arXiv subjects

Kuan Li

Publications and source records attributed to Kuan Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

AgentFold: Long-Horizon Web Agents with Proactive Context Management

LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Prevailing ReAct-based agents suffer from context saturation as they accumulate noisy, raw histories, while methods that fixedly summarize the full history at each step risk the irreversible loss of critical details. Addressing these, we introduce AgentFold, a novel agent paradigm centered on proactive context management, inspired by the human cognitive process of retrospective consolidation. AgentFold treats its context as a dynamic cognitive workspace to be actively sculpted, rather than a passive log to be filled. At each step, it learns to execute a `folding' operation, which manages its historical trajectory at multiple scales: it can perform granular condensations to preserve vital, fine-grained details, or deep consolidations to abstract away entire multi-step sub-tasks. The results on prominent benchmarks are striking: with simple supervised fine-tuning (without continual pre-training or RL), our AgentFold-30B-A3B agent achieves 36.2% on BrowseComp and 47.3% on BrowseComp-ZH. Notably, this performance not only surpasses or matches open-source models of a dramatically larger scale, such as the DeepSeek-V3.1-671B-A37B, but also surpasses leading proprietary agents like OpenAI's o4-mini.

cs.CL↗

arXiv2025

WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.

cs.CL↗

arXiv2025

WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

cs.LG↗

arXiv2025

Scaling Agents via Continual Pre-training

Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them to expert demonstrations, thereby creating fundamental optimization tensions. To this end, we are the first to propose incorporating Agentic Continual Pre-training (Agentic CPT) into the deep research agents training pipeline to build powerful agentic foundational models. Based on this approach, we develop a deep research agent model named AgentFounder. We evaluate our AgentFounder-30B on 10 benchmarks and achieve state-of-the-art performance while retains strong tool-use ability, notably 39.9% on BrowseComp-en, 43.3% on BrowseComp-zh, and 31.5% Pass@1 on HLE.

cs.CL↗

arXiv2025

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in the real world. This makes multimodal Deep Research highly challenging, as such agents require much stronger reasoning abilities in perception, logic, knowledge, and the use of more sophisticated tools compared to text-based agents. To address this limitation, we introduce WebWatcher, a multi-modal Agent for Deep Research equipped with enhanced visual-language reasoning capabilities. It leverages high-quality synthetic multimodal trajectories for efficient cold start training, utilizes various tools for deep reasoning, and further enhances generalization through reinforcement learning. To better evaluate the capabilities of multimodal agents, we propose BrowseComp-VL, a benchmark with BrowseComp-style that requires complex information retrieval involving both visual and textual information. Experimental results show that WebWatcher significantly outperforms proprietary baseline, RAG workflow and open-source agents in four challenging VQA benchmarks, which paves the way for solving complex multimodal information-seeking tasks.

cs.IR↗

arXiv2025

Strongly correlated electronic superconductivity in the noncentrosymmetric Re-Os-based high/medium-entropy alloys

The class of unconventional superconductors, particularly noncentrosymmetric superconductors, has been highly considered as potential materials for understanding the complex properties of quantum materials. Here, five previously unreported Re3.5Os3.5Ta0.5Hf0.5Nb3, Re3Os3Ta0.5Hf0.5Nb3, Re3.5Os3.5Mo0.5Hf0.5Nb3, Re3.5Os3.5Mo0.5W0.5Nb3, and Re3Os3Mo0.5Hf0.5Nb3 Re-Os-based high/medium-entropy alloys (MEAs-HEAs) with valence electron count ranging from 6.45 to 6.81 were synthesized and investigated using x-ray diffraction, transport, magnetization, and specific heat measurements. Our analyses confirm that all five compounds crystallize in a noncentrosymmetric α-Mn-type structure and exhibit type-II superconductivity with Tc values from 4.20 K to 5.11 K, respectively. Unexpectedly, despite being immersed in an acidic environment for one month, the structures and superconducting properties of HEAs remain stable. Our findings indicate that the Tc increases with an increasing valence electron count in MEAs-HEAs. Furthermore, these noncentrosymmetric α-Mn-type HEA superconductors have large Kadowaki-Woods ratios (KWR), implying the presence of strong electronic correlations.

