arXiv subjects

Jingjun Xu

Publications and source records attributed to Jingjun Xu.

At least 19 recordsLinked to original sources

arXiv2026

ExpWeaver: LLM Agents Learn from Experience via Latent RAG

Experience learning has achieved promising results in enhancing LLM agent planning and reasoning by integrating past interactions as reusable knowledge. However, existing methods remain confined to explicit text space, retrieving experiences via semantic similarity and concatenating them into the context window, leading to substantial token overhead and a decoupled architecture that separates retrieval from generation. To address these limitations, we propose ExpWeaver, a framework that enables LLM agents to learn from experience via latent retrieval-augmented generation, without requiring a separate RAG module. ExpWeaver encodes experiences using the LLM's own hidden states, retrieves relevant experiences directly in latent space at each decoding step, and integrates them through cross-attention aggregation and gated residual mechanisms. The entire pipeline is optimized end-to-end with reinforcement learning, supporting both generative and ranking tasks. We evaluate ExpWeaver on 13 diverse tasks spanning question answering, reasoning, coding, scientific prediction, and recommendation. Results demonstrate that ExpWeaver achieves state-of-the-art performance on 12 out of 13 tasks, outperforming the strongest baseline by over 6.8%; maintains token efficiency comparable to non-retrieval baselines while text-based retrieval methods require 1.5 to 2 times more tokens; and exhibits superior cross-domain generalization, outperforming the strongest baseline by 16.32% under zero-shot transfer and 15.21% under few-shot transfer. Our code for ExpWeaver is released at https://github.com/ulab-uiuc/ExpWeaver.

cs.CL↗

arXiv2026

ElasticMem: Latent Memory as a Learnable Resource for LLM Agents

Long-term memory is essential for LLM agents to reason coherently across extended interactions, personalize responses, and reuse past experience. However, existing memory-augmented methods typically treat memory as a fixed resource: text-space approaches concatenate retrieved memories into the context window, causing substantial token overhead and sensitivity to noisy evidence, while latent-space approaches reduce textual cost but still rely on rigid retrieval or fixed-capacity memory interfaces. This creates a mismatch between query-dependent memory utility and fixed memory allocation. We propose ElasticMem, a memory-augmented LLM framework that learns to use memory as an elastic latent resource. ElasticMem builds an offline latent memory bank with retrieval keys and content caches, retrieves memories adaptively from the reasoner's hidden state, assigns each retrieved memory a variable latent budget through a learned policy, and injects selected latent states as soft memory tokens for generation. The full memory-use process is optimized with downstream task rewards through group-relative policy optimization. We evaluate ElasticMem on MemorySuite, covering memory-intensive QA and embodied agent control. Across Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct backbones, ElasticMem improves weighted average QA accuracy by 26.2% and 24.6%, and improves ALFWorld success rate by 66.3% and 27.2%, respectively, over the strongest baselines, while achieving the lowest ALFWorld token cost. Ablations and qualitative analyses further show that adaptive retrieval and elastic budget allocation help ElasticMem prioritize useful evidence and transferable plans beyond rigid cosine similarity. Our code for ElasticMem will be released at https://github.com/ulab-uiuc/ElasticMem.

cs.CL↗

arXiv2026

ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents

Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scratch and fail to reuse successful strategies or failure lessons from prior experience. Fine-tuning on collected experience can improve reuse, but it is inflexible when stronger or more suitable executors emerge. We propose ExpGraph, a model-agnostic experience learning framework that enables frozen and replaceable LLM executors to improve through external experience reuse without parameter updates. ExpGraph summarizes historical trajectories into reusable skills and failure lessons, organizes them as nodes in a self-evolving experience graph, and retrieves useful experiences through graph diffusion and utility-aware ranking. A lightweight retrieval copilot is trained with reinforcement learning using feedback that compares executor performance with and without retrieved experiences, while the graph is updated online from downstream task outcomes. We evaluate ExpGraph on ExpSuite, covering question answering, mathematical reasoning, code generation, and multi-step agentic environments including ALFWorld and AppWorld. ExpGraph improves over the strongest baseline by 12.2% and 4.7% on static tasks with smaller and larger executors, and by 21.4% and 12.7% in agentic environments, while reducing average interaction steps by 12.7% and 21.6%. Ablations show that graph-structured experience, utility-aware ranking, and adaptive retrieval jointly enable effective experience reuse across diverse tasks and executor models.

