arXiv subjects

Kun Tao

Publications and source records attributed to Kun Tao.

9 recordsLinked to original sources

arXiv2026

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite. Recent work explores a paradigm where a main agent decomposes tasks and dispatches subtasks to subagents, which execute and return only summarized results, conserving the main agent's context budget. However, performing this well requires delegation intelligence: the ability to decompose complex tasks, determine when and what to delegate, and integrate returned results into the ongoing workflow. Training data for this capability is scarce in naturally occurring text, and to our knowledge, how to synthesize such data and train models to acquire this capability remains largely unexplored in the open-source community. To bridge this gap, we present a preliminary exploration targeting deep research, a representative long-horizon agent task. Specifically, we design a harness that guides the model toward high-quality task decomposition and delegation, while constraining subagents to return results properly to support the main agent's workflow. The harness-guided trajectories naturally encode correct delegation decisions, which we use as supervised fine-tuning data to internalize delegation intelligence into model weights. Our resulting model, SearchSwarm-30B-A3B, achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH, the best results among all models of comparable scale. We will release our harness, model weights, and training data to facilitate future research.

cs.AI↗

arXiv2026

Orbital-Selective Engineering of Strain-Tunable Chern Insulators in Momentum Space

Unlike conventional approaches where topological order is statically fixed post-synthesis, we demonstrate that a single external knob-strain-can independently modulate topological order and functional responses in the Tc-adsorbed penta-hexa silicene (Tc_PH-Si) monolayer, with both properties governed by a single microscopic mechanism: momentum-space orbital-selective engineering of Tc-dxz_Si-px hybridization. Combining first-principles calculations and tight-binding models, we show that biaxial strain drives a complete topological pathway: C=1 (0) to C=0 (-2) to C = -1 (-3 to -4) to C = 0 metallic state (-6). This is exemplified by two pivotal states: a topologically critical point yet functionally optimal state at -2 strain (C=0) hosting a direct bandgap (0.17 eV) and d11 = 8.34 pm_V, and a topologically nontrivial but equally optimal state at -4 strain (C = -1) with d11 = 11.01 pm_V-three times that of MoS2. Berry curvature analysis reveals that functionality arises from local orbital hybridization strength, while topology originates from its global phase distribution. This establishes a new paradigm for materials design, transforming static functional materials into dynamically tunable quantum platforms.

cond-mat.mtrl-sci↗

arXiv2026

DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization

In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective. This ability to robustly retarget diverse demonstrations opens the door to generating large-scale synthetic datasets of humanoid loco-manipulation trajectories, addressing a major bottleneck in real-world data collection.

cs.RO↗

arXiv2023

The 1/4 occupied O atoms induced ultraflat band and the one dimensional channels in the Pb$_{10-x}$Cu$_{x}$(PO$_4$)$_{6}$O$_{4}$ (x=0,0.5) crystal

The search for room-temperature superconductors has been a long-standing goal in condensed matter physics. In this study, we investigate the electronic and geometric properties of lead apatite with and without Cu doped within the frame work of the density functional theory. Based on our calculations, we found that without the Cu doped the lead apatite shows an insulator character with flat bands straddle the Fermi level. Once we introduce the O1 vacancies, the flat bands disappear. Furthermore, we analyze the effects of Cu doping on the crystal structure and electronic band structure of the material. Our calculations reveal the presence of one-dimensional channels induced by fully occupied O1 atoms, that are only 1/4 occupied in the literature, which may play a crucial role in the realization of room-temperature superconductivity. Based on our findings, we propose a possible solution to improve the quality of superconductivity by annealing the material in an oxygen atmosphere. These results contribute to a better understanding of the unusual properties of Cu-doped lead apatite and will pave the way for further exploration of its potential as a room-temperature superconductor.

cond-mat.supr-con↗

arXiv2022

Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT

Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity Recognition (NER), as well as on cross-lingual model transfer. At present, the mainstream methods to solve the cross-lingual downstream tasks are always using the last transformer layer's output of mBERT as the representation of linguistic information. In this work, we explore the complementary property of lower layers to the last transformer layer of mBERT. A feature aggregation module based on an attention mechanism is proposed to fuse the information contained in different layers of mBERT. The experiments are conducted on four zero-shot cross-lingual transfer datasets, and the proposed method obtains performance improvements on key multilingual benchmark tasks XNLI (+1.5 %), PAWS-X (+2.4 %), NER (+1.2 F1), and POS (+1.5 F1). Through the analysis of the experimental results, we prove that the layers before the last layer of mBERT can provide extra useful information for cross-lingual downstream tasks and explore the interpretability of mBERT empirically.

