TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields2758Multimodal564AI agents510Frontier LLMs336Inference & serving242Teacher policy distillation204Medical image segmentation169Physics informed neural139Supervised & diffusion models115Voice AI56Forecasting time56Remote sensing47Machine learned interatomic46Electrocardiogram ecg42Deepfake detection39Federated learning37All 25 fields

Rising research topics

  • AI tutors20+81.8%
  • Channel state information17+70.0%
  • Character recognition OCR12+9.1%
  • Supervised & diffusion models115+0.9%
  • Anomaly detectors210.0%
  • Electrocardiogram ecg42−2.3%
  • Machine learned interatomic46−4.2%
  • Physics informed neural139−4.8%

Open problems across fields

  • Interface lock-in in multimodal spatial reasoning1 paper raises it · 1 addresses it

    Specializing a model on one spatial task (e.g., side detection) degrades performance on others (e.g., distance estimation), limiting general spatial intelligence.

    • ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligenceraises · addresses
  • Lack of benchmarks for agent harness reliability1 paper raises it · 1 addresses it

    Existing evaluations focus on model capabilities, not the reliability of the systems that deploy and manage agents.

    • Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
  • Negative net value of agent memory systems1 paper raises it · 1 addresses it

    Memory systems often underperform naive retrieval, as their design can obscure or remove critical evidence from raw history.

    • Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
  • Credit assignment in diffusion language models1 paper raises it · 2 address it

    Iterative denoising in DLMs makes it hard to attribute rewards to individual tokens, limiting reinforcement learning effectiveness.

    • DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Modelsraises · addresses
    • Multiscale Policy Optimization for Long-Horizon LLM Agentsaddresses
  • Uncertainty quantification failure under class imbalance1 paper raises it · 1 addresses it

    Standard uncertainty measures fail to reflect clinical ambiguity in imbalanced datasets, systematically penalizing minority classes.

    • When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalanceraises · addresses

Named by an AI from these papers' abstracts.

Papers

  • arXiv cs.LGOct 11

    Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem

    Rasul Khanbayov, Hasan Kurban

    Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can be. We observe that almost every deployed truncation rule keeps a prefix of the probability-sorted vocabulary, so any two such rules are nested at every decoding step. Nesting yields a closed-form per-step distance and a coupling under which both samplers emit identical text until they first disagree. Accumulated over a generation, this gives a separation certificate that bounds the difference between two samplers on any bounded outcome, is computable from logs a comparison already produces, and equals their sequence-level total variation distance exactly when neither rule ever overtakes the other. Two consequences follow without measurement: exactness is fragile, and certifying a small difference requires the two retained masses to agree to very high precision at every step. On six open-weight models over four math and science benchmarks, the certificate for every hyperparameter grid we tested is at least 0.998, so a bound alone rarely settles a comparison, although two members of one family can be far closer. What remains useful is…

    PDF
  • arXiv cs.CVOct 11

    Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning

    Fan Yang, Lifeng Chen, Yipu Wang, Han Wang, Feilong Chen +12

    Recent multimodal large language models achieve promising results on visual reasoning tasks, approaching human-level performance on existing STEM benchmarks. However, these capabilities degrade under complex real-world scenes. We identify that chain-of-thought reasoning remains largely confined to the linguistic space, rarely anchoring each step in visual evidence. The main cause is the absence of such data during training. In this work, we introduce a training data augmentation pipeline, \textbf{Visual Augmentation Primitives} (VAP), which leverages state-of-the-art vision generative models to synthesize diverse photorealistic training samples and corresponding reasoning text. VAP introduces some basic operators and applies them to a seed image and gets a variant. It also constructs coherent multimodal reasoning chains throughout the generation process. Such training data force models to perceive visual content and perform logical reasoning according to them at every step. We further introduce multimodal chain-of-thought rubric-based reinforcement learning to enhance this. It rewards not only text reasoning but also visual reasoning by scoring intermediate reasoning steps for…

