arXiv subjects

Cong Shen

Publications and source records attributed to Cong Shen.

At least 19 recordsLinked to original sources

arXiv2026

SpecMind: Enabling Spectrum Intelligence via Multi-Agent Hybrid Retrieval-Augmented Generation

The exponential growth of wireless devices is driving unprecedented spectrum demand, pushing spectrum management toward more fine-grained decisions across space, time, and device constraints. As a result, spectrum policymakers and engineers must process large volumes of data that come from diverse sources and take many different forms, such as text and tables. These data sources are often disaggregated and require significant time and effort to integrate, search, and interpret. Furthermore, most of this information is formatted for human understanding and is not readily accessible to automated systems. To address this challenge, we propose SpecMind, a novel Multi-Agent Retrieval-Augmented Generation (RAG) system for spectrum intelligence that performs reasoning over heterogeneous data sources. This system enables autonomous agents to coordinate specialized sub-agents that retrieve and synthesize knowledge across policy proceedings, legal regulations, and license databases. We develop SpecBench, a question and answer (Q&A) dataset based on real-world license records and policy proceedings, addressing the lack of evaluation resources for RAG systems in the spectrum domain. Experimental results demonstrate that SpecMind outperforms traditional, general-purpose RAG systems across spectrum-related tasks, achieving over 80% win rate against strong baselines. The agent-based design enables more accurate retrieval, better contextual reasoning, and improved task completion across diverse query types.

cs.AI↗

arXiv2026

Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management

This paper develops a hybrid offline-online multi-agent reinforcement learning framework based on decision transformers. The policy is first pretrained offline via supervised sequence modeling of trajectories generated by existing policies, providing a safe and sample-efficient initialization. It is then fine-tuned online using a hybrid objective that incorporates critic-guided gradients, enabling performance improvements beyond the offline policy. To facilitate stable offline-to-online transfer and effective multi-agent coordination, the framework incorporates return-weighted sampling, a critic conditioned on neighbors' actions, and neighborhood-correlated exploration. The approach is fully distributed: both training and execution rely only on local observations and limited information exchange among neighboring agents. Evaluations with dynamic traffic arrivals in two settings: (i) joint scheduling and power allocation and (ii) coordinated beamforming, show that the proposed method achieves quality-of-service (QoS) performance comparable to centralized methods. Moreover, when pretrained on lower-quality datasets, online fine-tuning is also observed to surpass the initial offline policy. These results demonstrate a promising learning-based alternative for wireless resource management.

eess.SY↗

arXiv2026

SheafIQ: Sheaf-Theoretic Information Quantification of Vector Fields on Geometric Graphs

Vector fields on graph structures naturally arise in diverse biological and engineered systems, where vector-valued states are defined on the nodes and evolve through the network interactions. Existing methods primarily characterize either the graph topology or individual signals, but generally do not quantify how local interactions among node-associated vectors are organized across the graph. To address this limitation, a sheaf-theoretic framework, termed SheafIQ, is proposed to represent neighboring vectors in a common edge-associated coordinate system, map local incompatibilities to a residual energy distribution, and quantify its global organization through entropy. Across proteins, functional brain networks, urban traffic systems, and power grids, SheafIQ consistently reveals complementary organizational information beyond conventional graph- and signal-based descriptors. More broadly, it establishes a unified information-theoretic framework for quantifying the organization of vector-valued states on geometric graphs, extending network analysis beyond graph topology alone.

cs.IT↗

arXiv2026

The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory

Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update without checking whether it improves future behavior. As a result, updates that help the current task may overwrite useful knowledge, introduce over-specific rules, or bias the final memory toward recent examples. We propose Janus, a plug-in memory controller that decides whether to accept a candidate memory update or retain the previous memory. To make this decision efficient, Janus uses a Memory Momentum Trigger to identify suspicious deviations in the memory-update trajectory, and compares old and new memories on a compact hybrid evaluation set of coverage, boundary, and fresh tasks instead of replaying the full history. Janus is method-agnostic and wraps existing updaters without changing their update rules. Across six datasets, two backbone LLMs, and two memory updaters, Janus improves average accuracy by +2.7 to +4.6 points over the corresponding base updaters.