cs.CL↗

arXiv2020

Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension

Machine reading comprehension (MRC) is the task that asks a machine to answer questions based on a given context. For Chinese MRC, due to the non-literal and non-compositional semantic characteristics, Chinese idioms pose unique challenges for machines to understand. Previous studies tend to treat idioms separately without fully exploiting the relationship among them. In this paper, we first define the concept of literal meaning coverage to measure the consistency between semantics and literal meanings for Chinese idioms. With the definition, we prove that the literal meanings of many idioms are far from their semantics, and we also verify that the synonymic relationship can mitigate this inconsistency, which would be beneficial for idiom comprehension. Furthermore, to fully utilize the synonymic relationship, we propose the synonym knowledge enhanced reader. Specifically, for each idiom, we first construct a synonym graph according to the annotations from a high-quality synonym dictionary or the cosine similarity between the pre-trained idiom embeddings and then incorporate the graph attention network and gate mechanism to encode the graph. Experimental results on ChID, a large-scale Chinese idiom reading comprehension dataset, show that our model achieves state-of-the-art performance.

cs.CL↗

arXiv2020

R3: A Reading Comprehension Benchmark Requiring Reasoning Processes

Existing question answering systems can only predict answers without explicit reasoning processes, which hinder their explainability and make us overestimate their ability of understanding and reasoning over natural language. In this work, we propose a novel task of reading comprehension, in which a model is required to provide final answers and reasoning processes. To this end, we introduce a formalism for reasoning over unstructured text, namely Text Reasoning Meaning Representation (TRMR). TRMR consists of three phrases, which is expressive enough to characterize the reasoning process to answer reading comprehension questions. We develop an annotation platform to facilitate TRMR's annotation, and release the R3 dataset, a \textbf{R}eading comprehension benchmark \textbf{R}equiring \textbf{R}easoning processes. R3 contains over 60K pairs of question-answer pairs and their TRMRs. Our dataset is available at: \url{http://anonymous}.

cs.CL↗

arXiv2009

Hopf algebras and the logarithm of the S-transform in free probability

Let k be a positive integer and let G_k denote the set of non-commutative k-variable distributions μsuch that μ(X_1) = ... = μ(X_k) = 1. G_k is a group under the operation of free multiplicative convolution. We identify G_k as the group of characters of a certain Hopf algebra Y_k. Then, by using the log map from characters to infinitesimal characters of Y_k, we introduce a transform LS_μ for distributions μin G_k. The main property of the LS-transform is that it linearizes commuting products in G_k. For μin G_k, the transform LS_μ is a power series in k non-commuting indeterminates; its coefficients can be computed from the coefficients of the R-transform of μby using summations over chains in the lattices NC(n) of non-crossing partitions. In the particular case k=1 one has that Y_1 is naturally isomorphic to the Hopf algebra Sym of symmetric functions, and that the LS-transform is very closely related to the logarithm of the S-transform of Voiculescu, by the formula LS(z) = - z log S(z). In this case the group G_1 can be identified as the group of characters of Sym, in such a way that the S-transform, its reciprocal 1/S and its logarithm log S relate in a natural sense to the sequences of complete, elementary and respectively power sum symmetric functions.

math.OA↗

arXiv2008

Manipulating magnetism and conductance of an adatom-molecule junction on metal surfaces: ab initio study

The state of the art ab initio calculations reveal the effect of a scanning tunnelling microscopy tip on magnetic properties and conductance of a benzene-adatom sandwich on Cu(001). We concentrate on a benzene-Co system interacting with a Cr tip. Our studies give a clear evidence that magnetism and conductance in molecule-adatom junctions can be tailored by the STM tip. Varying the tip-substrate distance the magnetic moment of the Co adatom can be switched on/off. The interplay between spin-polarized electron transport through the junction and its magnetic properties is demonstrated. A spin-filter effect in the junction is predicted.

cond-mat.mtrl-sci↗