    PDF
  • arXiv cs.LGOct 11

    UNISON: A Unified Framework for Learning from Scored Bags

    Ofek Kirshenboim, Or Shkuri, Shani Finkelshtein, Yoram Louzoun

    We introduce UNISON, a unified framework that bridges multiple instance learning and recommendation systems by treating both as instances of learning from scored bag collections of (item, score) pairs. Unlike traditional approaches that address bag-level classification and personalized recommendation as separate problems, UNISON decomposes learning into three interconnected stages: (1) learning universal item representations, (2) modeling bag-specific preference patterns through lightweight personalized parameters, and (3) inferring bag-level characteristics from learned preferences. We justify the architectural choice of linear bag-specific scoring through a first-order analysis: when item embeddings are sufficiently smooth in the score, a linear function approximates the score up to a Taylor remainder controlled by the curvature of the underlying preference function. For cold-start scenarios, we show that the cold-bag fitting problem reduces to ridge-less linear regression with a closed-form solution, and provide convergence guarantees for the iterative variant. Empirically, UNISON matches or outperforms state-of-the-art approaches across diverse domains: entertainment (books,…

    PDF
  • arXiv cs.CVOct 11

    A Plausible Future Is Not a Causal Future: Can Video Models Generate How the World Unfolds?

    Jialiang Li, Zhengning Xu, Zongyang Ma, Shaobo Cui

    Large-scale video generation models are increasingly viewed as a promising path toward world models, yet their ability to capture causally coherent physical dynamics remains poorly understood. Existing evaluations largely emphasize visual quality, prompt adherence, or broad physical plausibility, leaving open whether a model can faithfully realize a complete causal cascade, in which an initiating event propagates through causally dependent interactions to a terminal outcome. We introduce CausalCascade, a simulator-grounded benchmark centered on 50 event-rich Blender scenes with structured event graphs, graph-grounded diagnostic VQA, three levels of future-event specification, and 2,832 controlled counterfactual variants, and use it to evaluate nine image-to-video models with complementary motion-, event-, and counterfactual-level diagnostics. Across the evaluated models, generated motion is more reliably localized spatially than realized with correct spatiotemporal evolution, while richer future-event specification improves event recovery but leaves physical realization limited. Counterfactual evaluation further reveals weak selective responsiveness to physical interventions,…

    PDF
  • arXiv cs.LOOct 11

    Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors

    Yeonseok Lee

    Vision-Language-Action (VLA) models commonly generate robot actions token by token through Large Language Model (LLM) decoders, causing inference latency to grow with action sequence length and limiting closed-loop control frequency. We present Goal-Conditioned Vision-Predictor-Action (VPA), which replaces autoregressive decoders with a lightweight latent control loop. A shared vision encoder and a frozen text encoder embed observations, goal images, and instructions; a neuro-symbolic selector chooses a discrete skill; a Joint-Embedding Predictive Architecture (JEPA) predictor forecasts the next latent state; and a flow-matching solver generates an entire action chunk in a few integration steps, so that sequential network evaluations per decision step do not depend on the action horizon. We analyze inference complexity, regularization against representation collapse, and conditions under which latent sub-goal thresholding limits error accumulation across task phases. As an initial proof of concept, we evaluated VPA on the LIBERO-10 suite. The trainable model has under 20M parameters (checkpoint under 75 MB, excluding a frozen 63.4M-parameter CLIP text encoder); a decision step of…

    PDF
  • arXiv cs.CVOct 11

    ELECT: Settling Identity Before Rendering for Scalable Story Visualization

    Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana, Aniket Joarder, Mahmudul Hasan +7

    Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically maintain consistency by conditioning each frame on other frames of the same story, coupling generation time, VRAM, or both to story length. We introduce ELECT, which instead settles cross-frame identity before final rendering through a language-guided scene-entity mapping and stationary anchors elected from the model's own drafts. This makes the per-frame cost of the final rendering pass independent of story length. Joint attention exceeds 96 GB of VRAM at 32 scenes, whereas ELECT remains at 8.3 s per frame and under 20 GB VRAM from 10 to 1000 scenes. On the Story50 long-story benchmark, ELECT reaches 0.833 average Character Consistency Similarity (aCCS), compared with 0.826 for ten-round refinement, at one seventh of its generation cost, with lower text alignment (0.327 vs. 0.340). At 1000 scenes, to our knowledge, the first evaluation of training-free story visualization at this length, ELECT exceeds ten-round refinement by 0.017 aCCS and the nearest flat-cost baseline by 0.091, while also surpassing refinement in…

