arXiv subjects

Tianqi Zheng

Publications and source records attributed to Tianqi Zheng.

16 recordsLinked to original sources

arXiv2026

Closed-Loop Motion Planning for Differentially Flat Systems: A Time-Varying Optimization Framework

Motion planning and control are two core components of the robotic autonomy stack. The standard way to combine them uses an offline/open-loop stage, planning, which designs a feasible and safe trajectory, and an online/closed-loop stage, tracking, which corrects for unmodeled dynamics and disturbances. This separation introduces conservatism in planning that becomes difficult to overcome as model complexity increases and real-time decisions must be made in a changing environment. This work addresses these challenges for differentially flat nonlinear systems by integrating planning and control into a single closed-loop task. We develop an optimization-based framework that steers a flat system to a trajectory implicitly defined via a constrained time-varying optimization problem. Generalizing feedback linearization, our controllers effectively transform the flat system into an algorithm that seeks the optimal solution of the time-varying problem. Under sufficient regularity assumptions, we prove global asymptotic convergence to the time-varying minimizer. We illustrate the method on multi-robot tracking and robot obstacle avoidance problems.

eess.SY↗

arXiv2026

The World Won't Stay Still: Programmable Evolution for Agent Benchmarks

LLM-powered tool-calling agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Yet, most existing benchmarks evaluate these systems under static environment interfaces, with fixed schemas and toolsets, making it difficult to assess how agents behave as environments evolves -- when capabilities are added, reorganized, or deprecated across successive environment versions. In this paper, we study structured environment evolution as a benchmark-construction problem for tool-calling agents. We propose ProEvolve, a graph-based framework that makes environment evolution programmable. At its core, a typed relational graph provides a unified, explicit representation of the environment - data, tools, and schema. Under this formalism, adding, removing, or modifying capabilities are expressed as graph transformations that coherently propagate updates across tools, schemas, and data access. Building on this, ProEvolve supports (1) automatic generation of evolved executable environments through explicit graph transformations, and (2) graph-grounded construction of task sandboxes via subgraph sampling and instantiation. We validate ProEvolve in two tool-calling domains, e-commerce and airline booking, in terms of quality, implementation validity, and failure modes. Finally, we use the generated benchmark as a downstream diagnostic to study how representative agents behave under structured environment evolution.

cs.AI↗

arXiv2026

WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale

Reinforcement learning (RL) for web agents demands environments that are both effective for evaluation and efficient enough for large-scale on-policy training. Current web environments fall short: server-side Docker setups are too resource-intensive for massive parallel rollouts, while browser-side interfaces produce noisy observations, execute actions unreliably under modern single-page applications, and omit visual interactivity cues. We introduce WebServ, a full-stack, RL-ready web environment that addresses these limitations end-to-end. On the server side, WebServ uses Incus containers with block-level copy-on-write, reducing launch latency by ~5x and persistent storage by ~240x, enabling 200+ concurrent isolated environments on a single host. On the browser side, WebServ provides a compact, site-agnostic observation and action interface derived automatically from the DOM with human-aligned interactivity cues, and a robust action execution backend using network-aware waiting for reliable SPA support. On WebArena-Lite, WebServ achieves state-of-the-art single-prompt results, with controlled comparisons confirming consistent gains across GPT-4o, OpenAI-o3, and Llama-3.1-8B over vanilla WebArena. We further train Qwen3-4B and Qwen3-30B-A3B with RL entirely within WebServ; the RL-trained 4B model achieves 55.5% mean accuracy, surpassing both Claude 4.5 Sonnet (50.0%) and the RL-trained 8B model from WebAgent-R1 (51.8%).

cs.LG↗

arXiv2026

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs

Personalizing large language models (LLMs) to individual users requires incorporating extensive interaction histories and profiles, but input token constraints make this impractical due to high inference latency and API costs. Existing approaches rely on heuristic methods such as selecting recent interactions or prompting summarization models to compress user profiles. However, these methods treat context as a monolithic whole and fail to consider how LLMs internally process and prioritize different profile components. We investigate whether LLMs' attention patterns can effectively identify important personalization signals for intelligent context compression. Through preliminary studies on representative personalization tasks, we discover that (a) LLMs' attention patterns naturally reveal important signals, and (b) fine-tuning enhances LLMs' ability to distinguish between relevant and irrelevant information. Based on these insights, we propose Attn-GS, an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences, then guides a compression model to generate task-relevant, high-quality compressed user contexts. Extensive experiments demonstrate that Attn-GS significantly outperforms various baselines across different tasks, token limits, and settings, achieving performance close to using full context while reducing token usage by 50 times.

