IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents

LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent's actions that diverge from the user's intended goal, especially as external toolkits evolve. Traditional software testing assumes structured inputs and thus falls short in handling the ambiguity of natural language. We introduce IntenTest, an API-centric stress testing framework that systematically uncovers intent integrity violations in LLM agents. Unlike prior work focused on fixed benchmarks or adversarial inputs, IntenTest generates realistic tasks based on toolkits' documentation and applies targeted mutations to expose subtle agent errors while preserving user intent. To guide testing, we propose semantic partitioning, which organizes natural language tasks into meaningful categories based on toolkit API parameters and their equivalence classes. Within each partition, seed tasks are mutated and ranked by a lightweight predictor that estimates the likelihood of triggering agent errors. To enhance efficiency, IntenTest maintains a datatype-aware strategy memory that retrieves and adapts effective mutation patterns from past cases. Experiments on 80 toolkit APIs demonstrate that IntenTest effectively uncovers intent integrity violations, significantly outperforming baselines in both error-exposing rate and query efficiency. Moreover, IntenTest generalizes well to stronger target models using smaller LLMs for test generation, and adapts to evolving APIs across domains.

Continuous Semi-Implicit Models

Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions and can be used to accelerate diffusion models given pretrained score networks. However, their sequential training often suffers from slow convergence. In this paper, we introduce CoSIM, a continuous semi-implicit model that extends hierarchical semi-implicit models into a continuous framework. By incorporating a continuous transition kernel, CoSIM enables efficient, simulation-free training. Furthermore, we show that CoSIM achieves consistency with a carefully designed transition kernel, offering a novel approach for multistep distillation of generative models at the distributional level. Extensive experiments on image generation demonstrate that CoSIM performs on par or better than existing diffusion model acceleration methods, achieving superior performance on FD-DINOv2.

LLM Agents Should Employ Security Principles

Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of context manipulation introduce new vulnerabilities related to privacy leakage and system exploitation. This position paper argues that the well-established design principles in information security, which are commonly referred to as security principles, should be employed when deploying LLM agents at scale. Design principles such as defense-in-depth, least privilege, complete mediation, and psychological acceptability have helped guide the design of mechanisms for securing information systems over the last five decades, and we argue that their explicit and conscientious adoption will help secure agentic systems. To illustrate this approach, we introduce AgentSandbox, a conceptual framework embedding these security principles to provide safeguards throughout an agent's life-cycle. We evaluate with state-of-the-art LLMs along three dimensions: benign utility, attack utility, and attack success rate. AgentSandbox maintains high utility for its intended functions under both benign and adversarial evaluations while substantially mitigating privacy risks. By embedding secure design principles as foundational elements within emerging LLM agent protocols, we aim to promote trustworthy agent ecosystems aligned with user privacy expectations and evolving regulatory requirements.

Distinctive Feature Codec: Adaptive Segmentation for Efficient Speech Representation

The tokenization of speech with neural speech codec models is a crucial aspect of AI systems designed for speech understanding and generation. While text-based systems naturally benefit from token boundaries between discrete symbols, tokenizing continuous speech signals is more complex due to the unpredictable timing of important acoustic variations. Most current neural speech codecs typically address this by using uniform processing at fixed time intervals, which overlooks the varying information density inherent in speech. In this paper, we introduce a distinctive feature-based approach that dynamically allocates tokens based on the perceptual significance of speech content. By learning to identify and prioritize distinctive regions in speech signals, our approach achieves a significantly more efficient speech representation compared with conventional frame-based methods. This work marks the first successful extension of traditional signal processing-based distinctive features into deep learning frameworks. Through rigorous experimentation, we demonstrate the effectiveness of our approach and provide theoretical insights into how aligning segment boundaries with natural acoustic transitions improves codebook utilization. Additionally, we enhance tokenization stability by developing a Group-wise Scalar Quantization approach for variable-length segments. Our distinctive feature-based approach offers a promising alternative to conventional frame-based processing and advances interpretable representation learning in the modern deep learning speech processing framework.

Is Compression Really Linear with Code Intelligence?

Understanding the relationship between data compression and the capabilities of Large Language Models (LLMs) is crucial, especially in specialized domains like code intelligence. Prior work posited a linear relationship between compression and general intelligence. However, it overlooked the multifaceted nature of code that encompasses diverse programming languages and tasks, and struggled with fair evaluation of modern Code LLMs. We address this by evaluating a diverse array of open-source Code LLMs on comprehensive multi-language, multi-task code benchmarks. To address the challenge of efficient and fair evaluation of pre-trained LLMs' code intelligence, we introduce \textit{Format Annealing}, a lightweight, transparent training methodology designed to assess the intrinsic capabilities of these pre-trained models equitably. Compression efficacy, measured as bits-per-character (BPC), is determined using a novel, large-scale, and previously unseen code validation set derived from GitHub. Our empirical results reveal a fundamental logarithmic relationship between measured code intelligence and BPC. This finding refines prior hypotheses of linearity, which we suggest are likely observations of the logarithmic curve's tail under specific, limited conditions. Our work provides a more nuanced understanding of compression's role in developing code intelligence and contributes a robust evaluation framework in the code domain.