cs.CL↗

arXiv2026

RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing

LLM routing is increasingly important for selecting suitable models under diverse user needs and deployment constraints, but its practical effectiveness depends on continual adaptation to emerging queries and newly released models. New-LLM integration is particularly challenging, as newly released models lack the query-response-reward interactions required for router training and cannot be profiled as directly as new queries via semantic embeddings. Existing profiles are limited: LLM-generated descriptions are often coarse, while interaction-based embeddings are costly to construct. To address this problem, we propose RouteProfile, a graph-based profiling framework that constructs LLM profiles from public signals in technical reports or model cards, including model family, model description, reported benchmark scores, and benchmark domains. RouteProfile organizes these heterogeneous signals into a graph and studies profile construction along four dimensions: organizational form, representation type, aggregation depth, and learning configuration. We evaluate RouteProfile in training-free cold-start routing and new-LLM integration settings. Experiments show that: (1) structured profiles outperform flat baselines in training-free cold-start routing; (2) model family metadata is more reliable than benchmark domain information; and (3) effective new-LLM integration requires profile-router co-design. Overall, our findings highlight the importance of profile design for enabling routing systems to adapt to the evolving model ecosystem.

cs.NI↗

arXiv2026

Fractal hierarchy enables exponential scaling of topological boundary states

Exponential growth describes an extremely rapid process ubiquitous across mathematics and diverse physical, biological, and technological systems. Here, we introduce a class of fractal-inspired lattices that combine long-range periodic order with self-similar hierarchy, establishing a structural motif that enables exponential scaling of topological boundary states. We demonstrate this phenomenon in (i) a quasi-one-dimensional lattice chain constructed from Koch-curve unit cells and (ii) a two-dimensional periodic tiling lattice composed of Sierpinski-gasket unit cells. We show that, for suitable coupling parameters, both the number of topological boundary states $N_{\ell}$ and the number of topological minigaps $M_{\ell}$ grow exponentially with the fractal generation index $\ell$. We find that $N_{\ell}$ is an integer multiple of $M_{\ell}$, with the integer determined by the underlying symmetry. This hierarchical scaling law is captured by multi-topological-phase theory and confirmed experimentally in laser-written photonic lattices. Our results identify fractal hierarchy as a materials architecture principle for controlling boundary-state multiplicity, revealing an interplay between topology, self-similar geometry, and periodic order. More broadly, this work suggests a route to synthetic materials and integrated photonic platforms in which large numbers of robust boundary modes can be engineered within compact architectures.

physics.optics↗

arXiv2026

A Non-Abelian Route to Z2 Non-Hermitian Skin Effects

The non-Hermitian skin effect (NHSE), characterized by extensive boundary accumulation of eigenstates under open boundary conditions, has emerged as a central phenomenon in non-Hermitian physics. Conventionally, the NHSE arises from either non-reciprocal couplings or onsite gain and loss combined with synthetic gauge fields. Existing studies, however, have been largely confined to frameworks with Abelian-coupling, leaving the role of non-Abelian couplings essentially unexplored. Here, we demonstrate that non-Abelian-couplings can generate the NHSE, giving rise to a time-reversal-symmetry-protected Z2 skin effect with pseudospin-dependent boundary localization and dynamical pseudospin separation. Experimentally, we implement a representative four-level model using a programmable topolectrical circuit and directly observe both the predicted NHSE and the boundary-induced pseudospin-inversion reflection. Our work establishes a fundamental link between non-Abelian coupling and non-Hermitian topology, opening new avenues for realizing non-reciprocity-free topological materials and devices.