cs.CL↗

arXiv2025

Measurement-Incompatibility Constraints for Maximal Randomness

Certifying maximal quantum randomness without assumptions about system dimension remains a pivotal challenge for secure communication and foundational studies. Here, we introduce a generalized framework to directly certify maximal randomness from observed probability distributions across systems with arbitrary user numbers, without relying on the Bell-inequality violations. By analyzing probability distributions directly, we identify a class of quantum states and projective measurements that achieve maximal randomness in bipartite and tripartite scenarios, ensuring practical feasibility. Further analysis reveals a counterintuitive trade-off governing measurement incompatibility among users: sufficient incompatibility for one user permits arbitrarily small incompatibility for others, defying conventional symmetry assumptions in the Bell test. This asymmetry provides a pathway to optimize device-independent protocols by strategically distributing quantum resources. Our results establish a versatile and experimentally accessible route to scalable randomness certification, with implications for quantum cryptography and the physics of nonlocal correlations.

quant-ph↗

arXiv2025

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation

Multimodal Retrieval-Augmented Generation (MRAG) systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities. While text-based RAG privacy risks have been studied, multimodal data presents unique challenges. We provide the first systematic analysis of MRAG privacy vulnerabilities across vision-language and speech-language modalities. Using a novel compositional structured prompt attack in a black-box setting, we demonstrate how attackers can extract private information by manipulating queries. Our experiments reveal that LMMs can both directly generate outputs resembling retrieved content and produce descriptions that indirectly expose sensitive information, highlighting the urgent need for robust privacy-preserving MRAG techniques.

cs.CR↗

arXiv2025

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing methods designed to update certain knowledge in LLMs without changing unrelated others. To make selective edits, previous efforts often sought to update a small amount of parameters in some specific layer(s) of a LLM. Nonetheless, in challenging scenarios, they still fall short in making successful edits while preserving knowledge irrelevant to the updates simultaneously, resulting in a notable editing-locality trade-off. In this work, we question if the trade-offs are caused by the fact that parameter-based updates have a global effect, i.e., edited parameters affect all inputs indiscriminately. In light of this, we explore the feasibility of representation fine-tuning, which applied some linear update to a few representations in a learned subspace, for knowledge editing. While being effective to enhance an LLM's general ability as demonstrated in the previous work, we theoretically show that this linear update imposes a tension in editing-locality trade-off. Subsequently, BaFT is proposed to break the linearity. BaFT computes a weight for each basis that spans a dimension of the subspace based on the input representation. This input-dependent weighting mechanism allows BaFT to manage different types of knowledge in an adaptive way, thereby achieving a better editing-locality trade-off. Experiments on three LLMs with five editing benchmarks in diverse scenarios show the superiority of our method.

cs.CL↗

arXiv2025

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach

Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend to over-rely on external knowledge, making them vulnerable to misleading and unhelpful contexts. To address this, we propose the concept of context-robust LLMs, which can effectively balance internal knowledge with external context, similar to human cognitive processes. Specifically, context-robust LLMs should rely on external context only when lacking internal knowledge, identify contradictions between internal and external knowledge, and disregard unhelpful contexts. To achieve this goal, we introduce Grft, a lightweight and plug-and-play gated representation fine-tuning approach. Grft consists of two key components: a gating mechanism to detect and filter problematic inputs, and low-rank representation adapters to adjust hidden representations. By training a lightweight intervention function with only 0.0004\% of model size on fewer than 200 examples, Grft can effectively adapt LLMs towards context-robust behaviors.

cs.CL↗

arXiv2025

Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data

Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key contextual information from the original data. In the stage-2, we further enhance the privacy properties of the synthetic data through an agent-based iterative refinement process. Extensive experiments demonstrate that using our synthetic data as the retrieval context achieves comparable performance to using the original data while substantially reducing privacy risks. Our work takes the first step towards investigating the possibility of generating high-utility and privacy-preserving synthetic data for RAG, opening up new opportunities for the safe application of RAG systems in various domains.

cs.CR↗

arXiv2024

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective

Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM's internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. Motivated by the findings, we further develop representation-based classifiers for knowledge filtering. We show substantial improvements in RAG performance, even when dealing with noisy knowledge databases. Our study provides new insights into leveraging LLM representations for enhancing the reliability and effectiveness of RAG systems.

cs.LG↗

arXiv2024

AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset

Query Autocomplete (QAC) is a critical feature in modern search engines, facilitating user interaction by predicting search queries based on input prefixes. Despite its widespread adoption, the absence of large-scale, realistic datasets has hindered advancements in QAC system development. This paper addresses this gap by introducing AmazonQAC, a new QAC dataset sourced from Amazon Search logs, comprising 395M samples. The dataset includes actual sequences of user-typed prefixes leading to final search terms, as well as session IDs and timestamps that support modeling the context-dependent aspects of QAC. We assess Prefix Trees, semantic retrieval, and Large Language Models (LLMs) with and without finetuning. We find that finetuned LLMs perform best, particularly when incorporating contextual information. However, even our best system achieves only half of what we calculate is theoretically possible on our test data, which implies QAC is a challenging problem that is far from solved with existing systems. This contribution aims to stimulate further research on QAC systems to better serve user needs in diverse environments. We open-source this data on Hugging Face at https://huggingface.co/datasets/amazon/AmazonQAC.

