arXiv:2008.13078v4 Announce Type: replace Abstract: Real-world complex systems often comprise many distinct types of elements as well as many more types of networked interactions between elements. When the relative abundances of types can be measured well, we often observe heavy-tailed categorical distributions for type frequencies. For the comparison of type frequency distributions of two systems or a system with itself at different time points in time -- a facet of allotaxonometry -- a great range of probability divergences are available. Here, we introduce and explore `probability-turbulence divergence', a tunable, straightforward, and interpretable instrument for comparing normalizable categorical frequency distributions. We model probability-turbulence divergence (PTD) after rank-turbulence divergence (RTD). While probability-turbulence divergence is more limited in application than rank-turbulence divergence, it is more sensitive to changes in type frequency. We build allotaxonographs to display probability turbulence, incorporating a way to visually accommodate zero probabilities for `exclusive types' which are types that appear in only one system. We explore comparisons of example distributions taken from literature, social media, and ecology. We show how probability-turbulence divergence either explicitly or functionally generalizes many existing kinds of distances and measures, including, as special cases, $L^{(p)}$ norms, the S{\o}rensen-Dice coefficient (the $F_{1}$ statistic), and the Hellinger distance. We discuss similarities with the generalized entropies of R{\'e}nyi and Tsallis, and the diversity indices (or Hill numbers) from ecology. We close with thoughts on open problems concerning the optimization of the tuning of rank- and probability-turbulence divergence.
Science Journals
arXiv:2307.06777v4 Announce Type: replace Abstract: The study of rational relations is fundamental to the study of formal languages and automata theory. A rational relation is conjugate if each pair of words in the relation is conjugate (or cyclic shifts of each other). The notion of conjugacy has been central in addressing many important algorithmic questions about rational relations. We address the problem of checking whether a rational relation is conjugate and show that it is decidable. Towards our decision procedure, we establish a new result that is of independent interest to word combinatorics. We identify a necessary and sufficient condition for the set of pairs given by $(a_0,b_0) G_1^* (a_1,b_1) \cdots G_k^*(a_k,b_k), k \geq 0$ to be conjugate, where $G_i$ is a (not necessarily rational) conjugate relation and $a_i, b_i$ are arbitrary words. This is similar to, and a nontrivial generalisation of, a characterisation given by Lyndon and Sch\"utzenberger in 1962 for the conjugacy of a pair of words. Furthermore, our condition can be evaluated in polynomial time, yielding a PTIME procedure for deciding the conjugacy of a rational relation given as a sumfree expression. Since any arbitrary rational expression can be expressed as a sum of sumfree expressions (with an exponential blow-up), decidability of conjugacy of rational relations follows.
arXiv:2601.09159v4 Announce Type: replace Abstract: Large language models (LLMs) have recently enabled remarkable progress in text representation. However, their embeddings are typically high-dimensional, leading to substantial storage and retrieval overhead. Although recent approaches such as Matryoshka Representation Learning (MRL) and Contrastive Sparse Representation (CSR) alleviate these issues to some extent, they still suffer from retrieval accuracy degradation. This paper proposes Isolation Kernel Embedding or IKE, a learning-free method that transforms an LLM embedding into a binary embedding using Isolation Kernel (IK). Lightweight and based on binary encoding, IKE offers a low memory footprint and fast bitwise computation, lowering retrieval latency. Experiments on multiple text retrieval datasets demonstrate that IKE offers up to 16.7x faster retrieval and 16x lower memory usage than the original LLM embeddings, while maintaining comparable accuracy. Theoretically, we show that IKE works because it satisfies four essential criteria for effective binary hashing that other methods do not possess. Compared to CSR, IKE consistently achieves better retrieval efficiency and effectiveness. IKE also works effectively with graph-based indexing, demonstrating its superiority in balancing accuracy and latency compared to alternative compression techniques in the approximate nearest neighbor (ANN) search setting.