    PDF
  • arXiv cs.CLOct 11

    An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays

    Uday Bindal, Ishaan Karan, Manan Garg, Ekansh Goyal, Rahul Mishra +1

    We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. {\em Does Uniform Information Density (UID) predict salient scenes?} 2. {\em What other linguistic properties distinguish salient scenes from non-salient background?} We answer both questions through a controlled corpus study on the MENSA corpus, paired with a Linguistically-Grounded Salience Model (LGSM), a dual-stream classifier that fuses a frozen BERT encoder with explicit linguistic features through adaptive gating. The UID picture is layered in long-form discourse. Per-scene UID summaries carry no independent signal once length is controlled, but at the token level salient scenes match non-salient material in the bulk while specifically suppressing the rarest, hardest-to-predict tokens in the upper tail. UID therefore lives at the within-scene token level rather than as a per-scene aggregate. Salient scenes also show a moderate and sustained cast of central characters (following an inverted-U pattern), strong third-person usage, syntactically simpler language, and more abstract vocabulary about motivation and conflict. LGSM exploits this signature and improves recall on…

    PDF
  • arXiv math.OCOct 11

    Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning

    Yuriy Dorn, Dmitrii Vishovan, Kirill Novoselov, Ilya Kuruzov, Darina Dvinskikh +1

    We study federated learning from continuously arriving data: each client samples from its own distribution, these distributions drift over time, and the server must track the minimizer of the clients' weighted average loss. Clients are not alike as they collect data at different rates, with different noise, and change at different speeds. The main question is how much history should each one keep? A single shared window must serve every client at once, and so makes a fast-changing client carry the sampling noise of a slow, nearly stationary one. We give each client a memory of its own, sized to that client's noise, arrival rate, and drift, and refresh it by restarted accelerated method that starts from a common point. The tracking error is then bounded by \[ R\left(\sum_m w_m^{3/2}\,σ_m\sqrt{γ_m/λ_m}\right)^{2/3}, \] for clients with weight $w_m$, noise $σ_m$, arrival rate $λ_m$, and drift rate $γ_m$ on a domain of diameter $R$. This is never worse than what any common window can achieve, and strictly better whenever noise and drift are spread unevenly across clients. A lower bound that puts different groups of clients on different drift clocks shows this quantity is the right…

    PDF
  • arXiv cs.CLOct 11▲ 17

    Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

    Project Apertus, :, Yixuan Xu, Yassine Turki, Vinko Sabolčec +128

    Language models are becoming infrastructure, and infrastructure built in the open, by public institutions, on documented data, is the alternative to dependence on a few providers; Apertus shows this is viable at scale. Apertus 1.5 extends the fully open Apertus family from text to multimodal reasoning. Continued pretraining of the Apertus 1.0 models, on 4T additional tokens for the 8B and 2T for the 70B, adds image and audio understanding and extends the context window fourfold to 262,144 tokens; multimodality enters through the tokenizer, the language-model head remains restricted to text, and the architecture is unchanged. Supervised finetuning, long-context finetuning, reinforcement learning with verifiable rewards, and preference alignment complete the released models. Thinking is a flag of the chat template rather than a separate model, and lifts mathematical reasoning by up to 20 points on the 8B model. The released models improve over their predecessors on nearly every benchmark; among fully open models of its class, the 8B leads on knowledge, instruction following, and cultural benchmarks, and its instruction following surpasses all compared models, including open-weight…

    PDF
  • arXiv cs.LGOct 11

    Sensitivity Fidelity Reveals Physical Dependencies Beyond Forecast Accuracy in Deep-Learning Earth-System Models