cs.IR↗

arXiv2024

Dissipative Gradient Descent Ascent Method: A Control Theory Inspired Algorithm for Min-max Optimization

Gradient Descent Ascent (GDA) methods for min-max optimization problems typically produce oscillatory behavior that can lead to instability, e.g., in bilinear settings. To address this problem, we introduce a dissipation term into the GDA updates to dampen these oscillations. The proposed Dissipative GDA (DGDA) method can be seen as performing standard GDA on a state-augmented and regularized saddle function that does not strictly introduce additional convexity/concavity. We theoretically show the linear convergence of DGDA in the bilinear and strongly convex-strongly concave settings and assess its performance by comparing DGDA with other methods such as GDA, Extra-Gradient (EG), and Optimistic GDA. Our findings demonstrate that DGDA surpasses these methods, achieving superior convergence rates. We support our claims with two numerical examples that showcase DGDA's effectiveness in solving saddle point problems.

math.OC↗

arXiv2022

Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several algorithms rooted in sampled-based primal-dual methods have been recently proposed to solve this problem in policy space. However, such methods are based on stochastic gradient descent ascent algorithms whose trajectories are connected to the optimal policy only after a mixing output stage that depends on the algorithm's history. As a result, there is a mismatch between the behavioral policy and the optimal one. In this work, we propose a novel algorithm for constrained RL that does not suffer from these limitations. Leveraging recent results on regularized saddle-flow dynamics, we develop a novel stochastic gradient descent-ascent algorithm whose trajectories converge to the optimal policy almost surely.

cs.LG↗

arXiv2021

Inner Approximations of the Positive-Semidefinite Cone via Grassmannian Packings

We investigate the problem of finding inner ap-proximations of positive semidefinite (PSD) cones. We developa novel decomposition framework of the PSD cone by meansof conical combinations of smaller dimensional sub-cones. Weshow that many inner approximation techniques could besummarized within this framework, including the set of (scaled)diagonally dominant matrices, Factor-widthkmatrices, andChordal Sparse matrices. Furthermore, we provide a moreflexible family of inner approximations of the PSD cone, wherewe aim to arrange the sub-cones so that they are maximallyseparated from each other. In doing so, these approximationstend to occupy large fractions of the volume of the PSD cone.The proposed approach is connected to a classical packingproblem in Riemannian Geometry. Precisely, we show thatthe problem of finding maximally distant sub-cones in anambient PSD cone is equivalent to the problem of packingsub-spaces in a Grassmannian Manifold. We further leverageexisting computational method for constructing packings inGrassmannian manifolds to build tighter approximations ofthe PSD cone. Numerical experiments show how the proposedframework can balance between accuracy and computationalcomplexity, to efficiently solve positive-semidefinite programs.

math.OC↗

arXiv2020

Implicit Trajectory Planning for Feedback Linearizable Systems: A Time-varying Optimization Approach

We develop an optimization-based framework for joint real-time trajectory planning and feedback control of feedback-linearizable systems. To achieve this goal, we define a target trajectory as the optimal solution of a time-varying optimization problem. In general, however, such trajectory may not be feasible due to , e.g., nonholonomic constraints. To solve this problem, we design a control law that generates feasible trajectories that asymptotically converge to the target trajectory. More precisely, for systems that are (dynamic) full-state linearizable, the proposed control law implicitly transforms the nonlinear system into an optimization algorithm of sufficiently high order. We prove global exponential convergence to the target trajectory for both the optimization algorithm and the original system. We illustrate the effectiveness of our proposed method on multi-target or multi-agent tracking problems with constraints.

eess.SY↗

arXiv2019

Kaleido: An Efficient Out-of-core Graph Mining System on A Single Machine

Graph mining is one of the most important categories of graph algorithms. However, exploring the subgraphs of an input graph produces a huge amount of intermediate data. The 'think like a vertex' programming paradigm, pioneered by Pregel, cannot readily formulate mining problems, which is designed to produce graph computation problems like PageRank. Existing mining systems like Arabesque and RStream need large amounts of computing and memory resources. In this paper, we present Kaleido, an efficient single machine, out-of-core graph mining system which treats disks as an extension of memory. Kaleido treats intermediate data in graph mining tasks as a tensor and adopts a succinct data structure for the intermediate data. Kaleido utilizes the eigenvalue of the adjacency matrix of a subgraph to efficiently solve the subgraph isomorphism problems with an acceptable constraint that the vertex number of a subgraph is less than 9. Kaleido implements half-memory-half-disk storage for storing large intermediate data, which treats the disk as an extension of the memory. Comparing with two state-of-the-art mining systems, Arabesque and RStream, Kaleido outperforms them by a GeoMean 12.3$\times$ and 40.0$\times$ respectively.

cs.DC↗