Searcharxiv⌕ Search

arXiv subjects

Jingyu Liu

Publications and source records attributed to Jingyu Liu.

At least 19 recordsLinked to original sources

RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn't

Agentic memory research has accumulated extraction, supersession, reflection, and graph synthesis on top of retrieval-augmented generation. However, we found that almost none of those primitives earn their cost in our tested memory benchmarks: we show this with BRIDGE, a deliberately minimal RAG memory with chained observation notes, hybrid BM25 with cosine retrieval, and chronological rendering, which reaches parity within bootstrap CI with the prior SOTA on LongMemEval-S and BEAM, and beats the best memory baseline on EverMemBench by 5.7-6.3 points at matched reader. It runs at ~5-7K reader-prompt tokens per query, using a single LLM call for each ingestion or query. We argue that this parity is itself the result: standard benchmarks score what memory retrieves, not what memory enables when the agent acts. To test the latter, we introduce five adversarial probes (Rule Application +-, Pattern Induction Style / Procedural, Dynamic Multiturn) judged at generation time by a cross vendor verification chain, where each query can only be solved by applying a remembered rule or pattern it never mentions. Across 5 probes x 20 scenarios, no architecture wins universally: atomic fact extractors (LangMem) win rule application, while BRIDGE's block-summary memory wins pattern induction. This result holds across four domains, three graders, and three reader families. Each design fails where the other wins, for reasons a recall benchmark cannot see: atomic-fact extractors discard the form a demonstrated pattern takes, while block-summary memory retrieves the rule but the reader does not act on it, a gap that presenting the rule more prominently largely closes. What separates memory designs is not what they retrieve but what they enable an agent to do, and that is what agentic memory should be evaluated on.

cs.AI↗

Singularity-Bench: Can Agents Build Agents?

Frontier AI agents increasingly succeed on realistic, long-horizon tasks and are beginning to improve the systems through which they operate. Yet existing benchmarks often restrict agents to narrow action spaces, use simplified environments, or rely on verification methods that are unreliable for evaluating arbitrary agent-generated systems. We introduce Singularity-Bench, an open-ended benchmark for autonomous AI development with six end-to-end tasks spanning pre-training, mid-training, post-training, inference, the agent harness, and cluster orchestration. Each task requires agents to implement core systems from a minimal starting point and evaluates them against mature human-engineered baselines on identical hardware. Additionally, through extensive red-teaming covering 9 of the 10 categories in the OWASP Top 10 for Agentic Applications, we expose reward-hacking vulnerabilities in the conventional Harbor framework and develop Breakwater, an extension of Harbor that blocks all attacks tested in our study. Across 11 agents built from 7 frontier models and 2 harnesses, Opus 5.5 with Claude Code matches or outperforms the human baseline on all six tasks with a Singularity-Index of 1.25, suggesting it may have the skills needed to reach the singularity. The remaining agents average only 0.60. Our vision is for Singularity-Bench to track how much of AI development agents can already automate and when they may transition from assisting to taking end-to-end responsibility for building stronger successors.

cs.AI↗

Agile Monoped Hopping on Complex and Discrete Terrain via Kinodynamic Planning with Distilled MPPI Steering

This paper presents FlowRRT, a kinodynamic planner for agile monoped hopping on discrete terrain. Steering for kinodynamic RRT on complex dynamical systems currently relies on motion primitives or closed-loop policies, limiting the diversity of motions or the planning speed. Distilling a trajectory optimizer avoids both, but existing methods regress a single solution per query, which fails on monoped hopping, where the feasible action set is narrow and disconnected. Our key insight is to treat steering as set-valued and predict the distribution of feasible actions instead. A multi-start MPPI expert collects the entire feasible set of each query offline, and conditional flow matching distills it into a generative sampler. With this sampler, FlowRRT coordinates successive jumps over long horizons and finds non-greedy maneuvers that are hard for reactive policies to discover. Benchmarks across different terrains show higher success rates and substantially shorter planning times than sampling-based baselines. On terrains with inclined platforms, FlowRRT reaches $80\%$ success within $1$~s, versus $24$~s for RL-RRT and $77$~s for SST. Sim-to-sim tracking in MuJoCo confirms accurate execution under full-order dynamics.