physics.optics↗

arXiv2026

Topological photonics in one-dimensional settings

Over the past decade, topological photonics has emerged as a vibrant field, attracting significant attention and witnessing remarkable advancements. This growth can be attributed to its fundamental appeal and the unique opportunities it offers for unconventional control of light, promising innovations in next-generation photonic devices. At the heart of topological photonics lies the one-dimensional (1D) SSH model. Originally conceived to elucidate the physics of a molecular chain of polyacetylene, this model has found widespread applications in exploring a wide range of topological phenomena in photonics and beyond. In this chapter, we aim to provide an overview of topological photonics in one-dimensional (1D) settings. After briefly introducing paradigmatic 1D models, including the SSH, Rice-Mele, and AAH models, we review recent advances in experimental studies and applications of topological photonics based on 1D platforms. Our discussion highlights demonstrated examples, such as the nonlinear tuning of topological states in both Hermitian and non-Hermitian photonic SSH lattices, as well as nonlinear harmonic generation and topological lasing in SSH-type photonic microstructures. We further discuss characteristic topological phenomena in other representative 1D settings, including Floquet systems, topological pumping, quasicrystals, and synthetic non-Hermitian systems. Finally, we examine selected examples of two-dimensional (2D) photonic topological crystalline insulators that are closely linked to the SSH model. Towards the end, we summarize the chapter and provide a list of key contributions, together with an outlook on possible future directions in 1D topological photonics. While this review focuses specifically on 1D topological photonics, it is not intended to be comprehensive or exhaustive.

physics.optics↗

arXiv2026

Time-independent theoretical framework for stroboscopic nonlinear dynamics based on time-nonlocal response

Recent experiments have demonstrated the ability to manipulate nonlinear interactions via time modulation, giving rise to the so-called stroboscopic nonlinearity. To date, however, this phenomenon has not been subjected to a rigorous theoretical analysis. In this work, we clarify the physical mechanism underlying stroboscopic nonlinear dynamics based on time-nonlocal response and establish an effective time-independent model under suitable modulation conditions. The proposed model almost exactly reproduces the full time-dependent dynamics in the quasi-steady state and significantly outperforms empirical descriptions used previously. Our results provide a clear physical picture of stroboscopic nonlinear dynamics, and can be extended to other systems with time-nonlocal response, establishing a general framework for engineering nonlinear interactions through temporal modulation.

physics.optics↗

arXiv2026

Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment

Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguistic harm. Existing agent safety evaluations rely on risk-oriented tasks tailored to specific agent settings, resulting in limited coverage of safety risk space and failing to assess agent safety behavior during long-horizon, interactive task execution in complex real-world deployments. Moreover, their specialization to particular agent settings limits adaptability across diverse agent configurations. To address these limitations, we propose Risky-Bench, a framework that enables systematic agent safety evaluation grounded in real-world deployment. Risky-Bench organizes evaluation around domain-agnostic safety principles to derive context-aware safety rubrics that delineate safety space, and systematically evaluates safety risks across this space through realistic task execution under varying threat assumptions. When applied to life-assist agent settings, Risky-Bench uncovers substantial safety risks in state-of-the-art agents under realistic execution conditions. Moreover, as a well-structured evaluation pipeline, Risky-Bench is not confined to life-assist scenarios and can be adapted to other deployment settings to construct environment-specific safety evaluations, providing an extensible methodology for agent safety assessment.

cs.AI↗

arXiv2026

Self-Guard: Defending Large Reasoning Models via enhanced self-reflection

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current alignment strategies predominantly rely on heavy post-training paradigms or external interventions. However, these approaches are often computationally intensive and fail to address the inherent awareness-compliance gap, a critical misalignment where models recognize potential risks yet prioritize following user instructions due to their sycophantic tendencies. To address these limitations, we propose Self-Guard, a lightweight safety defense framework that reinforces safety compliance at the representational level. Self-Guard operates through two principal stages: (1) safety-oriented prompting, which activates the model's latent safety awareness to evoke spontaneous reflection, and (2) safety activation steering, which extracts the resulting directional shift in the hidden state space and amplifies it to ensure that safety compliance prevails over sycophancy during inference. Experiments demonstrate that Self-Guard effectively bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility. Furthermore, Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales, offering a cost-efficient solution for LRM safety alignment.