    Qi Chen, Peng Zhan, Hongxing Cui, Wenqing Cui, Ibrahim Hoteit

    Deep-learning models increasingly rival numerical simulation in Earth-system forecasting, yet forecast error alone cannot determine whether their learned input-output dependencies are physically consistent. Here we introduce sensitivity fidelity as an additional criterion: alongside prediction error, model responses to input perturbations should be examined against a trusted reference or established physical knowledge. In an idealized Rayleigh-Bénard convection benchmark, four surrogate architectures achieved low forecast errors yet encoded markedly different sensitivities. Quantitative comparison with a matched adjoint distinguished the models far more sharply than forecast accuracy and showed that predictive skill and sensitivity fidelity need not coincide, while finite-perturbation experiments further linked these differences to the propagation of initial-condition uncertainty. We then applied this strategy to El Niño-Southern Oscillation prediction, where no adjoint reference exists and learned sensitivities showed event-wise robustness, validity under finite perturbations, and consistency with established precursors. These results identify gradient-based evaluation as a…

    PDF
  • arXiv cs.CROct 11

    Poisoned into Action: Context Attacks on Typed Decision Workflows

    Chenkai Wu, Xing Chang, Jun Yan

    Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating context poisoning thus requires connecting model decisions to execution outcomes while accounting for legitimate automation retained by defenses. We introduce an execution-aware protocol tracing poisoned evidence through retrieval, model choice, automated action, and persisted state. We evaluate it with 1,659 fresh calls to Jev-1.13.0 across 20 development tasks in two synthetic workflows, using three repetitions per condition. Under natural retrieval, a standalone payload reaches all 60 trials and produces five security-violating executions, while a carrier-payload pair exposes the payload in 57 trials and produces one violation. An initial source-exclusion gate blocks the pair's observed violation but also withholds ten otherwise correct attacked decisions and sixteen correct clean decisions. Correcting its empty-scope behavior restores twelve clean decisions without additional model calls. Factorial controls show that adding correct evidence reduces wrong executions from 119/120 to 55/120 in the semantic arm and from 60/120 to…

    PDF
  • arXiv cs.CVOct 11

    UMAS3D: Unified Mask-Free 3D Editing with Region-Adaptive Source Preservation

    Xianlin Zeng, Xiaolong Shen, Ruijie Quan, Yi Yang

    3D editing aims to modify an existing 3D asset according to user intent while preserving geometry and appearance outside the intended edit region. Existing methods often rely on task-specific training, source-3D inversion, or external 3D masks, and lack a unified framework for diverse editing conditions and tasks. We propose UMAS3D, a unified 3D editing framework that is training-free, inversion-free, and free from external 3D masks. UMAS3D converts text, bounding boxes, reference images, and their combinations into common target-view guidance, after which addition, deletion, modification, appearance, and pose editing share the same downstream 3D generation process. Our key insight is to couple online edit-region estimation with region-aware source preservation. Mask-Free Adaptive Region Modeling (MARM) initializes an Edit/Keep prior from source-target visual differences and progressively refines it as the target structure evolves, while Source-Guided Preservation Steering (SGPS) constrains the current Keep-region states to retain source geometry and appearance without suppressing target-driven changes. Experiments show that UMAS3D supports addition, deletion, modification,…

    PDF
  • arXiv cs.AIOct 11

    Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems

    Xiuming Liu, Le Gai, Zhiyuan Chang, Peiyang Li, Bin Zhu +2

    Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected by a later agent or propagated into a consequential task decision. Measuring local exploitability alone leaves this difference unresolved and provides limited evidence about which participant caused the final outcome. We present Agent-Canary-Mas, an end-to-end evaluation system that follows protocol risk through long-horizon multi-agent tasks. It covers five risk classes and 13 subclasses across A2A, ANP, and BCS, with 975 matched malicious--benign task pairs in five business domains. A shared OpenClaw framework runs autonomous, tool-using agents under different underlying models while preserving the task and execution setup. Matched runs separate local protocol success from downstream consequences; retained evidence connects participant selection, message consumption, tool activity, and task-state changes. We further evaluate a protocol-context Guard that checks an object's authority at consequential handoffs. Across three model conditions, local attack success is frequently at or above 90%, while consequence…

