoleSG, KFLM2, and MCMPP. After retraining on the separately curated AqSolDB dataset, the same approach, without redesign or retuning, reduced mean absolute error (MAE) relative to the classical ensemble and achieved lower mean MAE than Chemprop. These results show that accurate and transferable molecular property regression does not necessarily require a complex joint multimodal architecture: classical learning remains competitive when chemical insight guides the choice of molecular representations, and a graph model can add complementary information through simple prediction-level fusion.

physics.chem-ph↗
arXiv2026

Programmatic Search Agents: Extending Agentic Search Beyond Query Reformulation

Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control. Our trajectory analysis shows that supporting passages can be retrieved yet never delivered to the agent; a same-page oracle intervention shows that changing the returned evidence can reduce subsequent search. We introduce Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action. PSA unifies a persistent candidate workspace, flexible primitive composition, and selective evidence presentation. It incrementally generates program cells that reuse candidates, execute dependent operations, and select what the agent inspects next. The runtime resolves specified data dependencies within each cell, while the agent adapts its search strategy across cells as new evidence arrives. We compare PSA with the Query-based Agent and Tool-based Agent on InfoSeek-Eval and BrowseComp-Plus using five policy backbones without task-specific training. All three interfaces share the search substrate, and the Tool-based Agent also shares PSA's primitives and persistent workspace. Relative to the Query-based Agent, PSA improves macro-averaged task success by 4.00 and 7.56 percentage points on the two benchmarks, respectively; within-backbone reductions in final-step tokens average 28.3% and 33.9%. These results support extending agent control beyond query reformulation to the processing and presentation of retrieved evidence. Code will be released subject to approval.

cs.CL↗