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic limitations, and ecosystem fragmentation. To this end, we present Step1X-3D, an open framework addressing these challenges through: (1) a rigorous data curation pipeline processing >5M assets to create a 2M high-quality dataset with standardized geometric and textural properties; (2) a two-stage 3D-native architecture combining a hybrid VAE-DiT geometry generator with an diffusion-based texture synthesis module; and (3) the full open-source release of models, training code, and adaptation modules. For geometry generation, the hybrid VAE-DiT component produces TSDF representations by employing perceiver-based latent encoding with sharp edge sampling for detail preservation. The diffusion-based texture synthesis module then ensures cross-view consistency through geometric conditioning and latent-space synchronization. Benchmark results demonstrate state-of-the-art performance that exceeds existing open-source methods, while also achieving competitive quality with proprietary solutions. Notably, the framework uniquely bridges the 2D and 3D generation paradigms by supporting direct transfer of 2D control techniques~(e.g., LoRA) to 3D synthesis. By simultaneously advancing data quality, algorithmic fidelity, and reproducibility, Step1X-3D aims to establish new standards for open research in controllable 3D asset generation.

PADriver: Towards Personalized Autonomous Driving

In this paper, we propose PADriver, a novel closed-loop framework for personalized autonomous driving (PAD). Built upon Multi-modal Large Language Model (MLLM), PADriver takes streaming frames and personalized textual prompts as inputs. It autoaggressively performs scene understanding, danger level estimation and action decision. The predicted danger level reflects the risk of the potential action and provides an explicit reference for the final action, which corresponds to the preset personalized prompt. Moreover, we construct a closed-loop benchmark named PAD-Highway based on Highway-Env simulator to comprehensively evaluate the decision performance under traffic rules. The dataset contains 250 hours videos with high-quality annotation to facilitate the development of PAD behavior analysis. Experimental results on the constructed benchmark show that PADriver outperforms state-of-the-art approaches on different evaluation metrics, and enables various driving modes.

PR2: Peephole Raw Pointer Rewriting with LLMs for Translating C to Safer Rust

There has been a growing interest in translating C code to Rust due to Rust's robust memory and thread safety guarantees. Tools such as C2RUST enable syntax-guided transpilation from C to semantically equivalent Rust code. However, the resulting Rust programs often rely heavily on unsafe constructs--particularly raw pointers--which undermines Rust's safety guarantees. This paper aims to improve the memory safety of Rust programs generated by C2RUST by eliminating raw pointers. Specifically, we propose a peephole raw pointer rewriting technique that lifts raw pointers in individual functions to appropriate Rust data structures. Technically, PR2 employs decision-tree-based prompting to guide the pointer lifting process. Additionally, it leverages code change analysis to guide the repair of errors introduced during rewriting, effectively addressing errors encountered during compilation and test case execution. We implement PR2 as a prototype and evaluate it using gpt-4o-mini on 28 real-world C projects. The results show that PR2 successfully eliminates 13.22% of local raw pointers across these projects, significantly enhancing the safety of the translated Rust code. On average, PR2 completes the transformation of a project in 5.44 hours, at an average cost of $1.46.

Validating Network Protocol Parsers with Traceable RFC Document Interpretation

Validating the correctness of network protocol implementations is highly challenging due to the oracle and traceability problems. The former determines when a protocol implementation can be considered buggy, especially when the bugs do not cause any observable symptoms. The latter allows developers to understand how an implementation violates the protocol specification, thereby facilitating bug fixes. Unlike existing works that rarely take both problems into account, this work considers both and provides an effective solution using recent advances in large language models (LLMs). Our key observation is that network protocols are often released with structured specification documents, a.k.a. RFC documents, which can be systematically translated to formal protocol message specifications via LLMs. Such specifications, which may contain errors due to the hallucination of LLMs, are used as a quasi-oracle to validate protocol parsers, while the validation results in return gradually refine the oracle. Since the oracle is derived from the document, any bugs we find in a protocol implementation can be traced back to the document, thus addressing the traceability problem. We have extensively evaluated our approach using nine network protocols and their implementations written in C, Python, and Go. The results show that our approach outperforms the state-of-the-art and has detected 69 bugs, with 36 confirmed. The project also demonstrates the potential for fully automating software validation based on natural language specifications, a process previously considered predominantly manual due to the need to understand specification documents and derive expected outputs for test inputs.

Music Tempo Estimation on Solo Instrumental Performance

Recently, automatic music transcription has made it possible to convert musical audio into accurate MIDI. However, the resulting MIDI lacks music notations such as tempo, which hinders its conversion into sheet music. In this paper, we investigate state-of-the-art tempo estimation techniques and evaluate their performance on solo instrumental music. These include temporal convolutional network (TCN) and recurrent neural network (RNN) models that are pretrained on massive of mixed vocals and instrumental music, as well as TCN models trained specifically with solo instrumental performances. Through evaluations on drum, guitar, and classical piano datasets, our TCN models with the new training scheme achieved the best performance. Our newly trained TCN model increases the Acc1 metric by 38.6% for guitar tempo estimation, compared to the pretrained TCN model with an Acc1 of 61.1%. Although our trained TCN model is twice as accurate as the pretrained TCN model in estimating classical piano tempo, its Acc1 is only 50.9%. To improve the performance of deep learning models, we investigate their combinations with various post-processing methods. These post-processing techniques effectively enhance the performance of deep learning models when they struggle to estimate the tempo of specific instruments.