arXiv:2601.09173v5 Announce Type: replace Abstract: Representational similarity analysis and related methods compare the internal geometries of neural networks, but they measure only alignment between spaces, leaving a blind spot -- whether a representation's structure is reliably recoverable, not merely similar. We introduce geometric stability, a distinct axis, and \textit{Shesha}, a metric that quantifies it from a single representation by correlating dissimilarity matrices built from complementary random halves of the feature dimensions. Unlike CKA and Procrustes distance, Shesha is provably non-invariant to orthogonal rotations of the feature basis. This is by design: the basis is privileged for learned models, since probes, patching, and steering act on coordinates, and a rotation-invariant metric cannot see whether the targeted structure survives them. A double dissociation isolates the mechanism -- removing the top principal component collapses CKA while Shesha holds, whereas rotating a representation into its eigenbasis, which preserves the spectrum and CKA exactly, collapses Shesha. Across 2,463 encoder configurations in seven domains, the metrics are redundant under geometry-preserving transforms and anti-correlate under compression ($\rho=-0.47$). Across 170 vision models spanning 6 clean and 38 corruption-shifted datasets, DINOv2 ranks first or second in transferability on three of six clean datasets yet bottom-quartile in stability on five, an isolated dissociation rather than a trade-off.
arXiv:2606.14948v2 Announce Type: replace Abstract: LLMs have substantially improved software engineering yet real-world development requires architectural understanding. Such understanding is prohibitively expensive to label manually and impossible to verify through tests alone. We propose an agentic judging pipeline using a strong LLM as a scalable proxy for expert architectural evaluation, comprising two judges: the Architecture Complexity Judge (ACJ), which estimates codebase-specific architectural understanding a task demands, and the Architecture Quality Judge (AQJ), which evaluates patch conformance to repository-specific architectural conventions via source-grounded rubrics. Fine-tuning Qwen3-8B/14B/32B on 3,360 curated instances achieves resolved rates of up to 27.2% on SWE-bench Verified - up to 540% over the base model and 256% over unfiltered fine-tuning. Meanwhile, the trained models achieve strong cross-language generalization and consistent improvements in architectural patch quality.
arXiv:2607.05451v1 Announce Type: new Abstract: Pedestrian Dead Reckoning (PDR) can be applied to indoor navigation systems. GPS suffers from signal degradation due to roofs and high-rise buildings, whereas PDR can estimate positions without being affected by such signal degradation. The accuracy of a foot-mounted AHRS(Attitude and Heading Reference System)-based PDR depends on the accuracy of the attitude estimation algorithm used in the AHRS. In this article, a Quaternion-Averaging-Based Adaptive Complementary Filter (QAACF) for PDR with a foot-mounted AHRS is proposed to improve estimation accuracy while reducing computational cost. QAACF fuses a quaternion derived from angular velocity with quaternions derived from acceleration and magnetic field measurements using Markley's quaternion averaging, which combines two quaternions more rigorously than linear interpolation. In addition, QAACF adaptively adjusts the weights of angular velocity, acceleration, and magnetic field measurements according to gait phases and the level of magnetic disturbances. Experimental results showed that the proposed QAACF achieves low Root Mean Square Errors (RMSEs) compared to existing attitude estimation filters while requiring lower computational cost than Kalman filters.
arXiv:2607.06288v1 Announce Type: new Abstract: Due to significant progress in physical layer (PHY) technologies, future 6G networks are expected to feature much denser antenna deployments. Cell-free MIMO network designs are one of the most promising candidates to enable denser networks. While significant effort has been put into its PHY research, the challenges it brings to networking disciplines remain relatively unexplored. In this work, we propose various fronthaul network designs for cell-free MIMO. Our results show that while tree topologies may suffice for small-scale deployments, they become infeasible as the number of antennas increases. In contrast, with growing network size, the proposed Clos topology performs almost as well as the optimal topology.