cs.RO↗

A Superfast Direct Solver for Type-III Inverse Nonuniform Discrete Fourier Transform

Various fields in scientific computing require the use of the nonuniform discrete Fourier transform (NUDFT) and its inversion. In [H. Wilber, E. N. Epperly, and A. H. Barnett, SIAM J. Sci. Comput., 47 (2025), pp. A1702-A1732], the authors proposed a direct inversion method for the type-II NUDFT, which achieves quasi-linear complexity by approximating the type-II NUDFT matrix as a product of a hierarchical semiseparable (HSS) matrix and a DFT matrix. In this article, we propose a novel superfast direct inversion method for type-III NUDFT. The proposed method approximates the type-III NUDFT matrix as a product of a type-II NUDFT matrix and an HSS matrix. This decomposition enables both the forward application and the backward inversion to be accomplished with quasi-linear complexity. The fast inversion can serve as a high-accuracy direct solver or as an efficient preconditioner. Additionally, we provide an error bound for the approximation when the sample points are independent and identically distributed uniform random variables and the frequencies are perturbed continuous integers. Numerical results are presented to verify the relevant theoretical properties and demonstrate the efficiency of the proposed methods.

math.NA↗

Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

The brain uses discrete spikes for dynamic computation, yet in the fields of computational neuroscience and brain-inspired computing, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. In order to integrate seemingly incompatible spike timing and continuous gradients, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computational theory for the brain's temporal credit assignment mechanisms.

cs.NE↗

Your Trust, Your Terms: A General Paradigm for Near-Instant Cross-Chain Transfer

Cross-chain transactions today remain slow, costly, and fragmented. Existing custodial exchanges expose users to counterparty and centralization risks, while non-custodial liquidity bridges suffer from capital inefficiency and slow settlement; critically, neither approach guarantees users a unilateral path to recover assets if the infrastructure fails. We introduce the Delegated Ownership Transfer (DOT) paradigm, which decouples key ownership from value ownership to enable secure, high-performance cross-chain payments. In DOT, a user deposits funds into a sandboxed on-chain Temporary Account (TA) (value ownership) while delegating its private key (key ownership) to an abstract Trusted Entity (TE). Payments and swaps are thus reframed as near-instant, off-chain ownership handoffs. Security follows from dual guarantees: the TE's exclusive control prevents double-spending, while a pre-signed, unilateral recovery transaction ensures users retain ultimate authority over their assets. Building on this foundation, we design a novel off-chain atomic swap that executes optimistically in near real time and remains fair even if the TE fails. We formalize the security of DOT in the Universal Composability framework and present two concrete instantiations: a high-performance design based on Trusted Execution Environments (TEEs) and a cryptographically robust variant leveraging threshold cryptography. Our geo-distributed prototype shows that cross-chain payments complete in under 16.70 ms and atomic swaps in under 33.09 ms, with costs fully decoupled from Layer-1 gas fees. These results provide a practical blueprint for building secure, efficient, and interoperable cross-chain payment systems.

cs.CR↗

Hierarchical Matrices with Tucker Blocks: Construction and Forward Evaluation

In this paper, we introduce hierarchical matrices with Tucker blocks (HMTB) for data-sparse approximation of matrices arising from nonoscillatory and mildly oscillatory kernels. Building on the hierarchical matrix framework, HMTB matrices replace conventional low-rank blocks with Tucker representations. Using high-dimensional interpolation and tensor compression and contractions, we develop algorithms for constructing HMTB matrices and performing matrix-vector multiplication. For an $N \times N$ matrix, these algorithms have linear and quasi-linear complexities in $N$, respectively. Numerical comparisons with an interpolation-based $\mathcal{H}$-matrix implementation demonstrate storage savings and, in several cases, reduced construction times, while maintaining competitive forward-evaluation costs. The framework is also applicable to quasi-uniform grids.

math.NA↗

Expression of White and Gray Matter Autism Functional Network Connectivity Signatures in Infancy

