arXiv subjects

Jin Li

Publications and source records attributed to Jin Li.

At least 19 recordsLinked to original sources

arXiv2026

Cosmological Evolution of the Randall-Sundrum II Model with Running Vacuum: A Special Class of Solutions

In this work, we construct a novel cosmological framework by integrating the running vacuum model into the Randall-Sundrum II braneworld scenario. We derive a special class of analytical solutions in the model. Our investigation focuses on the complete evolutionary trajectory of the universe, with particular emphasis on the realization of primordial inflation and the evolution of cosmic entropy. We evaluate the model's viability across three scenarios: dust-dominated, radiation-dominated, and general perfect fluid-dominated universes. Our findings show that while the hybrid model is in principle capable of supporting inflation, producing enough e-fold number demands either severe fine-tuning of the parameter or unreasonably large (and thus physically unnatural) value of the parameter.

gr-qc↗

arXiv2026

One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning

While reinforcement learning has enabled LLM-based search agents to invoke external tools, existing methods train under fixed budgets and cannot adapt when constraints vary at deployment. We propose AnySearch, a framework that enables a single policy to perform budget-aware search under any budget constraint through a training scaffold and curriculum reinforcement learning. In the first phase, we train the agent with explicit budget state injection and structured reasoning prompts that guide efficient allocation under linearly decaying budgets. In the second phase, the scaffold is removed and the agent learns to operate autonomously under adaptively sampled budget constraints, matching inference conditions. Both phases are optimized with a composite reward that couples answer accuracy with budget efficiency through absolute and relative signals, where an adaptive weight amplifies the efficiency signal for high-accuracy queries and attenuates it for low-accuracy ones. Extensive experiments on seven general and multi-hop QA benchmarks show that our method outperforms baselines across all budget scales, generalizes to unseen constraints beyond the training range, and achieves superior tool productivity without excessive token overhead. Our code is available at https://github.com/xwsun01/AnySearch.

cs.AI↗

arXiv2026

Constraining AGN Disk Properties with Gravitational Waves from Inspiraling Stellar-Mass Binary Black Holes in Hierarchical Triple Systems

Space-based gravitational-wave detectors can observe stellar-mass binary black holes (BBHs) long before merger, allowing weak environmental perturbations to accumulate. For binaries embedded in active galactic nucleus (AGN) disks, the local gas density characterizes the environment of the supermassive black hole (SMBH) and compact-object migration. We study whether such signals can constrain this density when a stellar-mass BBH orbits a Kerr SMBH. We evolve the outer orbit with relativistic corrections and gaseous dynamical friction (DF), and construct the detector-frame waveform including BBH inspiral, de Sitter precession, DF phase correction, and moving-source effects. Using Fisher-matrix calculations for sampled systems, we estimate statistical uncertainties and systematic errors. Larger gas densities generally improve the statistical precision of several source and outer-orbit parameters, but also increase systematic errors when DF is omitted. For favorable GW190521-like systems observed by LISA for one year, the disk density can be constrained at the level of $\sigma_{\rho}\sim10^{-12}\text{--}10^{-10}\,{\rm g\,cm^{-3}}$. Such constraints would connect BBH merger environments to the gas structure of galactic nuclei and the conditions that support black hole growth. These results indicate that hierarchical BBH inspirals can probe AGN disk environments, provided that gas effects are modeled consistently.

gr-qc↗

arXiv2026

Phonon-Localization-Driven Decoupling of Dual-Channel Transport for Record-Low Intrinsic Lattice Thermal Conductivity