cond-mat.supr-con↗

arXiv2025

WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization

The advent of Large Language Model (LLM)-powered agents has revolutionized artificial intelligence by enabling solutions to complex, open-ended tasks through web-based information-seeking (IS) capabilities. The scarcity of high-quality training data has limited the development of IS agents. Existing approaches typically adopt an information-driven paradigm that first collects web data and then generates questions based on the retrieval. However, this may lead to inconsistency between information structure and reasoning structure, question and answer. To mitigate, we propose a formalization-driven IS data synthesis framework WebShaper to construct a dataset. WebShaper systematically formalizes IS tasks through set theory. Central to the formalization is the concept of Knowledge Projections (KP), which enables precise control over reasoning structure by KP operation compositions. During synthesis, we begin by creating seed tasks, then use a multi-step expansion process. At each step, an agentic Expander expands the current formal question more complex with retrieval and validation tools based on our formalization. We train our model on the synthesized dataset. Experiment results demonstrate that WebShaper achieves state-of-the-art performance among open-sourced IS agents on GAIA and WebWalkerQA benchmarks.

cs.CL↗

arXiv2025

WebSailor: Navigating Super-human Reasoning for Web Agent

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all opensource agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

cs.CL↗

arXiv2025

Large Processor Chip Model

Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on manual expertise, fragmented optimization across software and hardware layers, and high costs associated with exploring expansive design spaces. While automated methods leveraging optimization algorithms and machine learning have improved efficiency, they remain constrained by a single-stage focus, limited data availability, and a lack of comprehensive human domain knowledge. The emergence of large language models offers transformative opportunities for the design of computer system architecture. By leveraging the capabilities of LLMs in areas such as code generation, data analysis, and performance modeling, the traditional manual design process can be transitioned to a machine-based automated design approach. To harness this potential, we present the Large Processor Chip Model (LPCM), an LLM-driven framework aimed at achieving end-to-end automated computer architecture design. The LPCM is structured into three levels: Human-Centric; Agent-Orchestrated; and Model-Governed. This paper utilizes 3D Gaussian Splatting as a representative workload and employs the concept of software-hardware collaborative design to examine the implementation of the LPCM at Level 1, demonstrating the effectiveness of the proposed approach. Furthermore, this paper provides an in-depth discussion on the pathway to implementing Level 2 and Level 3 of the LPCM, along with an analysis of the existing challenges.

cs.AR↗

arXiv2025

Superconductivity in the Medium-Entropy/High-Entropy Re-based Alloys with a Non-Centrosymmetric $α$-Mn Lattice

Medium or high-entropy alloys (MEAs-HEAs) and rhenium-based compounds with a non-centrosymmetric (NC) structure have received a lot of attention for offering a fertile soil in search for unconventional superconductivity. Here, five previously unreported NC Re-based MEA-HEA superconductors with an $α$-Mn lattice are successfully synthesized, with their superconducting transition temperatures (Tcs) ranging from 4 to 5 K. An increase in the superconducting transition temperature (Tc) can be achieved by modulating the valence electron count (VEC) through compositional adjustments. Magnetization measurements confirm that all the synthesized Re-based MEA-HEAs are bulk type-II superconductors. Specific heat analysis reveals that the superconducting state of these HEAs can be well described by a single-gap s-wave model. Our results show that the Kadowaki-Woods ratio of these $α$-Mn MEA/HEA superconductors are close to the typical value of heavy fermion compounds, suggesting the existence of strong electronic correlation. These findings provide promising material platforms to study the role of high disorder in the origin of superconductivity in the NC MEAs-HEAs.