Functional connectivity studies have provided valuable insights into altered brain organization in autism spectrum disorder (ASD). However, most functional connectivity studies focus exclusively on either gray matter (GM) regions or white matter (WM) tracts and examine specific age groups, rather than investigating their functional interactions across brain development. This limits our understanding of how GM-WM functional interactions evolve developmentally and may obscure important aspects of brain network organization in ASD. We combined integrated WM+GM functional network connectivity (FNC) with brain-wide risk scores (BRSs) to quantify ASD-associated pattern expression in ABIDE I/II and an independent infant cohort. We employed a NeuroMark framework with predefined WM and GM intrinsic connectivity networks templates, to estimate subject-level FNC. First, we identified two distinct patterns of altered WM+GM FNC in ASD: GM-related hypoconnectivity centered on the paralimbic network and WM-GM hyperconnectivity centered on the frontal network. These findings highlight the involvement of higher-order cognitive networks and the importance of WM-GM functional interactions in characterizing ASD-related connectivity alterations. Second, infants with a higher familial likelihood of autism exhibited greater mean expression of ASD-associated FNC patterns than those with a lower familial likelihood, as quantified by BRS. These group-level findings do not establish developmental persistence or predict diagnostic outcomes at the individual level.

q-bio.NC↗

Sketch-and-Restart: Randomized Sketching in Quadrature-Based Restarting for Matrix Functions

We develop a sketch-and-restart framework for computing the action of a matrix function on a vector, $f(A) b$, where $A$ is large, sparse, and non-Hermitian. The framework combines quadrature-based restarting with Arnoldi-like decompositions generated by sketched or truncated Arnoldi processes. Within this framework, we develop two classes of restarted algorithms. The first uses a fixed Krylov subspace dimension and is based either on the sketched Arnoldi process or on a new sketched harmonic Arnoldi process proposed in this work. The second class chooses the Krylov subspace dimension adaptively by running the truncated Arnoldi process until the condition number of the generated basis, estimated from its sketch, exceeds a prescribed threshold. We also establish the convergence of the restarted sketched harmonic Arnoldi method for Stieltjes functions under the assumption that $A$ is positive real. Numerical experiments demonstrate the effectiveness of the proposed framework, including the computational savings achieved through sketching, the storage reduction enabled by adaptive truncation, and the acceleration obtained from thick restarting.

math.NA↗

A Multi-Asset Dataset and Tail-Risk Framework for DeFi Yield Trading Derivatives

Yield trading has emerged as a pivotal innovation in Decentralized Finance (DeFi) by decoupling principal from yield streams to enhance capital efficiency. Despite its significance, the field lacks fine-grained datasets for systematic empirical analysis. We address this gap by constructing the first large-scale benchmark dataset for Pendle, the pioneering on-chain interest rate derivatives protocol, spanning 24 months across 340 active markets with complete lifecycle observations. Our analysis reveals a structural market transition toward stablecoin-dominated "flight-to-quality" dynamics. To tackle the heavy-tailed nature of yield data, we propose Tail-MSE, an asymmetric loss function that prioritizes tail risk awareness through dynamic penalty weighting. Experiments across six state-of-the-art time series models demonstrate consistent improvements in volatility forecasting robustness, enabling the Tail-MSE Sniper strategy to achieve superior risk-adjusted returns in over half of all markets.

cs.CE↗

TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback

Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajectory-Adaptive Classifier-Free Guidance (TrajCFG), a training-free method for flow-matching models that adapts token-wise guidance using historical changes in guided velocity direction. TrajCFG maps this feedback to bounded scales, assigning stronger guidance to larger directional changes and weaker guidance to more consistent directions. It combines adjacent-step and interval-normalized longer-span feedback, reusing standard CFG predictions without additional model evaluations. Controlled diagnostics and ablations examine the roles of directional feedback, token-wise allocation, and history-span fusion. Experiments on text-to-video, image-to-video, text-to-audio-video, text-to-image, and image-to-3D generation show improvements over base samplers across multiple backbones. For text-to-video generation, TrajCFG improves VBench Total scores by 0.30-0.75 points over the strongest evaluated baseline on each of three backbones. These results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation. The project page is available at https://jyliu-98.github.io/trajcfg-project-page/.

