Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS) operations. To address this issue, we present GitGoodBench, a novel benchmark for evaluating AI agent performance on VCS tasks. GitGoodBench covers three core Git scenarios extracted from permissive open-source Python, Java, and Kotlin repositories. Our benchmark provides three datasets: a comprehensive evaluation suite (900 samples), a rapid prototyping version (120 samples), and a training corpus (17,469 samples). We establish baseline performance on the prototyping version of our benchmark using GPT-4o equipped with custom tools, achieving a 21.11% solve rate overall. We expect GitGoodBench to serve as a crucial stepping stone toward truly comprehensive SE agents that go beyond mere programming.
This article proposes an approach to design output-feedback controllers for unknown continuous-time linear time-invariant systems using only input-output data from a single experiment. To address the lack of state and derivative measurements, we introduce non-minimal realizations whose states can be observed by filtering the available data. We first apply this concept to the disturbance-free case, formulating linear matrix inequalities (LMIs) from batches of sampled signals to design a dynamic, filter-based stabilizing controller. The framework is then extended to the problem of asymptotic tracking and disturbance rejection - in short, output regulation - by incorporating an internal model based on prior knowledge of the disturbance/reference frequencies. Finally, we discuss tuning strategies for a class of multi-input multi-output systems and illustrate the method via numerical examples.
We investigate the data usage and predictive behavior of data-driven predictive control (DPC) with 1-norm regularization. Our analysis enables the offline removal of unused data and facilitates a comparison between the identified symmetric structure and data usage against prior knowledge of the true system. This comparison helps assess the suitability of the DPC scheme for effective control.
Accurate predictive turn-taking models (PTTMs) are essential for naturalistic human-robot interaction. However, little is known about their performance in noise. This study therefore explores PTTM performance in types of noise likely to be encountered once deployed. Our analyses reveal PTTMs are highly sensitive to noise. Hold/shift accuracy drops from 84% in clean speech to just 52% in 10 dB music noise. Training with noisy data enables a multimodal PTTM, which includes visual features to better exploit visual cues, with 72% accuracy in 10 dB music noise. The multimodal PTTM outperforms the audio-only PTTM across all noise types and SNRs, highlighting its ability to exploit visual cues; however, this does not always generalise to new types of noise. Analysis also reveals that successful training relies on accurate transcription, limiting the use of ASR-derived transcriptions to clean conditions. We make code publicly available for future research.
Speech dysfluency detection is crucial for clinical diagnosis and language assessment, but existing methods are limited by the scarcity of high-quality annotated data. Although recent advances in TTS model have enabled synthetic dysfluency generation, existing synthetic datasets suffer from unnatural prosody and limited contextual diversity. To address these limitations, we propose LLM-Dys -- the most comprehensive dysfluent speech corpus with LLM-enhanced dysfluency simulation. This dataset captures 11 dysfluency categories spanning both word and phoneme levels. Building upon this resource, we improve an end-to-end dysfluency detection framework. Experimental validation demonstrates state-of-the-art performance. All data, models, and code are open-sourced at https://github.com/Berkeley-Speech-Group/LLM-Dys.
Respiratory sound datasets are limited in size and quality, making high performance difficult to achieve. Ensemble models help but inevitably increase compute cost at inference time. Soft label training distills knowledge efficiently with extra cost only at training. In this study, we explore soft labels for respiratory sound classification as an architecture-agnostic approach to distill an ensemble of teacher models into a student model. We examine different variations of our approach and find that even a single teacher, identical to the student, considerably improves performance beyond its own capability, with optimal gains achieved using only a few teachers. We achieve the new state-of-the-art Score of 64.39 on ICHBI, surpassing the previous best by 0.85 and improving average Scores across architectures by more than 1.16. Our results highlight the effectiveness of knowledge distillation with soft labels for respiratory sound classification, regardless of size or architecture.
We introduce Music Source Restoration (MSR), a novel task addressing the gap between idealized source separation and real-world music production. Current Music Source Separation (MSS) approaches assume mixtures are simple sums of sources, ignoring signal degradations employed during music production like equalization, compression, and reverb. MSR models mixtures as degraded sums of individually degraded sources, with the goal of recovering original, undegraded signals. Due to the lack of data for MSR, we present RawStems, a dataset annotation of 578 songs with unprocessed source signals organized into 8 primary and 17 secondary instrument groups, totaling 354.13 hours. To the best of our knowledge, RawStems is the first dataset that contains unprocessed music stems with hierarchical categories. We consider spectral filtering, dynamic range compression, harmonic distortion, reverb and lossy codec as possible degradations, and establish U-Former as a baseline method, demonstrating the feasibility of MSR on our dataset. We release the RawStems dataset annotations, degradation simulation pipeline, training code and pre-trained models to be publicly available.