cs.AI↗

arXiv2026

DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Despite the growing adoption of large language models (LLMs) in scientific research workflows, automated support for academic rebuttal, a crucial step in academic communication and peer review, remains largely underexplored. Existing approaches typically rely on off-the-shelf LLMs or simple pipelines, which struggle with long-context understanding and often fail to produce targeted and persuasive responses. In this paper, we propose DRPG, an agentic framework for automatic academic rebuttal generation that operates through four steps: Decompose reviews into atomic concerns, Retrieve relevant evidence from the paper, Plan rebuttal strategies, and Generate responses accordingly. Notably, the Planner in DRPG reaches over 98% accuracy in identifying the most feasible rebuttal direction. Experiments on data from top-tier conferences demonstrate that DRPG significantly outperforms existing rebuttal pipelines and achieves performance beyond the average human level using only an 8B model. Our analysis further demonstrates the effectiveness of the planner design and its value in providing multi-perspective and explainable suggestions. We also showed that DRPG works well in a more complex multi-round setting. These results highlight the effectiveness of DRPG and its potential to provide high-quality rebuttal content and support the scaling of academic discussions. Codes for this work are available at https://github.com/ulab-uiuc/DRPG-RebuttalAgent.

cs.LG↗

arXiv2025

Quadratic Band Touching and Nontrivial Winding Reveal Generalized Angular Momentum Conservation

Angular momentum conservation stands as one of the most fundamental and robust laws of physics. In discrete lattices, however, its realization can deviate markedly from the continuous case, especially in the presence of nontrivial momentum-space band touchings. Here, we investigate angular momentum conservation associated with quadratic band-touching points (QBTPs) in two-dimensional lattices. We show that, unlike in graphene lattices hosting linear band-touching points (LBTPs), the conventional angular momentum is no longer conserved near QBTPs. Instead, we identify a generalized total angular momentum (GTAM) that remains conserved for both LBTPs and QBTPs, inherently determined by the topological winding number at the band-touching point (BTP). Using a photonic Kagome lattice, we experimentally demonstrate GTAM conservation through pseudospin-orbital angular momentum conversion. Furthermore, we show that this conservation principle extends to a broad class of discrete lattices with arbitrary pseudospin textures and higher-order winding numbers. These results reveal a fundamental link between pseudospin, angular momentum, and topology, establishing a unified framework for angular-momentum dynamics in discrete systems.

physics.optics↗

arXiv2025

Spatial-spectral mapping for long-duration broadband terahertz pulse generation in on-chip waveguide arrays

Conventional approaches to terahertz (THz) pulse generation are restricted by the Fourier-transform limit, which hinders the creation of sources that combine long duration with broad bandwidth--a capability crucial for many spectroscopic and sensing applications. In this work, we overcome this challenge in the terahertz domain using an on-chip gradient waveguide array. The key is to spectrally disperse the pulse into spatially separated channels within a lithium niobate chip, effectively decoupling the design of temporal and spectral properties. We validate the source by distinguishing amino acid mixtures, demonstrating its tailored biosensing potential. This work establishes a novel mechanism for integrated THz generation, offering considerable promise for broadband spectroscopy and on-chip photonics.

physics.optics↗

arXiv2025

ResearchArcade: Graph Interface for Academic Tasks

Academic research generates diverse data sources, and as researchers increasingly use machine learning to assist research tasks, a crucial question arises: Can we build a unified data interface to support the development of machine learning models for various academic tasks? Models trained on such a unified interface can better support human researchers throughout the research process, eventually accelerating knowledge discovery. In this work, we introduce ResearchArcade, a graph-based interface that connects multiple academic data sources, unifies task definitions, and supports a wide range of base models to address key academic challenges. ResearchArcade utilizes a coherent multi-table format with graph structures to organize data from different sources, including academic corpora from ArXiv and peer reviews from OpenReview, while capturing information with multiple modalities, such as text, figures, and tables. ResearchArcade also preserves temporal evolution at both the manuscript and community levels, supporting the study of paper revisions as well as broader research trends over time. Additionally, ResearchArcade unifies diverse academic task definitions and supports various models with distinct input requirements. Our experiments across six academic tasks demonstrate that combining cross-source and multi-modal information enables a broader range of tasks, while incorporating graph structures consistently improves performance over baseline methods. This highlights the effectiveness of ResearchArcade and its potential to advance research progress.