A fundamental bottleneck in pushing the intrinsic lattice thermal conductivity of inorganic crystalline solids to its lowest limit arises from the inherent competition between the particle-like propagation ($\kappa_{\mathrm{L}}^{\mathrm{P}}$) and wave-like tunneling ($\kappa_{\mathrm{L}}^{\mathrm{C}}$) channels. Herein, we demonstrate that phonon localization provides a robust pathway to decouple the dual-channel transport, achieving record-low $\kappa_{\mathrm{L}}$ in quasi-1D ternary helical crystals. Despite the structural complexity leading to densely populated phonon branches and thus inducing abundant coherent phonons, the weak interchain interactions and heavy elements compress numerous branches into highly localized, nearly dispersionless flat bands. Such strong localization simultaneously suppresses both the diagonal and off-diagonal components of the group velocity, thereby synergistically suppressing $\kappa_{\mathrm{L}}^{\mathrm{P}}$ and $\kappa_{\mathrm{L}}^{\mathrm{C}}$. Taking InSeI as an example, the interchain room-temperature $\kappa_{\mathrm{L}}^{\mathrm{P}}$ and $\kappa_{\mathrm{L}}^{\mathrm{C}}$ are 0.145 and 0.053 W/mK, respectively, yielding an ultralow total $\kappa_{\mathrm{L}}$ of 0.198 W/mK. Weaker interchain interactions further drive the room-temperature $\kappa_{\mathrm{L}}$ of GaSeI and AlSeI to record lows of 0.086 and 0.089 W/mK, respectively; these values even drop to 0.058 and 0.059 W/mK at 900 K. These findings provide useful insights into exploring the thermal conductivity limit in crystals.

cond-mat.mtrl-sci↗

arXiv2026

Praxist: From Experimental Artifacts to Solution Lineages

Autonomous R\&D agents now write, run, and improve executable artifacts under automated evaluation---but largely as laboratory instruments: shown on curated benchmarks, with gains that are hard to trace to a cause and costs well above what sustained engineering practice absorbs. The limitation is structural. Most systems treat each attempt as nearly self-contained, so logs, memories, and search trees record what happened without establishing which design element produced an improvement, whether its evidence survived validation, or how it recombines with others. Long campaigns therefore keep re-learning the same lessons. We introduce Praxist, a lineage-centered generational system that converts reproducible artifacts and evaluator outcomes into a typed evidence graph of findings, lane-structured frontiers, and agendas. Separating local artifact construction from cohort-level evidence synthesis lets later attempts inherit validated mechanisms, unresolved claims, and useful constraints, and leaves results attached to an inspectable lineage. On the standardized 75-task MLE-bench suite, the finalized official-grader results give Praxist 60 medals (80.0\%), 49 of them gold, against 55 medals (73.3\%) and 34 gold for a Claude Code baseline on Claude Opus 4.8---at a recorded model spend of US\$3,054 versus US\$38,370, roughly a twelfth of the cost. Four case studies---quantitative trading, LiDAR-inertial-visual SLAM, tokamak magnetic control, and rocket landing---carry the same process into open-ended engineering problems, improving on each task-native baseline in headline accuracy, survival, or resource cost, with the discovery path on record. Stronger artifacts at an order of magnitude less spend, each backed by an auditable lineage, are, to our knowledge, first brought together here: the operating profile production research requires, not the one a benchmark demonstration establishes.

cs.MA↗

arXiv2026

CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception

Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven by benchmarks that evaluate end-to-end task success, these evaluations largely overlook two fundamental sources of difficulty in real web browsing: complex actions over rich user interfaces and visual perception of dynamically rendered content, especially in workflows that span multiple websites. We introduce CAP, a scalable benchmark for evaluating browser agents on cross-site, human-like web tasks that require non-trivial UI interactions and visual understanding. Specifically, we adopt a decomposition-and-recomposition pipeline that first abstracts each website into a structured site card capturing user-facing functions, complex execution operations, and perceptual requirements, and then recomposes these components into realistic cross-site workflows. Each task is therefore grounded in multiple specific operations on each website, enabling fine-grained diagnosis. Built on this framework, we construct 420 tasks across 108 real-world websites and 24 domains under careful quality control. Experiments on state-of-the-art browser agents using our verifiable agent-as-a-judge evaluation framework show low success rates and reveal that perception-heavy interactions remain a major bottleneck, exposing substantial gaps between current agents and real-world web browsing demands.