Complex systems are often driven by higher-order interactions among multiple units, naturally represented as hypergraphs. Understanding dependency structures within these hypergraphs is crucial for understanding and predicting the behavior of complex systems but is made challenging by their combinatorial complexity and computational demands. In this paper, we introduce a class of probabilistic models that efficiently represents and discovers a broad spectrum of mesoscale structure in large-scale hypergraphs. The key insight enabling this approach is to treat classes of similar units as themselves nodes in a latent hypergraph. By modeling observed node interactions through latent interactions among classes using low-rank representations, our approach tractably captures rich structural patterns while ensuring model identifiability. This allows for direct interpretation of distinct node- and class-level structures. Empirically, our model improves link prediction over state-of-the-art methods and discovers interpretable structures in diverse real-world systems, including pharmacological and social networks, advancing the ability to incorporate large-scale higher-order data into the scientific process.
Despite advances in reasoning and planning of R1-like models, Large Language Models (LLMs) still struggle with tasks requiring precise computation, symbolic manipulation, optimization, and algorithmic reasoning, in which textual reasoning lacks the rigor of code execution. A key challenge is enabling LLMs to decide when to use textual reasoning versus code generation. While OpenAI trains models to invoke a Code Interpreter as needed, public research lacks guidance on aligning pre-trained LLMs to effectively leverage code and generalize across diverse tasks. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL) to autonomously generate multiple code queries during step-by-step reasoning. We curate 144 reasoning and planning tasks (107 for training, 37 for testing), each with over 200 diverse questions. We fine-tune Qwen-2.5 models (3B/7B/14B) using various SFT and RL strategies, investigating different answer formats, reasoning vs. non-reasoning models, cold vs. warm starts, GRPO vs. PPO, and masked vs. unmasked code outputs. Unlike prior RL work on narrow domains, we find that Code Interpreter training is significantly harder due to high task diversity and expensive code execution, highlighting the critical role of the SFT stage. Our final model, R1-CI-14B, improves average accuracy on the 37 test tasks from 44.0\% to 64.1\%, outperforming GPT-4o (text-only: 58.6\%) and approaching GPT-4o with Code Interpreter (70.9\%), with the emergent self-checking behavior via code generation. Datasets, Codes, and Models are available at https://github.com/yongchao98/R1-Code-Interpreter and https://huggingface.co/yongchao98.
The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than simple scripts. Building such repositories from scratch remains a major challenge. Fortunately, GitHub hosts a vast, evolving collection of open-source repositories, which developers frequently reuse as modular components for complex tasks. Yet, existing frameworks like OpenHands and SWE-Agent still struggle to effectively leverage these valuable resources. Relying solely on README files provides insufficient guidance, and deeper exploration reveals two core obstacles: overwhelming information and tangled dependencies of repositories, both constrained by the limited context windows of current LLMs. To tackle these issues, we propose RepoMaster, an autonomous agent framework designed to explore and reuse GitHub repositories for solving complex tasks. For efficient understanding, RepoMaster constructs function-call graphs, module-dependency graphs, and hierarchical code trees to identify essential components, providing only identified core elements to the LLMs rather than the entire repository. During autonomous execution, it progressively explores related components using our exploration tools and prunes information to optimize context usage. Evaluated on the adjusted MLE-bench, RepoMaster achieves a 110% relative boost in valid submissions over the strongest baseline OpenHands. On our newly released GitTaskBench, RepoMaster lifts the task-pass rate from 24.1% to 62.9% while reducing token usage by 95%. Our code and demonstration materials are publicly available at https://github.com/wanghuacan/RepoMaster.
Turn-taking is richly multimodal. Predictive turn-taking models (PTTMs) facilitate naturalistic human-robot interaction, yet most rely solely on speech. We introduce MM-VAP, a multimodal PTTM which combines speech with visual cues including facial expression, head pose and gaze. We find that it outperforms the state-of-the-art audio-only in videoconferencing interactions (84% vs. 79% hold/shift prediction accuracy). Unlike prior work which aggregates all holds and shifts, we group by duration of silence between turns. This reveals that through the inclusion of visual features, MM-VAP outperforms a state-of-the-art audio-only turn-taking model across all durations of speaker transitions. We conduct a detailed ablation study, which reveals that facial expression features contribute the most to model performance. Thus, our working hypothesis is that when interlocutors can see one another, visual cues are vital for turn-taking and must therefore be included for accurate turn-taking prediction. We additionally validate the suitability of automatic speech alignment for PTTM training using telephone speech. This work represents the first comprehensive analysis of multimodal PTTMs. We discuss implications for future work and make all code publicly available.