arXiv:2607.06225v1 Announce Type: new Abstract: Many bioinformatics algorithms, such as sequence alignment and structure prediction, can be expressed as recurrence equations over a dynamic programming matrix. Efficient implementations of these algorithms for large-scale biological data often require changing the order in which matrix cells are calculated and pruning ineffectual regions of the matrix from consideration altogether, but these techniques typically complicate implementation. We introduce FILTR, a domain-specific language (DSL) and compiler framework for bioinformatics recurrences. FILTR keeps the core recurrence rules separate from the pruning and scheduling strategies, where pruning acts as an approximation to limit where in the DP matrix cells are computed, and scheduling determines the iteration order for how cells are explored. FILTR compiles these high-level descriptions into optimized C++ code that matches the performance of hand-tuned implementations while enabling rapid exploration of new heuristics. FILTR is competitive with hand-optimized sequence-alignment libraries, ranging from 0.95x to 30x faster across biological benchmarks.
arXiv:2410.00346v2 Announce Type: replace Abstract: Across professional, scientific, entrepreneurial, and workplace collaboration platforms, algorithms increasingly shape how individuals find and connect with collaborators. These systems create tensions between user agency and organizational values: Should algorithms organize individuals directly in line with organizational goals, allow individuals to choose freely, or nudge choices toward those goals while preserving agency? This study examines how team formation algorithms that vary in user agency and incorporate organizational values--specifically, promoting teams with different expertise and backgrounds--influence collaborator selection, team composition, team processes, and team outcomes. We conducted a 2 x 2 between-subjects laboratory experiment using a team-formation recommendation system, manipulating user agency (assignment vs. choice) and heterogeneity criteria (included vs. not included). Across four conditions, 332 participants either selected collaborators through the system or were assigned to teams by the system, and then worked as members of 83 teams. Results show that modest differences in algorithm design can systematically reshape team composition and collaboration decisions, often without users fully perceiving the system's influence. While allowing user agency reinforced homophily, nudging by reordering recommendations based on heterogeneity criteria increased the selection of different collaborators and produced teams that performed better than those formed through unconstrained choice. Nevertheless, nudging operated without users' awareness, raising questions about transparency and autonomy. Our findings demonstrate that algorithms embedded in collaboration platforms constitute a distinct mode of algorithmic governance, where resolving tensions between user agency and organizational values raises questions about transparency, access, and control over collaboration.
arXiv:2409.20066v3 Announce Type: replace Abstract: A V-shaped module (VSM) photovoltaic technique, which breaks traditional concepts, has been proven by European and American scientists to enable power-conversion-efficiency to increase by 50% for thin-film solar cells. Furthermore, the VSM technique raises power-conversion-efficiency for all kinds of solar cells (J. Environ. Sci. Eng. A 12, 214 (2023). https://doi.org/10.17265/2162-5298/2023.06.002). Mysterious dark energy is thought to result in the surprising VSM effect. The VSM approach opens up new avenues to study photovoltaic physics. In this study, the external quantum efficiency (EQE) of commercial polycrystalline silicon solar cells in the VSM was investigated, which exhibits a surprising phenomenon of EQE above 100%. In theory, non-infrared light incident into a solar cell can cause infrared emission. The VSM could trap the emitted infrared photons and lead to extra photoexcited carriers. The easy-to-reproduce VSM effect is thus explainable. The energy of emitted infrared photons is considered as the so-called dark energy. This study provides new clues and evidences to unravel the mystery of the surprising VSM effect. The VSM technique could also be used to develop photodetectors for infrared and ultraviolet light respectively.