cs.AI↗

arXiv2026

UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling

Joint-Embedding Predictive Architectures (JEPAs) have emerged as a principled framework for self-supervised learning of world models in compact latent spaces, yet existing methods are fragmented: some predict masked parts of a single image in latent space (I-JEPA), others learn to predict global photometric transformations (Image World Models), while video-scale JEPAs predict future temporal states and are post-trained for action-conditioned planning (V-JEPA~2, DINO-World, DINO-WM). These objectives are treated as distinct recipes with separate encoders, predictors, and anti-collapse regularizers, hindering a single model from unifying image-level and video-level world modeling. We present UniJEPA, a unified JEPA that jointly learns photometric prediction (image-level transformations) and temporal prediction (video-level next-state dynamics) in one shared latent space. A single end-to-end objective, composed of a next-embedding prediction loss and a Gaussian regularizer, yields a provably anti-collapse encoder-predictor pair trainable from raw pixels without EMA, stop-gradient, or pre-trained encoders. We show that the same latent space supports controllable abstraction: photometric prediction learns invariant structure while temporal prediction learns equivariant dynamics. After action-conditioned post-training on offline trajectories, UniJEPA enables zero-shot planning by treating goal features as prediction targets. On image, video, and control benchmarks, UniJEPA matches or surpasses task-specific JEPAs while requiring a single loss hyperparameter, and plans up to tens of times faster than generative world models at comparable accuracy.

cs.CV↗

arXiv2026

Full analytic expressions of overlap reduction functions for anisotropies of the stochastic gravitational-wave background with pulsar timing arrays

Pulsar timing arrays (PTAs) have detected a stochastic gravitational-wave background (SGWB) in the nanohertz band, enabling tests of gravity and cosmology, as well as studies of supermassive black holes and early Universe physics. PTA data analysis relies on cross-correlating timing residuals, where overlap reduction functions (ORFs) critically determine sensitivity. Conventional ORF calculations using the short-wavelength approximation break down for the scalar longitudinal mode and cannot handle frequency dependence or anisotropies. This work rigorously derives the full response functions within an analytical cross-correlation framework. We reveal, for the first time, intrinsic symmetries and relations among anisotropic ORF integrals for all polarizations. By variable substitutions and coordinate rotations, we transform complex integrals into tractable forms, resolving divergences in vector and scalar longitudinal modes. Building on this, we establish a universal framework yielding fully analytical expressions for anisotropic ORFs to arbitrary order for all six modes. As a direct application, we give complete expressions up to l <= 5. This framework is free of approximations; its (0,0) component recovers the isotropic Hellings--Downs curve. Compared with numerical integration, our results offer broader applicability, faster computation, and higher precision, providing a valuable foundation for anisotropic sky mapping, polarization-mode separation, and new-physics searches with PTA data.

gr-qc↗

arXiv2026

Machine Learning-Guided Screening of Advantageous Solvents for Solid Polymer Electrolytes in Lithium Metal Batteries

Trace residual solvents in solid polymer electrolytes (SPEs) significantly affect electrolyte and interface properties, where optimal selection enhances ionic conductivity and transference numbers. However, solvent complexity hinders general screening methods. We establish a universal criterion linking electronic (HOMO, LUMO) and macroscopic properties (dielectric constant, dipole moment, polarizability) via machine learning on an approximately 10,000-solvent dataset from high-throughput DFT. Two solvents, N-methoxy-N-methyl-2,2,2-trifluoroacetamide and 2,2,2-trifluoro-N,N-dimethylacetamide, were identified. Experimental incorporation of trace N-methoxy-N-methyl-2,2,2-trifluoroacetamide into a poly(vinylidene fluoride-co-hexafluoropropylene) matrix achieves a 4.5 V window, 5.5x10^-4 S cm^-1 conductivity (30 C), and 0.78 Li+ transference number. The cell retains 86.7% capacity over 500 cycles (LiFePO4) and 98.7% after 200 cycles at 2C (LiNi0.9Co0.05Mn0.05O2), outperforming 2,2,2-trifluoro-N,N-dimethylacetamide, dimethylformamide, N-methyl-2-pyrrolidone, and dimethyl sulfoxide. This synergy enables balanced ion transport, wide stability, and cycling durability, advancing safer, high-energy lithium metal batteries. Our integrated approach establishes a solvent screening paradigm for rational SPE design, accelerating next-generation battery development.