Graph neural networks (GNNs), which capture graph structures via a feature aggregation mechanism following the graph embedding framework, have demonstrated a powerful ability to support various tasks. According to the topology properties (e.g., structural roles or community memberships of nodes) to be preserved, graph embedding can be categorized into identity and position embedding. However, it is unclear for most GNN-based methods which property they can capture. Some of them may also suffer from low efficiency and scalability caused by several time- and space-consuming procedures (e.g., feature extraction and training). From a perspective of graph signal processing, we find that high- and low-frequency information in the graph spectral domain may characterize node identities and positions, respectively. Based on this investigation, we propose random feature aggregation (RFA) for efficient identity and position embedding, serving as an extreme ablation study regarding GNN feature aggregation. RFA (i) adopts a spectral-based GNN without learnable parameters as its backbone, (ii) only uses random noises as inputs, and (iii) derives embeddings via just one feed-forward propagation (FFP). Inspired by degree-corrected spectral clustering, we further introduce a degree correction mechanism to the GNN backbone. Surprisingly, our experiments demonstrate that two variants of RFA with high- and low-pass filters can respectively derive informative identity and position embeddings via just one FFP (i.e., without any training). As a result, RFA can achieve a better trade-off between quality and efficiency for both identity and position embedding over various baselines.
Bioacoustic sound event detection (BioSED) is crucial for biodiversity conservation but faces practical challenges during model development and training: limited amounts of annotated data, sparse events, species diversity, and class imbalance. To address these challenges efficiently with a limited labeling budget, we apply the mismatch-first farthest-traversal (MFFT), an active learning method integrating committee voting disagreement and diversity analysis. We also refine an existing BioSED dataset specifically for evaluating active learning algorithms. Experimental results demonstrate that MFFT achieves a mAP of 68% when cold-starting and 71% when warm-starting (which is close to the fully-supervised mAP of 75%) while using only 2.3% of the annotations. Notably, MFFT excels in cold-start scenarios and with rare species, which are critical for monitoring endangered species, demonstrating its practical value.
Vision-and-Language Navigation (VLN) requires the agent to navigate by following natural instructions under partial observability, making it difficult to align perception with language. Recent methods mitigate this by imagining future scenes, yet they rely on vision-based synthesis, leading to high computational cost and redundant details. To this end, we propose to adaptively imagine key environmental semantics via \textit{language} form, enabling a more reliable and efficient strategy. Specifically, we introduce a novel Adaptive Text Dreamer (ATD), a dual-branch self-guided imagination policy built upon a large language model (LLM). ATD is designed with a human-like left-right brain architecture, where the left brain focuses on logical integration, and the right brain is responsible for imaginative prediction of future scenes. To achieve this, we fine-tune only the Q-former within both brains to efficiently activate domain-specific knowledge in the LLM, enabling dynamic updates of logical reasoning and imagination during navigation. Furthermore, we introduce a cross-interaction mechanism to regularize the imagined outputs and inject them into a navigation expert module, allowing ATD to jointly exploit both the reasoning capacity of the LLM and the expertise of the navigation model. We conduct extensive experiments on the R2R benchmark, where ATD achieves state-of-the-art performance with fewer parameters. The code is \href{https://github.com/zhangpingrui/Adaptive-Text-Dreamer}{here}.
Decentralized machine learning - where each client keeps its own data locally and uses its own computational resources to collaboratively train a model by exchanging peer-to-peer messages - is increasingly popular, as it enables better scalability and control over the data. A major challenge in this setting is that learning dynamics depend on the topology of the communication graph, which motivates the use of real graph datasets for benchmarking decentralized algorithms. Unfortunately, existing graph datasets are largely limited to for-profit social networks crawled at a fixed point in time and often collected at the user scale, where links are heavily influenced by the platform and its recommendation algorithms. The Fediverse, which includes several free and open-source decentralized social media platforms such as Mastodon, Misskey, and Lemmy, offers an interesting real-world alternative. We introduce Fedivertex, a new dataset of 182 graphs, covering seven social networks from the Fediverse, crawled weekly over 14 weeks. We release the dataset along with a Python package to facilitate its use, and illustrate its utility on several tasks, including a new defederation task, which captures a process of link deletion observed on these networks.