arXiv:2607.05465v1 Announce Type: new Abstract: Complex image creation and editing often require more than a single generation or editing model. A user request may involve synthesizing images, localizing objects, segmenting regions, editing selected content, compositing intermediate assets, reading text, and enhancing the final result. Such tasks shift multimodal agents from perception-augmented reasoning to manipulation-centered visual creation, where tools must actively transform visual states rather than merely inspect them. However, existing multimodal tool-use agents are mostly optimized for perception, search, or domain-specific editing, and lack large-scale supervision for executable image-creation trajectories. In this paper, we introduce CanvasCraft, a large-scale multimodal tool-use dataset for complex image creation and editing, and \textbf{CanvasAgent}, a tool-augmented multimodal agent that learns to orchestrate heterogeneous visual tools through multi-turn interaction. CanvasCraft contains 140K fully annotated executable trajectories and 10K RL task specifications. CanvasAgent is first trained with SFT to learn executable reasoning-action trajectories, and is then optimized with GRPO using a hybrid reward that combines outcome- and process-level signals. During rollout, CanvasAgent inspects intermediate results, tracks visual assets, and adapts tool decisions to the evolving visual state. Experiments evaluate both final image quality and trajectory behavior, demonstrating the effectiveness of CanvasAgent and the proposed dataset for complex multi-tool image creation workflows.
arXiv:2607.05468v1 Announce Type: new Abstract: World Action Models (WAMs) have shown strong potential for robotic manipulation by jointly modeling visual future dynamics and executable action sequences. However, existing video-action co-training methods primarily optimize appearance-oriented video latents, which may insufficiently capture the temporally evolving geometry required for precise manipulation. We propose MECo-WAM, a Multi-Expert Co-Training World Action Model that injects action-relevant 4D geometric priors into video-action representations while preserving the original lightweight inference graph. During training, MECo-WAM combines video and action experts with a lightweight 4D expert supervised by relational targets from a frozen VGGT encoder. Asymmetric expert visibility prevents non-causal shortcuts from auxiliary geometry to action generation. To transfer geometric knowledge into the deployed video-action pathway, we introduce decayed 4D read-mask attention, which provides restricted current-frame geometric guidance early in training and progressively removes this dependency. We further propose action-aware temporal geometric distillation, which aligns within-frame geometric relations and their temporal evolution while emphasizing visual regions most relevant to robot actions. At deployment, all auxiliary 4D components are removed. Experiments on LIBERO (98.2%), RoboTwin 2.0 (92.6%), and challenging real-world manipulation tasks show that MECo-WAM improves manipulation performance without increasing inference cost.
arXiv:2607.05473v1 Announce Type: new Abstract: According to commonly consented theories, the minimum hardware requirement for gaze tracker is one camera and two light sources to realize gaze estimation with free head movements. However, in some scenarios such as eye tracking on mobile devices, it is preferable to use less components, especially light sources. We propose a gaze estimation method with one camera and one light source. A "virtual light source" is introduced, which is geometrically placed symmetrically to the real light source with respect to the camera, and generates a "virtual glint" in the acquired image. We estimate the "virtual glint" by exploiting the relationship between the distance between two pupils and two glints in the captured image, and estimate the gaze with polynomial regression assuming two light sources are available. A new normalization factor for regression method is verified, which turns out to be practical for one-glint system. The performance is proved to be acceptable, while degradation is noticed compared to system with two actual light sources.
arXiv:2607.05528v1 Announce Type: new Abstract: Metal-oxide-semiconductor field-effect transistor (MOSFET) test structures are investigated to characterize p-stop isolation implants between n-type electrodes in p-type silicon sensors. The device transfer characteristics are measured as a function of the voltage applied to the backside to extract the threshold voltage, which quantifies inter-electrode isolation, and the field-dependent mobility parameters. We present a methodology to reconstruct depth-dependent doping profiles from the threshold voltage characteristics, accounting for the localized space-charge effects and electric-field screening induced by the p-stop implants. The study evaluates the sensitivity of this technique to various p-stop geometries and doping concentrations across different wafer types. The results demonstrate the potential of MOSFET-based structures as a non-destructive diagnostic for monitoring p-stop consistency and inter-electrode isolation properties in silicon detectors.