cond-mat.mtrl-sci↗

arXiv2026

DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stated reasoning path diverges from the computation that actually produced the answer, undermining reliability in safety-critical applications. We present DiffuseAgent-MI, a self-evolving agent whose perceptual grounding is governed by a KL-minimal energy model over feature units, providing a distributional view of visual mechanistic interpretability. The agent learns an energy landscape that softly constrains generated samples to lie near the native prior conditioned on the chosen interpretable unit, closing the gap between the explanation and the internal representation. A verifier then supplies trajectory-level faithfulness rewards, and a repair branch re-conditions the energy when the verifier flags an unfaithful step. On GeoQA, SciVis, VQA-v2 and an in-house multimodal reasoning set, DiffuseAgent-MI improves accuracy by up to 5.1 points over prior self-evolving agents while more than doubling mutual-information faithfulness and human-interpretability agreement. Our analysis shows the energy term and the verifier are complementary: the former guarantees distributional faithfulness, the latter trajectory-level faithfulness, and only their combination closes both gaps.

cs.CV↗

arXiv2026

Qualitative Shadow Anomaly as a Smoking-gun Signature of Nonmetricity

In general relativity and its metric-formalism extensions, the innermost stable circular orbit and the photon ring of a charged black hole contract as the charge increases. In this paper, we discover a qualitative anomaly that violates this universal behavior, serving as a smoking-gun signature of geometric nonmetricity. By considering a minimal coupling between the bosonic field and the independent affine metric, we demonstrate that nonmetricity induces an effective geometric force that triggers a trajectory expansion of both massless and massive bosons with increasing black hole charge. This qualitative inversion directly imprints onto the black hole shadow, lifting the degeneracy between metric-affine gravity and general relativity. Using Eddington-inspired Born-Infeld gravity as a concrete implementation, we show that next-generation horizon-scale imaging can resolve this signature, probing a complementary high-energy window up to the $10^{5}_{~}\,\text{TeV}$ scale.

gr-qc↗

arXiv2026

Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models

A persistent interactive world model keeps its running state resident on the GPU that serves it: a multi-gigabyte attention cache, almost all of it rewritten at every generation step. That state cannot be recomputed in interactive time or approximated without changing the world, so a live session pins its device. The pin is a scheduling problem. WorldMove moves a live session under one guarantee: the destination is bit-identical to the source, or nothing is installed. It relocates the cache in 18.8 ms same-node, 101x faster than save/load. It holds a checksum-verified 92.1-94.8 Gb/s on a 100 Gb fabric. At that rate the cache fits inside one interactive block. Migrating an actively generating session, it converges at a block boundary and the destination continues the world bit for bit. An admissibility condition decides each move. The move must complete inside the readout horizon, over bandwidth that covers the state plus its dirty rate. Lifted to a fleet schedulability test, it governed a consolidation loop that executed 48 of 48 migrations bit-identical across two providers. Two constraints are structural. Bit-exactness survives only inside a controlled configuration of one GPU architecture, so moving the state is the only way to preserve it exactly in interactive time. Verification cannot hide inside the wire on this fabric. Receive-path checksums stall the transport at protocol timescales under fan-in, and unscheduled incast silently collapses a receiver while every delivered byte stays correct. An incast-aware admission controller holds zero misses to 1.4x offered load and sheds overload as rejects. A lossless GPU codec widens the admission gate to fabrics raw motion cannot use. We exercise the serving loop and the mover separately, each end to end. Their composition on one fabric is unbuilt. Exact-state elasticity is a joint scheduling problem over transport and verification.