cs.AI↗

arXiv2026

A Boolean-Lattice Perspective for All-Loop Two-Site Cosmological Wavefunction

We revisit the shifted-tree decomposition formula proposed in our previous work arXiv:2410.17192 for two-site cosmological wavefunction coefficients. For the two-site bubble-like family at arbitrary loop order, we show that the nontrivial central part of the decomposition reduces to an alternating subset sum over shifted diagonal divisors. This subset sum is naturally organized by the Boolean lattice associated with the internal energies, and can be rewritten as a product of commuting finite-difference operators acting on a seed divisor. The finite-difference form first gives a vertex expansion on the Boolean lattice and then leads to an equivalent maximal-chain expansion over complete filtrations from the empty subset to the full set of internal energies. We prove this maximal-chain formula in two complementary ways. Algebraically, the identity follows from a telescoping relation for products of shifted divisors. Geometrically, the finite-difference expression is represented by a cubical integral over the Boolean cube, while the maximal-chain expansion gives its simplex decomposition. After restoring the common two-site prefactor, this maximal-chain expansion reproduces the tubing representation of the loop-level wavefunction coefficient. Thus the shifted-tree decomposition and the tubing construction are two realizations of the same Boolean-lattice identity, providing a concrete geometric interpretation of the all-loop two-site formula.

hep-th↗

arXiv2026

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits

Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines, establishing a principled and efficient framework for multi-objective prompt optimization.

cs.LG↗

arXiv2026

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory

Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluations of LLM memory mostly rely on aggregate metrics such as final hold-out accuracy or cumulative online performance, which can obscure critical failure modes such as forgetting and negative transfer. In this paper, we introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving LLM memory. Drawing inspiration from continual learning, it targets a test-time setting in which memory is external, prompt-mediated, and updated without modifying model parameters. Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference. Specifically, it measures online utility, hold-out generalization, backward transfer, and forgetting, providing a finer-grained view of memory quality. Through extensive experiments across diverse tasks and memory methods, we show that higher final or cumulative accuracy does not necessarily imply better memory quality: many methods exhibit strong performance gains while suffering from substantial forgetting or negative transfer. Moreover, different memory designs exhibit distinct trade-offs between adaptability and stability that remain invisible under standard evaluation metrics.

cs.LG↗

arXiv2026

$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun exploring alternative divergences (e.g., forward KL, chi-squared) as regularizers in RLHF. However, a unified theoretical understanding of general $f$-divergence regularization remains under-explored. To fill this gap, this work develops a comprehensive theoretical framework for online RLHF with a general $f$-divergence regularized objective. Rather than treating each possible divergence function individually, we adopt a holistic perspective across the entire function class and propose two algorithms based on distinct sampling principles. The first extends the classical optimism principle with a carefully designed exploration bonus, while the second introduces a new method that exploits the sensitivity of the optimal policy to reward perturbations under $f$-divergence regularization. Theoretical analysis shows that $O(\log T)$ regret and $O(1/T)$ sub-optimality gap are achievable, establishing provable efficiency of both algorithms and, to the best of our knowledge, the first performance bounds for online RLHF under general $f$-divergence regularization.

cs.LG↗

arXiv2026

HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings

Traditional Differential Privacy (DP) mechanisms are typically tailored to specific analysis tasks, which limits the reusability of protected data. DP tabular data synthesis overcomes this by generating synthetic datasets that can be shared for arbitrary downstream tasks. However, existing synthesis methods predominantly assume centralized or local settings and overlook the more practical horizontal federated scenario. Naively synthesizing data locally or perturbing individual records either produces biased mixtures or introduces excessive noise, especially under heterogeneous data distributions across participants. We propose HeteroFedSyn, the first DP tabular data synthesis framework designed specifically for the horizontal federated setting. Built upon the PrivSyn paradigm of 2-way marginal-based synthesis, HeteroFedSyn introduces three key innovations for distributed marginal selection: (i) an L2-based dependency metric with random projection for noise-efficient correlation measurement, (ii) an unbiased estimator to correct multiplicative noise, and (iii) an adaptive selection strategy that dynamically updates dependency scores to avoid redundancy. Extensive experiments on range queries, Wasserstein fidelity, and machine learning tasks show that, despite the increased noise inherent to federated execution, HeteroFedSyn achieves utility comparable to centralized synthesis. Our code is open-sourced via the link.

cs.CR↗

arXiv2026

Following the Diagnostic Trace: Visual Cognition-guided Cooperative Network for Chest X-Ray Diagnosis