arXiv:2607.06371v1 Announce Type: new Abstract: Chatbots powered by generative AI (e.g., OpenAI's ChatGPT and Google's Gemini) are increasingly being appropriated for emotional support and companionship. These tools offer a suite of security and privacy (S&P) controls, including model training opt-outs and memory toggles, yet how the presence of these controls influences users' attitudes toward emotionally sensitive disclosure remains understudied. We conducted a mixed-methods vignette study with 354 U.S. participants to examine how S&P controls influence users' willingness to engage with generative AI chatbots for emotional support, their perceptions of how protected they are when using these systems, and their perceptions of how effective the chatbots are for providing support. Controls enabling deletion of disclosures had the largest positive impact: these offerings outperformed technically sophisticated controls such as local-only processing and model training opt-outs, where participants expressed difficulty understanding the underlying mechanisms. Yet trust remains fragile, and participants often doubted S&P controls would function as promised. We conclude with actionable recommendations informed by our results to bridge users' comprehension gaps, build credible assurances, and properly calibrate barriers for users in distress.
arXiv:2504.16595v2 Announce Type: replace Abstract: Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. When dealing with highly diverse 3D objects (household or grocery items), closed-form solutions are infeasible, and heuristic or model-free Reinforcement Learning~(RL) methods tend to focus solely on geometric optimization, relying on exhaustive searches of the discretized solution space. This leads to long training times (for pure RL) and high latency (heuristics), limited transferability to robotic scenarios, and ultimately ignores object characteristics (fragility, deformability) and human preferences. We propose HERB, a human-augmented RL framework for packing irregular objects, the first to explore the potential of learning from human demonstrations to solve this complex task. It leverages human demonstrations of packing strategies, which inherently exhibit latent factors such as space optimization, stability, and object properties that are difficult to model explicitly. The human-expert data is combined with RL exploration to provide the placement of each object inside the container. Experimental results show that our method outperforms heuristic, purely RL-based, and imitation learning approaches in packing efficiency and latency. Qualitative results highlight that our packing strategy produces more stable, human-like arrangements, which we expect to be more appropriate and widely accepted. Finally, we demonstrate the real-world feasibility of our method on a robotic system.
arXiv:2503.13212v3 Announce Type: replace Abstract: Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning. A widely adopted approach is identifying "metamers," stimuli physically different yet perceptually equivalent within a system. However, conventional methods lack a direct approach to searching for the human metameric space. Instead, researchers first develop biologically inspired models and then infer about human metamers indirectly by testing whether model metamers also appear as metamers to humans. Here, we propose the Multidimensional Adaptive Metamer Exploration (MAME) framework, enabling direct, high-dimensional exploration of human metameric spaces through online image generation guided by human perceptual feedback. MAME modulates reference images across multiple dimensions based on hierarchical neural network responses, adaptively updating generation parameters according to participants' perceptual discriminability. Using MAME, we successfully measured multidimensional human metameric spaces within a single psychophysical experiment. Experimental results using a biologically plausible CNN model showed that human discrimination sensitivity was lower for metameric images based on Gram-matrix representations derived from low-level CNN features than for those derived from high-level CNN features. The finding suggests a relatively worse alignment between the metameric spaces of humans and the CNN model for low-level processing compared to high-level processing. Counterintuitively, given recent discussions on alignment at higher representational levels, our results highlight the importance of early visual computations in shaping biologically plausible models. Our MAME framework can serve as a future scientific tool for directly investigating the functional organization of human vision.
arXiv:2607.05493v1 Announce Type: new Abstract: Natural-language queries about 3D environments become actionable when responses are verifiable and metric. Verifiability requires explicit grounding to the referred 3D region, while metric answers report physical measurements in real-world units (e.g., size, thickness, clearance, and distance). Existing 3D large multimodal models (LMMs) approaches remain limited: conversational systems typically respond without explicit 3D grounding, while 3D grounding models are not designed for interactive, metric-aware dialogue. In this paper, we present Ground3D-LMM, a unified model that takes a point cloud and an optional RGB image as input and supports 3D spatial conversation with (i) point-grounded responses and (ii) metric numeric outputs at both object and part granularity, including multi-object queries. To evaluate this intersection of grounding and measurement, we define the 3D Grounded Measurement task, which requires predicting the referred 3D region and the corresponding metric quantities in real-world units. We introduce a large-scale dataset built on ScanNet and ScanNet++ datasets with dense object and part annotations and roughly 2.5M question-answer pairs spanning eight tasks, along with a manually verified test set. Extensive experiments on multiple datasets and tasks show that our proposed Ground3D-LMM model provides a strong baseline for grounded, metric-aware 3D conversational understanding. Our dataset and model are publicly available.