cs.CL↗

arXiv2025

Lithium Niobate Vertical Cavity Electro-Optic Modulator

Electro-optic modulators (EOMs) are vital for optical imaging and information processing, with free-space devices enabling LiDAR and beam control. Lithium niobate (LN), powered by the strong Pockels effect and scalable LN-on-insulator (LNOI) platform, has become a leading material for high-performance EOMs. Here we realize a vertical-cavity EOM in which an LN membrane is sandwiched between two photonic crystal (PhC) mirrors with integrated electrodes. The cavity supports sharp defect-mode resonances that shift efficiently under the Pockels effect, enabling strong modulation of transmission. Experiments show a depth of 43 % at 50 V and a bandwidth of 5 MHz. This architecture combines free-space compatibility with fabrication simplicity, opening new routes to compact electro-optic platforms for ranging, holography, and beam steering.

physics.optics↗

arXiv2025

Local perfect chirality at reflection-zeros away from exceptional points in optical whispering gallery microcavity

Recently, a local and imperfect chirality of the resonant eigenmode at the exceptional point (EP) has been reported in the optical whispering gallery microcavity system perturbed by two strong nanoscatterers [Phys. Rev. A 108, L041501 (2023)]. Here, we discover a local perfect chirality of the resonant eigenmode away from the EP in the parameter space of the strongly perturbed microcavity system. By considering the multiple scattering process of the azimuthally propagating modes (APMs) at the nanoscatterers with a first-principles-based model, the local perfect chirality is predicted to result from the unidirectional reflectionlessness, i.e., the reflection-zero (R-zero) of the APMs at the two nanoscatterers. Numerical results and model predictions consistently show that the structural parameters of the R-zero typically deviate from those of the EP, which means that the pair of split resonant eigenmodes at the R-zero have different complex resonance frequencies and electromagnetic fields. In general, only one of the pair of split eigenmodes exhibits a local perfect chirality within the local azimuthal range divided by the two nanoscatterers. With the decrease of the two nanoscatterers' sizes or their relative azimuthal angle, the R-zero tends to coincide with the EP.

physics.optics↗

arXiv2024

Multi-topological phases of matter

The discovery of topological phases of matter and topological boundary states had tremendous impact on condensed matter physics and photonics, where topological phases are defined via energy bands, giving rise to topological band theory. However, topological systems that cannot be described by band topology but still support non-trivial boundary states are little-known and largely unexplored. Here, we uncover a new kind of topological phase of matter named "multi-topological phase" (MTP) that features multiple sets of boundary states, where each set is associated with one distinct topological invariant. Unlike conventional topological phase transitions, the MTP transitions can occur without band-gap closing. We present typical examples of MTPs in a one-dimensional topological insulator and a two-dimensional higher-order topological insulator, where the systems are otherwise trivial according to band topology. Furthermore, MTPs can exist also in indirectly gapped Chern insulators, beyond the regime where the conventional bulk-boundary correspondence predicts the existence of boundary states. Experimentally, we demonstrate the first two examples of MTPs in laser-written photonic lattices. Our findings constitute a fundamental advance in topological physics and provide a route for designing novel topological materials.

physics.optics↗

arXiv2024

Soft-Matter-Based Topological Vertical Cavity Surface Emitting Lasers

Polarized topological vertical cavity surface-emitting lasers (VCSELs), as stable and efficient on-chip light sources, play an important role in the next generation of optical storage and optical communications. However, most current topological lasers demand complex design and expensive fabrication processes, and their semiconductor-based structures pose challenges for flexible device applications. By use of an analogy with two-dimensional Semenov insulators in synthetic parametric space, we design and realize a one-dimensional optical superlattice (stacked polymerized cholesteric liquid crystal films and Mylar films), thereby we demonstrate a flexible, low threshold, circularly polarized topological VCSEL with high slope efficiency. We show that such a laser maintains a good single-mode property under low pump power and inherits the transverse spatial profile of the pump laser. Thanks to the soft-matter-based flexibility, our topological VCSEL can be "attached" to substrates of various shapes, enabling desired laser properties and robust beam steering even after undergoing hundreds of bends. Our results may find applications in consumer electronics, laser scanning and displays, as well as wearable devices.

physics.optics↗