    PDF
  • arXiv cs.CLOct 11

    A Step in the Right Place: Understanding and Optimizing Timestep Placement in Continuous Diffusion Language Models

    Shutian Zheng, Zhihong Yu, Linye Wei, Zeyang Zhang, Meng Li

    Continuous diffusion language models represent an emerging paradigm for language modeling. They generate text in parallel by iteratively refining continuous representations and mapping them back to tokens through a decoder. However, realizing the efficiency advantage of parallel generation requires maintaining generation quality with only a few denoising steps. Even when the number of steps is fixed, their placement along the denoising trajectory remains flexible. In this paper, we demonstrate that changing timestep placement alone can substantially alter the final latent representations and thereby affect the decoded token distributions. Building on these findings, we introduce StepTune, an algorithm that searches for timestep placements that improve generation quality. The search is conducted on a small calibration set and guided by a language-aware objective, with the model and sampling budget fixed. Once calibrated, the timestep placement is fixed and reused across inputs. Experiments demonstrate consistent improvements in unconditional generation perplexity and conditional task metrics across all evaluated sampling budgets. In particular, StepTune enables 16-step sampling…

    PDF
  • arXiv cs.ROOct 11

    GNFormer: Gaussian Neural Field Transformer for Efficient Camera-based Occupancy Prediction

    Guangcheng Chen, Li He, Hong Zhang

    Camera-based occupancy prediction provides geometric and semantic scene understanding for robot perception and has been adopted in autonomous vehicle and UAV perception systems. Gaussian primitives offer a promising alternative by potentially representing only occupied regions, thereby concentrating computation and representational capacity where needed and reducing wasted computation and memory in empty space. However, existing Gaussian-based methods suffer from poor primitive utilization, as ineffective training objectives leave some Gaussians in empty space, while the limited expressiveness of Gaussian functions restricts their ability to model complex shapes. To address these limitations, we propose a novel 3D representation, Gaussian Neural Field (GNF), which can accurately map voxel positions to semantic occupancies. In GNF, Gaussians and a neural network jointly parameterize the field, where the Gaussians define its spatial support and provide features for neural decoding, while the neural network enables more expressive occupancy modeling than Gaussian functions alone. We further develop the Gaussian Neural Field Transformer (GNFormer), a streamlined and flexible method…

    PDF
  • arXiv cs.GTOct 11

    Improving the Bounds on Approximating Weighted Maximin Share for Chores

    Trung Thanh Nguyen, Khaled Elbassioni, Jörg Rothe

    We investigate the problem of allocating indivisible chores among agents with arbitrary positive weights and additive nonnegative cost functions. An allocation is said to be $α$-weighted-maximin-share (WMMS) fair if the cost incurred by each agent is at most $α$ times her weighted maximin share. We establish that every instance admits a $4.124234528$-WMMS allocation. Moreover, for instances in which all weights and costs are rational numbers represented in binary, we give an algorithm that computes a $4.12424$-WMMS allocation in time polynomial in the number of agents, the number of chores, and the total binary encoding length of the input. Complementing these upper bounds, we construct a family of instances with strictly positive, identically ordered costs for which the optimal WMMS approximation factors converge to $e$. Together, our results substantially narrow the previously best-known gap of $[2,12]$ established by Li et al.~\cite{LWX26} to $[e,4.12424]$.