cs.DC↗

arXiv2026

DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data

Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstructured data and annotate them into structured data for causal graph construction. However, they remain limited by two key challenges (CHs): (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, due to the lack of domain-specific knowledge; and (CH2) unreliable factor annotation, caused by the lack of domain-grounded reasoning, which propagates errors to the resulting causal graphs. To address these challenges, we introduce a novel Domain Knowledge-enhanced Causal Discovery framework (DKCD) for causal discovery from unstructured data in high-expertise domains with three interconnected components: (1) Knowledge Mining: It retrieves relevant domain knowledge based on observable factors to support subsequent causal reasoning. (2) Knowledge-guided Causal Reasoning: Reasoning with relevant knowledge, it discovers latent causal factors to address CH1 and generates key causal clues for more accurate data annotation to address CH2. (3) Causal Structure Discovery: It constructs the final causal graphs based on a more complete factor set and accurate annotations. Experiments on two domain-specific datasets show that DKCD significantly improves both causal factor identification and causal graph construction.

cs.CL↗

arXiv2026

Effects of Solar Wind Plasma Noise on Stochastic Gravitational Wave Background Searches with the LISA-Taiji Network

The LISA-Taiji dual detector network improves millihertz SGWB sensitivity through cross correlation measurements. Solar wind plasma, however, can generate plasma noise correlated between detectors and bias SGWB cross correlation estimates. We use high time resolution electron density data from Wind/SWE, estimate the solar wind electron density fluctuation spectrum with the Lomb-Scargle method, and propagate the resulting plasma noise to the TDI A/E channels of the LISA-Taiji network. By including finite arm propagation, Taylor frozen flow spatial correlations, and the network overlap reduction response, we compute the SGWB parameter bias induced by interdetector plasma noise. Although the single detector plasma residual is below the reference noise, the component correlated between detectors can enter the SGWB cross correlation estimator directly. Under dual detector scale coverage, the plasma induced parameter bias for a power law SGWB can reach 12.73% of the corresponding Fisher parameter uncertainty. For M2/M3 cosmic string spectra, the bias in ln Gmu can reach 19.26% of the corresponding Fisher parameter uncertainty for the network configurations, observing times, and frequency bands considered here. These results show that the impact of solar wind plasma noise cannot be assessed from the single detector residual noise level alone. In LISA-Taiji SGWB searches, the interdetector correlated component of this noise can directly affect parameter estimation.

astro-ph.CO↗

arXiv2026

Tests of general relativity using analytic derivatives of parametrized post-Einsteinian gravitational waveforms within the Fisher-matrix framework

Testing gravity beyond general relativity (GR) is essential for probing fundamental physics in the strong-field and highly dynamical regime accessed by gravitational-wave (GW) observations. In this work, we derive analytic expressions for waveform derivatives in the Fisher-matrix formalism within the parametrized post-Einsteinian framework, using the frequency-domain inspiral waveform. These analytic derivatives enable stable and efficient Fisher-matrix calculations without relying on finite-difference schemes. We apply this method to a wide range of detector configurations, including space-based, ground-based, and multiband observations, and combine it with different binary black hole population models. Our results reveal clear and systematic trends in the constraints on non-GR effects as functions of post-Newtonian order, detector type, and source population. They also demonstrate the complementarity between space- and ground-based detectors, particularly for effects that accumulate during the low-frequency inspiral. The analytic approach substantially reduces computational cost and avoids numerical systematics associated with step-size choices, making it well suited for large-scale parameter studies. These results provide robust forecasts for the capability of future GW observations to constrain a broad class of non-GR effects and environmental influences, highlighting the scientific potential of upcoming detector networks for precision tests of gravity.

gr-qc↗

arXiv2026

Automating the Design of Embodied Agent Architectures

Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected. Agent Architecture Search (AAS) automates such design for text-domain agents, but has not been systematically evaluated on perceptual embodied agents through simulator rollouts. We study this transfer. We introduce AgentCanvas, a typed-graph runtime that hosts embodied executors as editable node-and-wire programs with simulator-aware execution and episode-level logs, and KDLoop, a coding-agent search procedure that cycles through proposal, critique, experiment, and distillation, with triggered reflection after stalls. We evaluate three AAS variants across four embodied executors spanning vision-language navigation, embodied question answering, and language-conditioned manipulation. The resulting 3x4 matrix shows that architecture-level search can produce deployable and directional success-rate gains on embodied tasks, while one apparent high-scoring candidate is rejected as leak-bearing. At the same time, the experiments expose constraints that are muted in text-domain AAS: optimization signals can be masked by rollout noise, search can become trapped in local edit basins, and episode-level credit assignment only partially emerges even when detailed logs are available. These results characterize both the promise and the current limits of automated architecture search for embodied agents.

