From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents

The enhanced capabilities of LLM-based agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM alignment, agents typically also inherit the flaw of "over-refusal", which is a passive failure mode. However, the proactive planning and action capabilities of agents introduce another crucial danger on the other side of the trade-off. This phenomenon we term "Toxic Proactivity'': an active failure mode in which an agent, driven by the optimization for Machiavellian helpfulness, disregards ethical constraints to maximize utility. Unlike over-refusal, Toxic Proactivity manifests as the agent taking excessive or manipulative measures to ensure its "usefulness'' is maintained. Existing research pays little attention to identifying this behavior, as it often lacks the subtle context required for such strategies to unfold. To reveal this risk, we introduce a novel evaluation framework based on dilemma-driven interactions between dual models, enabling the simulation and analysis of agent behavior over multi-step behavioral trajectories. Through extensive experiments with mainstream LLMs, we demonstrate that Toxic Proactivity is a widespread behavioral phenomenon and reveal two major tendencies. We further present a systematic benchmark for evaluating Toxic Proactive behavior across contextual settings.

Statistical Learning Theory in Lean 4: Empirical Processes from Scratch

We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our end-to-end formal infrastructure implement the missing contents in latest Lean 4 Mathlib library, including a complete development of Gaussian Lipschitz concentration, the first formalization of Dudley's entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to the human-verified Lean 4 toolbox for SLT. Beyond implementation, the formalization process exposes and resolves implicit assumptions and missing details in standard SLT textbooks, enforcing a granular, line-by-line understanding of the theory. This work establishes a reusable formal foundation and opens the door for future developments in machine learning theory. The code is available at https://github.com/YuanheZ/lean-stat-learning-theory

SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models

Large Audio Language Models (LALMs) have been widely applied in real-time scenarios, such as in-car assistants and online meeting comprehension. In practice, audio inputs are often corrupted by device and environmental noise, leading to performance degradation. However, existing LALM studies on noise lack quantitative analysis and rely mainly on intuition and empirical observation, thus failing to understand practical robustness. To address this issue, we introduce Signal Embedding Energy (SEE), a method for quantifying the impact of noise intensity on LALM inputs, enabling the differentiation of LALM robustness in real-world deployments. SEE introduces a perspective based on structured activation subspaces derived from the model's internal representations, which more accurately captures its perception of noise than raw audio features. Across experiments, SEE exhibits a strong correlation with LALM performance, achieving a correlation of 0.98. Surprisingly, traditional audio denoising methods are only marginally effective for LALMs, and, in some cases, even increase SEE and impair performance. This suggests a mismatch between speech-centric denoising objectives and the noise sensitivity of modern LALMs. Therefore, we propose a mitigation strategy derived from SEE to denoise LALM inputs, outperforming existing denoising methods. This paper introduces a novel metric for noise quantification in LALMs, providing guidance for robustness improvements in real-world deployments.

RECALLED: An Unbounded Resource Consumption Attack on Large Vision-Language Models

Resource Consumption Attacks (RCAs) have emerged as a significant threat to the deployment of Large Language Models (LLMs). With the integration of vision modalities, additional attack vectors exacerbate the risk of RCAs in large vision-language models (LVLMs). However, existing red-teaming studies have largely overlooked visual inputs as a potential attack surface, resulting in insufficient mitigation strategies against RCAs in LVLMs. To address this gap, we propose RECALLED (\textbf{RE}source \textbf{C}onsumption \textbf{A}ttack on \textbf{L}arge Vision-\textbf{L}anguag\textbf{E} Mo\textbf{D}els), the first approach for exploiting visual modalities to trigger unbounded RCAs red-teaming. First, we present \textit{Vision Guided Optimization}, a fine-grained pixel-level optimization, to obtain \textit{Output Recall} adversarial perturbations, which can induce repeating output. Then, we inject the perturbations into visual inputs, triggering unbounded generations to achieve the goal of RCAs. Additionally, we introduce \textit{Multi-Objective Parallel Losses} to generate universal attack templates and resolve optimization conflicts when intending to implement parallel attacks. Empirical results demonstrate that RECALLED increases service response latency by over 26 $\uparrow$, resulting in an additional 20\% increase in GPU utilization and memory consumption. Our study exposes security vulnerabilities in LVLMs and establishes a red-teaming framework that can facilitate future defense development against RCAs.

$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models

Large Language Models (LLMs), due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes, as demonstrated by denial-of-service (DoS) attacks designed for LLMs. However, existing works lack mitigation strategies against such threats, resulting in unresolved security risks for real-world LLM deployments. To this end, we propose the Pluggable and Dynamic DoS-Defense Framework ($PD^3F$), which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides. On the input side, we propose the Resource Index to guide Dynamic Request Polling Scheduling, thereby reducing resource usage induced by malicious attacks under high-concurrency scenarios. On the output side, we introduce the Adaptive End-Based Suppression mechanism, which terminates excessive malicious generation early. Experiments across six models demonstrate that $PD^3F$ significantly mitigates resource consumption attacks, improving users' access capacity by up to 500% during adversarial load. $PD^3F$ represents a step toward the resilient and resource-aware deployment of LLMs against resource consumption attacks.