arXiv:2607.05471v1 Announce Type: new Abstract: We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capability is bottlenecked less by model scale than by the scarcity of reproducible environments, verifiable rewards, and high-value trajectories, which we address with an end-to-end agentic post-training framework. AutoBuilder reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale, from which we regenerate self-contained task specifications, recover near-miss trajectories, and distill supervision through process-aware filtering, while KwaiClawEnv synthesizes large-scale tool-use trajectories from executable services and real task seeds. We further scale reinforcement learning with harness randomization, a reliability-hardened sandbox, an asymmetric actor--critic PPO with hindsight-augmented value estimation, and a harness-oriented reward framework, and unify SWE, Agent-Claw, and WebCoding experts via Multi-Teacher On-Policy Distillation. Across six software-engineering and agentic benchmarks, KAT-Coder-V2.5 delivers the best agentic tool-use result on PinchBench and ranks second only to the frontier Opus 4.8 on repository-level software engineering. Our service is available at https://streamlake.com/product/kat-coder.
arXiv:2607.05474v1 Announce Type: new Abstract: Algorithmic Complexity Vulnerabilities (ACVs) arise when adversarial inputs trigger worst-case execution behavior, causing severe performance degradation or Denial-of-Service conditions. A key but underexplored source is shadow complexity: non-trivial computational costs hidden inside seemingly benign standard library APIs. Because these costs are invisible at call sites, attackers can exploit them to induce unexpected superlinear runtime behavior. Existing ACV detectors often rely on fuzzing, symbolic execution, or hybrid analysis, but they are usually language-specific, require substantial manual effort to construct harnesses, and depend on heavy runtime instrumentation. We present ShadowProbe, a scalable and language-extensible framework for discovering ACVs through lightweight static analysis, automated reconstruction of execution contexts, and Large Language Model (LLM) assisted test generation. ShadowProbe uses a structured multi-stage pipeline: it statically screens for candidate functions guided by shadow-complexity signals, reconstructs minimal executable contexts from project-level symbols, and synthesizes size-controlled inputs to probe worst-case behavior. It then validates candidates using execution-time measurements and robust statistical growth inference, separating true algorithmic blowups from runtime noise such as garbage collection and JIT compilation effects. We evaluate ShadowProbe on the WISE benchmark, where it consistently improves analysis efficiency over existing approaches. We further apply it to large-scale systems including CPython, the JDK, Zig, Rustc, and vLLM, uncovering many previously unknown ACVs, many of which have been confirmed and partially remediated by maintainers. These results show that ShadowProbe can identify hidden algorithmic risks across diverse real-world codebases.
arXiv:2607.05641v1 Announce Type: new Abstract: Rendering time series as chart images for CNN-based classification has become increasingly common in time-series classification (TSC). However, it remains unclear whether models learn underlying temporal patterns or rely on encoding-specific visual cues introduced by chart design. We present VEIL: a systematic study examining how chart encodings influence learned representations through complementary analyses of similarity, transferability, and attribution. Attention-guided training appears to mitigate this effect when encoding sensitivity is consistently identified across diagnostics, but provides limited or negative benefit when such signals are absent. These findings position VEIL within the broader question of how machines perceive visualizations -- extending graphical perception from human readers to vision models -- and show that visualization design choices shape learned representations in ways that warrant treating chart-based TSC as a representation and measurement problem rather than a simple modeling decision.