Computer-aided diagnosis (CAD) has significantly advanced automated chest X-ray diagnosis but remains isolated from clinical workflows and lacks reliable decision support and interpretability. Human-AI collaboration seeks to enhance the reliability of diagnostic models by integrating the behaviors of controllable radiologists. However, the absence of interactive tools seamlessly embedded within diagnostic routines impedes collaboration, while the semantic gap between radiologists' decision-making patterns and model representations further limits clinical adoption. To overcome these limitations, we propose a visual cognition-guided collaborative network (VCC-Net) to achieve the cooperative diagnostic paradigm. VCC-Net centers on visual cognition (VC) and employs clinically compatible interfaces, such as eye-tracking or the mouse, to capture radiologists' visual search traces and attention patterns during diagnosis. VCC-Net employs VC as a spatial cognition guide, learning hierarchical visual search strategies to localize diagnostically key regions. A cognition-graph co-editing module subsequently integrates radiologist VC with model inference to construct a disease-aware graph. The module captures dependencies among anatomical regions and aligns model representations with VC-driven features, mitigating radiologist bias and facilitating complementary, transparent decision-making. Experiments on the public datasets SIIM-ACR, EGD-CXR, and self-constructed TB-Mouse dataset achieved classification accuracies of 88.40%, 85.05%, and 92.41%, respectively. The attention maps produced by VCC-Net exhibit strong concordance with radiologists' gaze distributions, demonstrating a mutual reinforcement of radiologist and model inference. The code is available at https://github.com/IPMI-NWU/VCC-Net.

cs.CV↗

arXiv2026

Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning

Split Federated Learning (SFL) enables collaborative training between resource-constrained edge devices and a compute-rich server. Communication overhead is a central issue in SFL and can be mitigated with auxiliary networks. Yet, the fundamental client-side computation challenge remains, as back-propagation requires substantial memory and computation costs, severely limiting the scale of models that edge devices can support. To enable more resource-efficient client computation and reduce the client-server communication, we propose HERON-SFL, a novel hybrid optimization framework that integrates zeroth-order (ZO) optimization for local client training while retaining first-order (FO) optimization on the server. With the assistance of auxiliary networks, ZO updates enable clients to approximate local gradients using perturbed forward-only evaluations per step, eliminating memory-intensive activation caching and avoiding explicit gradient computation in the traditional training process. Leveraging the low effective rank assumption, we theoretically prove that HERON-SFL's convergence rate is independent of model dimensionality, addressing a key scalability concern common to ZO algorithms. Empirically, on ResNet training and language model (LM) fine-tuning tasks, HERON-SFL matches benchmark accuracy while reducing client peak memory by up to 64% and client-side compute cost by up to 33% per step, substantially expanding the range of models that can be trained or adapted on resource-limited devices.

cs.LG↗

arXiv2025

Tele-LLM-Hub: Building Context-Aware Multi-Agent LLM Systems for Telecom Networks

This paper introduces Tele-LLM-Hub, a user friendly low-code solution for rapid prototyping and deployment of context aware multi-agent (MA) Large Language Model (LLM) systems tailored for 5G and beyond. As telecom wireless networks become increasingly complex, intelligent LLM applications must share a domainspecific understanding of network state. We propose TeleMCP, the Telecom Model Context Protocol, to enable structured and context-rich communication between agents in telecom environments. Tele-LLM-Hub actualizes TeleMCP through a low-code interface that supports agent creation, workflow composition, and interaction with software stacks such as srsRAN. Key components include a direct chat interface, a repository of pre-built systems, an Agent Maker leveraging finetuning with our RANSTRUCT framework, and an MA-Maker for composing MA workflows. The goal of Tele-LLM-Hub is to democratize the design of contextaware MA systems and accelerate innovation in next-generation wireless networks.

cs.NI↗

arXiv2025

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or specialized information. A natural strategy to increase the likelihood of retrieving relevant information is to expand the number of retrieved documents. However, involving more documents could introduce significant noise, as many documents may be irrelevant or misleading, thereby reducing the overall accuracy of the generated responses. To overcome the challenge associated with handling a larger number of documents, we propose WinnowRAG, a novel RAG framework designed to systematically filter out noisy documents while preserving valuable content -- a process we refer to as winnowing. WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters. Each cluster is assigned to an LLM agent for generating a unique answer. In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones. To retain useful documents when discarding agents, we propose two strategic merging techniques to ensure that only relevant knowledge is used for generating the final response. Crucially, WinnowRAG is model-agnostic and does not require any model fine-tuning, making it easily adaptable to various tasks. Extensive experiments on various realistic datasets demonstrate the effectiveness of WinnowRAG over state-of-the-art baselines.