Path planning is a critical component in autonomous drone operations, enabling safe and efficient navigation through complex environments. Recent advances in foundation models, particularly large language models (LLMs) and vision-language models (VLMs), have opened new opportunities for enhanced perception and intelligent decision-making in robotics. However, their practical applicability and effectiveness in global path planning remain relatively unexplored. This paper proposes foundation model-guided path planners (FM-Planner) and presents a comprehensive benchmarking study and practical validation for drone path planning. Specifically, we first systematically evaluate eight representative LLM and VLM approaches using standardized simulation scenarios. To enable effective real-time navigation, we then design an integrated LLM-Vision planner that combines semantic reasoning with visual perception. Furthermore, we deploy and validate the proposed path planner through real-world experiments under multiple configurations. Our findings provide valuable insights into the strengths, limitations, and feasibility of deploying foundation models in real-world drone applications and providing practical implementations in autonomous flight. Project site: https://github.com/NTU-ICG/FM-Planner.
As Large Language Models (LLMs) evolve in understanding and generating code, accurately evaluating their reliability in analyzing source code vulnerabilities becomes increasingly vital. While studies have examined LLM capabilities in tasks like vulnerability detection and repair, they often overlook the importance of both structure and semantic reasoning crucial for trustworthy vulnerability analysis. To address this gap, we introduce SV-TrustEval-C, a benchmark designed to evaluate LLMs' abilities for vulnerability analysis of code written in the C programming language through two key dimensions: structure reasoning - assessing how models identify relationships between code elements under varying data and control flow complexities; and semantic reasoning - examining their logical consistency in scenarios where code is structurally and semantically perturbed. Our results show that current LLMs are far from satisfactory in understanding complex code relationships and that their vulnerability analyses rely more on pattern matching than on robust logical reasoning. These findings underscore the effectiveness of the SV-TrustEval-C benchmark and highlight critical areas for enhancing the reasoning capabilities and trustworthiness of LLMs in real-world vulnerability analysis tasks. Our initial benchmark dataset is publicly available.
We present ReverbFX, a new room impulse response (RIR) dataset designed for singing voice dereverberation research. Unlike existing datasets based on real recorded RIRs, ReverbFX features a diverse collection of RIRs captured from various reverb audio effect plugins commonly used in music production. We conduct comprehensive experiments using the proposed dataset to benchmark the challenge of dereverberation of singing voice recordings affected by artificial reverbs. We train two state-of-the-art generative models using ReverbFX and demonstrate that models trained with plugin-derived RIRs outperform those trained on realistic RIRs in artificial reverb scenarios.
Motion forecasts of road users (i.e., agents) vary in complexity as a function of scene constraints and interactive behavior. We address this with a multi-task learning method for motion forecasting that includes a retrocausal flow of information. The corresponding tasks are to forecast (1) marginal trajectory distributions for all modeled agents and (2) joint trajectory distributions for interacting agents. Using a transformer model, we generate the joint distributions by re-encoding marginal distributions followed by pairwise modeling. This incorporates a retrocausal flow of information from later points in marginal trajectories to earlier points in joint trajectories. Per trajectory point, we model positional uncertainty using compressed exponential power distributions. Notably, our method achieves state-of-the-art results in the Waymo Interaction Prediction dataset and generalizes well to the Argoverse 2 dataset. Additionally, our method provides an interface for issuing instructions through trajectory modifications. Our experiments show that regular training of motion forecasting leads to the ability to follow goal-based instructions and to adapt basic directional instructions to the scene context. Code: https://github.com/kit-mrt/future-motion
LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that reflects real-world SWE scenarios, where agents must interact with development environments, execute code and adapt behavior based on the outcomes of their actions. Existing datasets are either limited to one-shot code generation or comprise small, manually curated collections of interactive tasks, lacking both scale and diversity. Second, the lack of fresh interactive SWE tasks affects evaluation of rapidly improving models, as static benchmarks quickly become outdated due to contamination issues. To address these limitations, we introduce a novel, automated, and scalable pipeline to continuously extract real-world interactive SWE tasks from diverse GitHub repositories. Using this pipeline, we construct SWE-rebench, a public dataset comprising over 21,000 interactive Python-based SWE tasks, suitable for reinforcement learning of SWE agents at scale. Additionally, we use continuous supply of fresh tasks collected using SWE-rebench methodology to build a contamination-free benchmark for agentic software engineering. We compare results of various LLMs on this benchmark to results on SWE-bench Verified and show that performance of some language models might be inflated due to contamination issues.