arXiv:2607.05655v1 Announce Type: new Abstract: Weather and climate foundation models produce high-dimensional forecasts whose learned relationships are difficult to inspect with static plots alone. GeoXplain is an interactive Python-based visualization toolkit for exploring geospatial attribution maps across climate variables, atmospheric pressure levels, and forecast time. The toolkit accepts attribution bundles containing attribution grids together with corresponding metadata and renders them in a notebook widget or browser with map and globe modes, linked timelines, pressure-level controls, target annotations, and optional physical-field overlays. We frame GeoXplain as a model-agnostic earth-system visualization toolkit and present the GeoXplain Aurora Adapter as its first computation backend. The adapter computes explanations for the Aurora foundation model, either in a local GPU process, through a GPU listener, or through a SLURM-backed listener, while preserving the same Python call site for analysts. It currently supports gradient saliency, Integrated Gradients, RISE, ViT-CX, multi-frame saliency and Integrated Gradients rollouts, and retrieval of ERA5 overlays. GeoXplain can be installed as a PyPI package with pip install geoxplain. The code is open-source and available at https://github.com/clemenskoprolin/geoxplain.
arXiv:2508.02440v2 Announce Type: replace Abstract: We design and analyse a new numerical method to solve ODE system based on the structural method. We compute approximations of solutions together with its derivatives up to order $K$ by solving an entire block corresponding to $R$ time steps. We build the physical relations that connect the function and derivative approximations at each time step by using the ODE and its derivatives, and develop the structural equations that establish linear relations between the function and its derivative over the whole block of $R$ times steps. The non-linear system is solved and provide very accurate approximations with nice spectral resolution properties.
arXiv:2607.05659v1 Announce Type: new Abstract: Multi-agent LLM systems for Software Engineering (SE) typically differentiate agents through roles and workflows, but little is known about how agents' behavioral profiles affect team performance. We investigate the impact of personality and emotion profiles on LLM agent teams using a psychology-informed framework that combines Big Five personality traits, basic emotions, SE-relevant work styles, and task roles. We evaluate 78 team-profile configurations across code generation and code review using four LLMs and 659 task instances. Results show that profile choice substantially affects both performance and team behavior. For code generation, the gap between the best and worst shared-profile configurations reaches 7.1-11.3 percentage points in pass@1 across models, while the best mixed-profile configuration outperforms the best shared-profile configuration in six of eight model-task settings. Profiles also influence collaboration dynamics and cost: fear and high-conscientiousness profiles increase revision activity, over-revision, and token usage without consistent performance gains. These findings identify agent profiles as an important design dimension in multi-agent SE systems, affecting not only task outcomes but also the efficiency of collaboration.
arXiv:2607.05677v1 Announce Type: new Abstract: AI coding assistants such as GitHub Copilot and Cursor have evolved from code-suggestion tools into conversational collaborators, enabling vibe-coding workflows in which developers guide AI-generated code through natural-language dialogue. Although researchers have increasingly recognized the importance of AI coding agents and begun examining their impact on open-source development, a comprehensive understanding of how developers' chat-based interactions with AI relate to subsequent open-source development and collaboration remains limited. This hinders efforts to effectively design, evaluate, and govern AI-assisted open-source software development. To address this gap, we collected 13,360 AI conversation sessions comprising 79,172 user messages from 1,356 OSS repositories, linked them to repository development histories, and complemented this analysis with a targeted developer survey. We find heavier AI use in smaller, less mature, and less collaborative repositories. After AI adoption, projects tended to show more active contributors and lower contributor concentration (p < .001), although communication remained highly concentrated. Code Writing was the dominant chat purpose, and nearly all AI chat sessions were followed by subsequent commits. We find no broad deterioration in code-quality signals or pull request merging rates. However, developers perceive others' AI-generated code as harder to maintain than their own (p = .029) and view AI as lowering barriers to OSS contribution. While most developers (68%) are willing to share their chat, concerns remain around appearing incompetent, increasing reviewer burden, and exposing ideas to competitors. These findings provide a large-scale empirical characterization of AI-assisted OSS contribution and offer practical insights for designing and governing responsible vibe-coding practices in open-source development.