cond-mat.supr-con↗

arXiv2025

LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing

Effectively incorporating external knowledge into Large Language Models (LLMs) is crucial for enhancing their capabilities and addressing real-world needs. Retrieval-Augmented Generation (RAG) offers an effective method for achieving this by retrieving the most relevant fragments into LLMs. However, the advancements in context window size for LLMs offer an alternative approach, raising the question of whether RAG remains necessary for effectively handling external knowledge. Several existing studies provide inconclusive comparisons between RAG and long-context (LC) LLMs, largely due to limitations in the benchmark designs. In this paper, we present LaRA, a novel benchmark specifically designed to rigorously compare RAG and LC LLMs. LaRA encompasses 2326 test cases across four practical QA task categories and three types of naturally occurring long texts. Through systematic evaluation of seven open-source and four proprietary LLMs, we find that the optimal choice between RAG and LC depends on a complex interplay of factors, including the model's parameter size, long-text capabilities, context length, task type, and the characteristics of the retrieved chunks. Our findings provide actionable guidelines for practitioners to effectively leverage both RAG and LC approaches in developing and deploying LLM applications. Our code and dataset is provided at: \href{https://github.com/Alibaba-NLP/LaRA}{\textbf{https://github.com/Alibaba-NLP/LaRA}}.

cs.CL↗

arXiv2025

Large upper critical fields and strong coupling superconductivity in the medium-entropy alloy (Ti1/3Hf1/3Ta1/3)1-xNbx

Since the discovery of high-entropy superconductors in 2014, superconductivity has remained a focal point of interest in medium- and high-entropy alloys (MEAs-HEAs). Here, we report a series of (Ti0.33Hf0.33Ta0.33)1-xNbx MEA superconductors crystallized in the BCC structure, whose superconductivity was characterized by resistivity, magnetization, and specific heat measurements. The study found that the (Ti0.33Hf0.33Ta0.33)1-xNbx MEAs exhibit bulk superconductivity. With the doping of Nb, the superconducting transition temperature (Tc) increases from 5.31 K to 9.11 K, and the normalized Cel jumps at Tc, and the logarithmically averaged characteristic phonon frequency exhibit dome-shaped curves. Results from specific heat measurements indicate that the superconductivity is of a strongly coupled s-wave type observed. Furthermore, at low Nb content, the upper critical field of the samples is larger than the Pauli paramagnetic limit. The strongly coupling behavior and large upper critical field in s-wave type (Ti0.33Hf0.33Ta0.33)1-xNbx MEA superconductors are unusual, as they typically occur in other unconventional superconductors. Thus, (Ti0.33Hf0.33Ta0.33)1-xNbx may have significant potential in the research and understanding of physical mechanisms.

cond-mat.supr-con↗

arXiv2024

Superconductivity in the medium entropy alloys Nb2TiW and Nb2TiMo

This study describes the synthesis and characterization of Nb2TiW and Nb2TiMo medium entropy alloys (MEAs). The Nb2TiW and Nb2TiMo MEAs can be successfully synthesized by an arc melting method. Their structures and superconducting properties are investigated by detailed characterization of X ray diffraction (XRD), resistivity, magnetization, and specific heat measurements. XRD results confirm that the obtained Nb2TiW and Nb2TiMo compounds have the same body-centered cubic (BCC) structures. Experimental results show that the superconducting transition temperatures Tcs of Nb2TiW and Nb2TiMo are around 4.86 K and 3.22 K, respectively. The upper and lower critical fields of Nb2TiW are 3.52(2) T and 53.36(2) Oe, respectively, and those of Nb2TiMo are 2.11(2) T and 68.23(3) Oe, respectively. First-principles calculations reveal that the d electrons of Nb, Ti, and Mo or W are the dominant contribution of the density of states near the Fermi level. Specific heat measurement results indicate that Nb2TiW and Nb2TiMo display BCS full-gap s-wave superconductivity.