cs.CL↗

arXiv2025

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning

The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.

cs.AI↗

arXiv2025

Greedy Sampling Is Provably Efficient for RLHF

Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized target with only preference feedback poses additional challenges compared with canonical RL. Existing works mostly study the reward-based Bradley-Terry (BT) preference model, and extend classical designs utilizing optimism or pessimism. This work, instead, considers the general preference model (whose practical relevance has been observed recently) and obtains performance guarantees with major, order-wise improvements over existing ones. Surprisingly, these results are derived from algorithms that directly use the empirical estimates (i.e., greedy sampling), as opposed to constructing optimistic or pessimistic estimates in previous works. This insight has a deep root in the unique structural property of the optimal policy class under the KL-regularized target, and we further specialize it to the BT model, highlighting the surprising sufficiency of greedy sampling in RLHF.

cs.LG↗

arXiv2025

A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization

We study bilevel optimization problems where the lower-level problems are strongly convex and have coupled linear constraints. To overcome the potential non-smoothness of the hyper-objective and the computational challenges associated with the Hessian matrix, we utilize penalty and augmented Lagrangian methods to reformulate the original problem as a single-level one. Especially, we establish a strong theoretical connection between the reformulated function and the original hyper-objective by characterizing the closeness of their values and derivatives. Based on this reformulation, we propose a single-loop, first-order algorithm for linearly constrained bilevel optimization (SFLCB). We provide rigorous analyses of its non-asymptotic convergence rates, showing an improvement over prior double-loop algorithms -- form $O(\epsilon^{-3}\log(\epsilon^{-1}))$ to $O(\epsilon^{-3})$. The experiments corroborate our theoretical findings and demonstrate the practical efficiency of the proposed SFLCB algorithm. Simulation code is provided at https://github.com/ShenGroup/SFLCB.

math.OC↗

arXiv2025

Federated Split Learning with Improved Communication and Storage Efficiency

Federated learning (FL) is one of the popular distributed machine learning (ML) solutions but incurs significant communication and computation costs at edge devices. Federated split learning (FSL) can train sub-models in parallel and reduce the computational burden of edge devices by splitting the model architecture. However, it still requires a high communication overhead due to transmitting the smashed data and gradients between clients and the server in every global round. Furthermore, the server must maintain separate partial models for every client, leading to a significant storage requirement. To address these challenges, this paper proposes a novel communication and storage efficient federated split learning method, termed CSE-FSL, which utilizes an auxiliary network to locally update the weights of the clients while keeping a single model at the server, hence avoiding frequent transmissions of gradients from the server and greatly reducing the storage requirement of the server. Additionally, a new model update method of transmitting the smashed data in selected epochs can reduce the amount of smashed data sent from the clients. We provide a theoretical analysis of CSE-FSL, rigorously guaranteeing its convergence under non-convex loss functions. The extensive experimental results further indicate that CSE-FSL achieves a significant communication reduction over existing FSL solutions using real-world FL tasks.

cs.LG↗

arXiv2025

Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection

Transformers have shown potential in solving wireless communication problems, particularly via in-context learning (ICL), where models adapt to new tasks through prompts without requiring model updates. However, prior ICL-based Transformer models rely on deep architectures with many layers to achieve satisfactory performance, resulting in substantial storage and computational costs. In this work, we propose CHain Of thOught Symbol dEtection (CHOOSE), a CoT-enhanced shallow Transformer framework for wireless symbol detection. By introducing autoregressive latent reasoning steps within the hidden space, CHOOSE significantly improves the reasoning capacity of shallow models (1-2 layers) without increasing model depth. This design enables lightweight Transformers to achieve detection performance comparable to much deeper models, making them well-suited for deployment on resource-constrained mobile devices. Experimental results demonstrate that our approach outperforms conventional shallow Transformers and achieves performance comparable to that of deep Transformers, while maintaining storage and computational efficiency. This represents a promising direction for implementing Transformer-based algorithms in wireless receivers with limited computational resources.

cs.LG↗