    PDF
  • arXiv cs.LGOct 11

    OceanFlow: Coherent Flow Matching for Probabilistic Ocean Modeling

    Yuan Gao, Fan Xu, Hao Wu, Xiaomeng Huang

    Probabilistic ocean modeling is essential for risk-aware marine operations, climate analysis, and scientific decision-making, where downstream decisions depend on the conditional distribution of future ocean states rather than a single deterministic trajectory. Recent data-driven ocean models have made deterministic global ocean modeling increasingly accurate and efficient, but probabilistic ocean modeling remains underdeveloped. Specifically, perturbation-driven ensembles can create spread without explicitly optimizing the joint distribution of their members, often yielding poor calibration and physical inconsistency. To address these issues, we propose OceanFlow, a coherent flow matching framework for probabilistic global ocean modeling. OceanFlow first establishes a sharp, stable mean anchor for the conditional ensemble. Flow matching then learns a coherent state-conditioned pathwise law that jointly reshapes the residual distribution around this anchor at each transition, preserving the predictive center while refining state-dependent uncertainty. We further introduce a Factorized Dynamics Operator (FDO), which combines factorized transitions with a learned state-conditioned…

    PDF
  • arXiv cs.CVOct 11

    Semantically Steerable Image Tokenization

    Danilo de Goede, Mohammad Mahdi Derakhshani, Yuki M. Asano, Cees G. M. Snoek

    Adaptive image tokenizers compress an image into a variable number of tokens matched to its complexity, and recent work makes this allocation controllable: conditioned on a target reconstruction error, the tokenizer itself decides how many tokens an image needs. However, the fidelity measure guiding this allocation shapes which aspects of the image are preserved under compression. The pixel-wise error used in prior work is blind to the spatial structure that carries an image's meaning, and under heavy compression such tokenizers are prone to abruptly discarding tokens that encode essential content. We introduce GIST (Guided Image Semantic Tokenizer), an adaptive tokenizer that can be steered toward a requested semantic fidelity. Its token allocation is jointly controlled by pixel-level and semantic target errors, with semantic error measured in the feature space of a frozen DINOv3 encoder. This joint control enables semantic protection: with the semantic target fixed at zero, the reconstruction target can be relaxed to discard pixel detail while preserving what the image depicts. In a controlled comparison on ImageNet-100, GIST outperforms its pixel-controlled counterpart KARL at…

    PDF
  • arXiv cs.LGOct 11

    SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning

    Sankar Behera, Dhruv Singh, Satyadev Ahlawat, Yamuna Prasad

    Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-agnostic speedup. Existing post-training methods couple neuron selection and weight reconstruction through a shared calibration dataset, introducing domain bias and out-of-memory failures at high sparsity. We propose SARATHI, a framework that decouples these two stages. A data-free \emph{NMF Residual Subspace Probe} scores neurons using intrinsic weight geometry, without accessing any calibration data, and carries a formal connection to Robust PCA. \emph{Adaptive OBS} then reconstructs the pruned weights with a localized calibration batch, operating in $\mathcal{O}(d^2)$ peak memory per layer and eliminating the global memory bottleneck of coupled methods. A \emph{Bias Shift Compensation} step corrects systematic activation drift in post-LayerNorm architectures that would otherwise cause perplexity collapse at high sparsity. Experiments across six models from two architecture families (gated and non-gated FFN) at 15--40\% sparsity show that SARATHI achieves competitive perplexity and matches or exceeds existing structured pruning…

    PDF
  • arXiv cs.CLOct 11

    REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming

    Abrar Alotaibi, Moataz Ahmed

    Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming methods either require privileged access unavailable in production, rely on manually engineered per-model templates, or optimize a single objective without population-level diversity. We present REPRO (Reflective Evolutionary Prompt Optimization), a pure black-box framework that discovers adversarial prompts through evolutionary optimization driven entirely by a compressed open-weight 7B reflective model on a single consumer GPU. REPRO introduces two mechanisms absent from prior work, both isolated in a component ablation: semantic crossover, an LLM-guided multi-parent recombination operator, and Bayesian strategy selection via Thompson Sampling informed by structured failure analysis. We catalog REPRO's behavior on AdvBench, JailbreakBench, and HarmBench across 36 target models from 11 families, including GPT-5-nano, Claude-3.5-Sonnet, Gemini-2.5-Pro, and Grok-4.1. Under our protocol REPRO reaches 100\% attack success rate (ASR) on every evaluated target in a single turn, at a median of 24 target queries per behavior. Two…

    PDF
Load more