cond-mat.supr-con↗

arXiv2024

Effects of Lanthanides on the Structure and Oxygen Permeability of Ti-doped Dual-phase Membranes

The trade-off effect of the oxygen permeability and stability of oxygen transport membranes (OTMs) still exists in working atmospheres containing CO2. Herein, we reported a new series of 60 wt%Ce0.9Ln0.1O2-δ-40wt%Ln0.6Sr0.4Fe0.9Ti0.1O3-δ (CLnO-LnSFTO, Ln = La, Pr, Nd, Sm, Gd, Tb) dual-phase OTMs by selecting different Ln elements based on the reported highly stable Ti-doped CPrO-PrSFTO. The effects of different Ln elements on the structure and oxygen permeability of Ti-doped dual-phase OTMs were systematically studied. Basically, as the atomic number of Ln elements increases, the unit cell parameters of both the fluorite phase and the perovskite phase become smaller. The unit cell volume and spatial symmetry of the perovskite phase are reduced, resulting in a reduction in oxygen permeability. The optimal CLaO-LaSFTO showed JO2 of 0.60 and 0.54 mL min-1 cm-2 with He and CO2 sweeping at 1000 oC, respectively. In addition, all CLnO-LnSFTO OTMs could work for more than 100 hours with no significant performance degradation in a CO2 atmosphere, maintaining excellent stability. This work explores candidate OTM materials for CO2 capture and oxygen separation, as well as provides some ideas for addressing the trade-off effect.

cond-mat.mtrl-sci↗

arXiv2024

A new approach to N-doped di-molybdenum carbide with enhanced superconductivity via Urea

Chemical doping is a critical factor in the development of new superconductors or optimizing the superconducting transition temperature (Tc) of the parent superconducting materials. Herein, a new simple urea approach is developed to synthesize the N-doped alfa-Mo2C. Benefiting from the simple urea method, a broad superconducting dome is found in the Mo2C1-xNx compositions. XRD results show that the structure of alfa-Mo2C remains unchanged and that there is a variation of lattice parameters with nitrogen doping. Resistivity, magnetic susceptibility, and heat capacity measurement results confirm that the superconducting transition temperature (Tc) was strongly increased from 2.68 K (x = 0) to 7.05 K (x = 0.49). First-principles calculations and our analysis indicate that increasing nitrogen doping leads to a rise in the density of states at the Fermi level and doping-induced phonon softening, which enhances electron-phonon coupling. This results in an increase in Tc and a sharp rise in the upper critical field. Our findings provide a promising strategy for fabricating transition metal carbonitrides and provide a material platform for further study of the superconductivity of transition metal carbides.

cond-mat.supr-con↗

arXiv2024

Mapping Hydrogen Evolution Activity Trends of V-based A15 Superconducting Alloys

Exploring high-efficiency and low-cost electrocatalysts is valuable for water-splitting technologies. Recently, Si-group compounds have attracted increasing attention in electrocatalysis, considering the abundant Si-group elements on Earth. However, Si-group compounds for HER electrocatalysis have not been systematically studied. In this study, we unveil the activity trends of non-noble metal catalyst A15-type V3M (i.e., V3Si, V3Ge, and V3Sn) superconductors and show that V3Si is the most efficient HER catalyst because of the high electronic conductivity and suitable d-band center. Among them, the V3Si only requires 33.4 mV to reach 10 mA cm-2, and only 57.6 mV and 114.6 mV are required to attain a high current density of 100 mA cm-2 and 500 mA cm-2, respectively. These low overpotentials are close to the 34.3 mV at 10 mA cm-2 of state-of-art Pt/C (20 %) but superior to 168.5 mV of Pt/C (20 %) at 100 mA cm-2. Furthermore, the V3Si illustrates exceptional durability with no obvious decay in the 120 h at the different current densities (i.e., 10 - 250 mA cm-2). The excellent HER activity of V3Si alloy can be ascribed to the synergies of superior electronic conductivity and suitable d-band center. Moreover, DFT calculations reveal that the absolute hydrogen adsorption Gibbs free energy is decreased after introducing the V to Si. Beyond offering a stable and high-performance electrocatalyst in an acidic medium, this work inspires the rational design of desirable silicide electrocatalysts.