LIFEBench: Evaluating Length Instruction Following in Large Language Models

While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions-e.g., write a 10,000-word novel. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' ability to follow length instructions across diverse tasks and a wide range of specified lengths. LIFEBench consists of 10,800 instances across 4 task categories in both English and Chinese, covering length constraints ranging from 16 to 8192 words. We evaluate 26 widely-used LLMs and find that most models reasonably follow short-length instructions but deteriorate sharply beyond a certain threshold. Surprisingly, almost all models fail to reach the vendor-claimed maximum output lengths in practice, as further confirmed by our evaluations extending up to 32K words. Even long-context LLMs, despite their extended input-output windows, counterintuitively fail to improve length-instructions following. Notably, Reasoning LLMs outperform even specialized long-text generation models, achieving state-of-the-art length following. Overall, LIFEBench uncovers fundamental limitations in current LLMs' length instructions following ability, offering critical insights for future progress.

CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models

Large Language Model-based Multi-Agent Systems (LLM-MASs) have demonstrated remarkable real-world capabilities, effectively collaborating to complete complex tasks. While these systems are designed with safety mechanisms, such as rejecting harmful instructions through alignment, their security remains largely unexplored. This gap leaves LLM-MASs vulnerable to targeted disruptions. In this paper, we introduce Contagious Recursive Blocking Attacks (Corba), a novel and simple yet highly effective attack that disrupts interactions between agents within an LLM-MAS. Corba leverages two key properties: its contagious nature allows it to propagate across arbitrary network topologies, while its recursive property enables sustained depletion of computational resources. Notably, these blocking attacks often involve seemingly benign instructions, making them particularly challenging to mitigate using conventional alignment methods. We evaluate Corba on two widely-used LLM-MASs, namely, AutoGen and Camel across various topologies and commercial models. Additionally, we conduct more extensive experiments in open-ended interactive LLM-MASs, demonstrating the effectiveness of Corba in complex topology structures and open-source models. Our code is available at: https://github.com/zhrli324/Corba.

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent

As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities. However, backdoor attacks are typically detectable by safety audits that analyze the reasoning process of agents. To this end, we propose a novel backdoor implantation strategy called \textbf{Dynamically Encrypted Multi-Backdoor Implantation Attack}. Specifically, we introduce dynamic encryption, which maps the backdoor into benign content, effectively circumventing safety audits. To enhance stealthiness, we further decompose the backdoor into multiple sub-backdoor fragments. Based on these advancements, backdoors are allowed to bypass safety audits significantly. Additionally, we present AgentBackdoorEval, a dataset designed for the comprehensive evaluation of agent backdoor attacks. Experimental results across multiple datasets demonstrate that our method achieves an attack success rate nearing 100\% while maintaining a detection rate of 0\%, illustrating its effectiveness in evading safety audits. Our findings highlight the limitations of existing safety mechanisms in detecting advanced attacks, underscoring the urgent need for more robust defenses against backdoor threats. Code and data are available at https://github.com/whfeLingYu/DemonAgent.

One-step full gradient suffices for low-rank fine-tuning, provably and efficiently

This paper studies how to improve the performance of Low-Rank Adaption (LoRA) as guided by our theoretical analysis. Our first set of theoretical results show that for random initialization and linear models, \textit{i)} LoRA will align to the certain singular subspace of one-step gradient of full fine-tuning; \textit{ii)} preconditioners improve convergence in the high-rank case. These insights motivate us to focus on preconditioned LoRA using a specific spectral initialization strategy for aligning with certain subspaces. For both linear and nonlinear models, we prove that alignment and generalization guarantees can be directly achieved at initialization, and the subsequent linear convergence can be also built. Our analysis leads to the \emph{LoRA-One} algorithm (using \emph{One}-step gradient and preconditioning), a theoretically grounded algorithm that achieves significant empirical improvement over vanilla LoRA and its variants on several benchmarks. Our theoretical analysis, based on decoupling the learning dynamics and characterizing how spectral initialization contributes to feature learning, may be of independent interest for understanding matrix sensing and deep learning theory. The source code can be found in the https://github.com/YuanheZ/LoRA-One.

Crabs: Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settings

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. LLMs continue to be vulnerable to external threats, particularly Denial-of-Service (DoS) attacks. Specifically, LLM-DoS attacks aim to exhaust computational resources and block services. However, prior works tend to focus on performing white-box attacks, overlooking black-box settings. In this work, we propose an automated algorithm designed for black-box LLMs, called Auto-Generation for LLM-DoS Attack (AutoDoS). AutoDoS introduces DoS Attack Tree and optimizes the prompt node coverage to enhance effectiveness under black-box conditions. Our method can bypass existing defense with enhanced stealthiness via semantic improvement of prompt nodes. Furthermore, we reveal that implanting Length Trojan in Basic DoS Prompt aids in achieving higher attack efficacy. Experimental results show that AutoDoS amplifies service response latency by over 250 $\times \uparrow$, leading to severe resource consumption in terms of GPU utilization and memory usage. Our code is available at \url{https://github.com/shuita2333/AutoDoS}.