cs.RO↗

arXiv2026

Constructions and Characterizations of $s$-Plateaued Partitions

Bent partitions play a significant role in constructing bent functions and have rich connections with coding theory and combinatorics. In this paper, we introduce $s$-plateaued partitions, which generalize the bent partitions. Let $\Gamma=\{A_{i}, 1 \leq i \leq K\}$ be a partition of $V_{n}^{(p)}$, where $V_{n}^{(p)}$ is an $n$-dimensional vector space over the prime field $\mathbb{F}_{p}$ and $p \mid K$. Then $\Gamma$ is called an $s$-plateaued partition of $V_{n}^{(p)}$ of depth $K$ if each $p$-ary function $f: V_{n}^{(p)} \rightarrow \mathbb{F}_{p}$ for which every $j \in \mathbb{F}_{p}$ has exactly $\frac{K}{p}$ of sets $A_{i}$ in $\Gamma$ in its preimage set, is a $p$-ary $s$-plateaued function. By using an $s$-plateaued partition, a large number of $p$-ary $s$-plateaued functions, vectorial $s$-plateaued functions and generalized $s$-plateaued functions can be constructed. In particular, $0$-plateaued partitions are just bent partitions. In general, $s$-plateaued partitions are much more complicated than bent partitions. We analyze the possible cardinality of $A_{i}$ of an $s$-plateaued partition. We give some explicit constructions of $s$-plateaued partitions for which any generated $p$-ary $s$-plateaued function has no nonzero linear structure. We give a characterization of an $s$-plateaued partition $\Gamma=\{A_{i}, 1 \leq i \leq K\}$, where $p$ is odd, $K \geq 5$ and $-A_{i}=A_{i}, 1 \leq i \leq K$. Based on which, we show that if $p \geq 5$, then the preimage set partition of a $p$-ary $s$-plateaued function $f: V_{n}^{(p)} \rightarrow \mathbb{F}_{p}$ with $f(x)=f(-x)$ is an $s$-plateaued partition if and only if $f$ is of $(p-1)$-form, where $n+s$ is even.When $s=0$, we partially address an open problem on whether a bent partition $\Gamma$ of $V_{n}^{(p)}$ of depth $p^{\frac{n}{2}}$ must be obtained from spreads.

cs.IT↗

arXiv2026

STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity

Speech-to-speech translation (S2ST) should preserve not only lexical meaning, but also expressive attributes: emotion, scenario style (e.g., news reporting vs. dramatic dialogue), and nonverbal vocalizations (NVs). Moreover, collecting cross-lingual target speech that is both translation-faithful and expressively aligned with the source is difficult at scale, making reference-based evaluation impractical. We introduce STEB (Speech-to-Speech Translation Expressiveness Benchmark), a 32.6-hour Chinese--English benchmark that evaluates both standard dimensions (translation fidelity, speaker similarity, duration alignment) and expressiveness dimensions (emotion, scenario style, NV preservation). For expressiveness evaluation, STEB uses a caption-then-summarize framework that converts speech into structured expressive attributes and compares source and hypothesis attributes with an LLM judge. Human validation shows statistically significant correlations with listener judgments across all expressive dimensions. We evaluate six S2ST systems covering cascaded systems, end-to-end models, and speech large language models. Many systems, especially cascaded ones, achieve strong translation fidelity, but they still struggle with emotion preservation (best: 3.82/5) and NV preservation (best: 2.31/5). These results reveal a gap between semantic transfer and expressive transfer, identifying expressiveness preservation as an open challenge for S2ST. Audio samples are available at https://cmots.github.io/steb.github.io/.

cs.SD↗