cond-mat.mtrl-sci↗

arXiv2024

Excellent and CO$_2$$_{0.85}$Nd$_{0.1}$Cu$_{0.05}$O$_{2-δ}$-Nd$_x$Sr$_{1-x}$Fe$_{1-y}$Cu$_y$O$_{3-δ}$ dual-phase oxygen transport membranes

Oxygen transport membranes(OTMs)have provided great opportunities in the last decades but are suffering from the trade-off effect between stability and oxygen permeability. Here, we report a group of new planar dual-phase mixed ionic-electronic conducting (MIEC) OTMs consisting of CO$_2$$_{0.85}$Nd$_{0.1}$Cu$_{0.05}$O$_2$ (CNCO) and Nd$_x$Sr$_{1-x}$Fe$_{1-y}$Cu$_y$O$_3$(NSFCO; $x = 0.4, 0.6$; $y = 0.05, 0.1$) phases, showing excellent oxygen permeability while comparable CO$_2$-resistant stability. The substitution of Cu as a bifunctional additive decreases the sintering temperature and enhances bulk diffusion and oxygen permeability with the co-doping of Nd.The oxygen permeation fluxes reached 2.62 and 1.52 mL min$^{-1}$ cm$^{-2}$ at 1000$^\circ$C through the optimal 60wt%Ce0.85Nd0.1Cu0.05O2-40wt%Nd0.4Sr0.6Fe0.9Cu0.1O3 (CNCO-NSFCO41) composition with He and CO$_2$ sweeping, respectively, higher than all reported dense dual-phase OTMs. Such excellent CO$_2$-tolerant permeability meets the needs of potential industrial applications. Analysis with Zhu's oxygen permeation model shows lower bulk diffusion resistance of CNCO-NSFCO41 than that of reported 60wt%Ce0.85Pr0.1Cu0.05O2-40wt%Pr0.4Sr0.6Fe0.9Cu0.1O3(CPCO-PSFCO41)and more limitation by the interfacial exchange at high temperature. All the prepared OTMs also show good long-term stability over 100 hours in both atmospheres. Our results confirm the excellent oxygen permeability and stability under a high-concentration CO2 atmosphere, providing a material candidate for CO2 capture in oxyfuel combustion.

cond-mat.mtrl-sci↗

arXiv2024

Non-trivial Topological Surface States Regulation of 1T-OsCoTe$_2$ Enables Selective C-C Coupling for Highly Efficient Photochemical CO$_2$ Reduction Toward C$_{2+}$ hydrocarbons

Despite ongoing research, the rational design of nontrivial topological semimetal surface states for the selective photocatalytic CO$_2$ conversion into valuable products remains full of challenges. Herein, we present the synthesis of 1T-OsCoTe$_2$ for the photoreduction upgrading of CO$_2$ to tricarbon alkane C$_3$H$_8$,by the integration of experimental work and theory calculation. Experimental studies suggested a high electron based selectivity of 71.2% for C$_3$H$_8$ and an internal quantum efficiency of 54.6% at 380 nm. In-situ X-ray photoelectron spectroscopy and X-ray absorption fine structure spectroscopy demonstrated that Co and Os atoms coordinated with Te atoms enable an efficient Os-Te-Co electron transfer to activate the generation of *CH$_3$,*CHOCO and *CH$_2$OCOCO. Density functional theory calculations further confirmed Os-Te-Co electron bridging on the improved CO$_2$ conversion kinetics. To our knowledge, this is the first report suggesting the role of Os atoms in accelerating the photocatalytic CO$_2$ conversion activity of the topological semimetal 1T-OsCoTe$_2$.

cond-mat.mtrl-sci↗