cs.CV↗

Diagnosing Task Insensitivity in Language Agents

Language agents select actions based on task descriptions, environmental observations, and interaction histories. We investigate whether task requirements reliably constrain these decisions when the surrounding context already suggests how to proceed. Across five models and three interactive environments, we find that models, including GPT-5.6-Sol, can continue to act when task descriptions are replaced with the meaningless placeholder xxxx, even when prompted to ask for clarification. Action generation is more frequent in states that suggest a concrete next operation, although these cues do not establish whether that operation serves the user's goal. These findings suggest a possible training-based explanation: contextual cues can make demonstrated responses predictable, allowing models to fit them with limited reliance on task requirements. Tracking seven models during fine-tuning, we observe an overall decrease in attention to task-description tokens and an increase in attention to current observations. To strengthen task dependence, we introduce Task-Perturbed Negative Log-Likelihood (TPNLL), which contrasts the prediction costs of the same response under different task descriptions while holding the non-task context fixed. TPNLL increases attention to task-description tokens and improves complete-episode success in out-of-distribution settings.

cs.AI↗

Real-Arithmetic Sketched Eigensolvers for Symmetric Matrices

In this work, we develop sketched variants of subspace iteration and TraceMIN, called sSI and sTraceMIN, for real symmetric eigenvalue problems by combining basis whitening with the sketched Rayleigh-Ritz (sRR) procedure. The nonsymmetric projected matrix in sRR may have nonreal eigenpairs, leading to complex arithmetic and additional computational costs. We overcome this difficulty using a real Schur formulation of sRR that keeps the iterations in real arithmetic. We further develop procedures for characteristic subspace selection and convergence monitoring within this formulation. On the theoretical side, we discuss suitable subspace embedding assumptions for sketched eigensolvers that use a fixed sketching matrix throughout the iterations. Under a mild embedding assumption, we establish local convergence results for sSI and sTraceMIN. Numerical experiments demonstrate runtime savings of up to 39% for sSI and 21% for sTraceMIN relative to their standard counterparts on the test problems.

math.NA↗

SEIS: Self-Evolving Inference Systems

Inference systems determine how fast and how cheaply language models can be served, so making them faster has direct practical value. However, prior work focuses mostly on optimizing certain parts such as kernels or memory within the large system. In this work, we take a holistic approach and apply agentic self-evolution to optimize the whole system end-to-end. Our SEIS (Self-Evolving Inference Systems) autonomously optimizes the entire mini-sglang engine without human intervention through iterative sessions with inherited experiences and code changes. Serving Qwen3-0.6B on H100, the resulting engine reaches 3.27X the throughput of the original mini-sglang implementation and beats SOTA engines like vLLM, TensorRT-LLM, and SGLang in the single-request workload. The correctness of the optimized inference engine by SEIS is tested in terms of numerical difference and downstream accuracy on math and long-context retrieval tasks. The code and session histories show that the speedup comes from redesigning the whole engine and that building on earlier sessions beats independent attempts. These results suggest that agentic self-evolution can optimize a complex system end-to-end. The evaluation also has to evolve with the engine, and letting agents evolve it is a natural next step.

cs.AI↗

When History Fails to Become Experience: Action Calibration in Language Agents

Language agents should draw on prior attempts and environmental feedback to improve subsequent decisions within the same task. However, providing additional interaction history can sometimes reduce task success, suggesting that agents do not consistently use this information effectively. To investigate this limitation, we examine how agents use history. We find that history improves task completion overall, yet much of this benefit persists even when past actions are shuffled. Disrupting the correspondence between actions and observations causes only a modest decline in task success. We therefore hypothesize that agents do not reliably connect past actions with their outcomes when deciding how to proceed. To test this hypothesis, we explicitly label each returned observation as the outcome of the preceding action. This simple annotation improves task success and reduces next-action repetition without introducing new environmental information. Building on this insight, we introduce a learned calibrator that explicitly reassesses past actions and selectively records experience to guide subsequent decisions, improving task success beyond outcome labeling alone.

cs.CL↗

A Superfast Direct Solver for 2D Type-II Inverse Nonuniform Discrete Fourier Transform Based on Hierarchically Semiseparable Matrices

Reconstructing images on Cartesian grids from nonuniform Fourier samples is a basic computational task in Fourier reconstruction methods for computed tomography. This paper proposes a direct solver for the 2D type-II nonuniform discrete Fourier transform~(NUDFT) based on the face-splitting product of hierarchically semiseparable~(HSS) matrices. We define the face-splitting product of two HSS trees and prove that the face-splitting product of two HSS matrices admits an HSS representation on the resulting tree. The proof is constructive, providing explicit formulas for the HSS generators and bounds on the off-diagonal ranks at each level. For the NUDFT, a Fourier change of basis expresses the transformed 2D matrix as a face-splitting product of two transformed 1D NUDFT matrices. This identity yields an algebraic construction of a 2D HSS approximation from two 1D HSS approximations, for which we establish a Frobenius-norm approximation error bound. Combining this construction with recompression, URV factorization, and a two-dimensional inverse fast Fourier transform gives a direct solver for the associated least-squares problem. For fixed accuracy, square frequency grids, and balanced HSS trees with fixed leaf column sizes, the solver has an offline complexity of $O(M \log^{2} N + N^{3 / 2} \log^{3} N)$ and an online complexity of $O(M + N \log^{3} N)$ per right-hand side, where $M$ and $N$ are the numbers of sample points and unknown coefficients, respectively. Numerical experiments on random and polar grids illustrate the computational scaling and reconstruction accuracy of the method, and demonstrate a substantial reduction in lsqr iteration counts when the direct solver is used as a preconditioner.

math.NA↗

World-Action Models for Robot Learning and Control: A Survey

Robots operating in open environments act under partial observability, physical constraints, and dynamic task contexts. Beyond mapping observations and language instructions to actions, they must anticipate how candidate actions may affect future states and task-relevant outcomes. Recent advances in world models, video generation, and Vision-Language-Action (VLA) policies have motivated the development of World-Action Models (WAMs), which couple future world prediction with executable action generation. This survey provides a robotics-oriented review of WAMs. We clarify their scope relative to conventional world models, model-based reinforcement learning, action-conditioned video generation, and reactive VLA policies, and organize existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. We further review applications of WAMs in manipulation, navigation, and autonomous driving, and we summarize the datasets, benchmarks, metrics, and protocols used to evaluate WAM systems. Finally, we discuss key challenges in action alignment, world-action factorization, spatial and multi-view consistency, long-horizon memory, neural simulation for closed-loop policy learning, and efficient inference. Taken together, this survey aims to provide a concise technical foundation for integrating predictive world modeling with action generation, toward more reliable embodied robot intelligence. Project page: https://rcl-robotics.github.io/Awesome-World-Action-Models.

cs.RO↗

Approximate Inversion of Discrete Fourier Integral Operators via Hierarchically Semiseparable Matrices

This paper introduces a novel method for approximating the inverse of discrete Fourier integral operators (FIOs). Given an $N \times N$ matrix representation $K$ of an FIO, the proposed algorithm consists of two stages. In the offline stage, we first construct a butterfly factorization (BF) $\tilde{K}$ of $K$, which enables fast forward matrix-vector multiplication. We then construct a hierarchically semiseparable (HSS) approximation $\tilde{G} \approx G$, where $G = K^{*} K$, using fast applications of $\tilde{K}$ and $\tilde{K}^{*}$ to random matrices. Finally, we apply the ULV factorization to the HSS matrix $\tilde{G}$ to obtain an approximation $\tilde{F} \approx G^{-1}$. Combining these approximations yields an approximate inverse $K^{-1} \approx \tilde{F} \tilde{K}^{*}$. The offline stage has complexity $O(N \log^{2} N)$ for 1D problems and $O(N^{1.5} \log N)$ for 2D problems. In the online stage, the proposed method approximates $K^{-1} u$ for a given input vector $u$ with complexity $O(N \log N)$ for both 1D and 2D problems. The proposed method can be used either as a direct solver or as a preconditioner for iterative methods. Numerical results for 1D and 2D FIOs demonstrate the effectiveness of the proposed method.

math.NA↗