# Research Papers — 2026-05 · bundle page 117 of 326 > Full-text markdown of papers #5801–5850 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/117 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/116.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/118.md) ### WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems Authors: Xuan Wu, Jinbiao Chen, Yang Li, Lijie Wen, Chunguo Wu, Yuanshu Li, Yubin Xiao, Chunyan Miao, You Zhou, Di Wang Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22876v2 Existing neural solvers for Multi-Objective Combinatorial Optimization Problems (MOCOPs) commonly adopt decomposition-based strategies that scalarize a MOCOP into multiple subproblems associated with distinct weight vectors. However, they either inject weights only once during decoding, limiting weight-conditioned context modeling, or primarily during encoding, causing weight-signal dilution during decoding. Moreover, their preference optimization methods rely on purely random sampling to construct solution pairs for training solvers, which often produces less informative pairs and thus leads to low training effectiveness. To better address these limitations, we propose an efficient Weight-Conditioned neural solver (WeCon). Specifically, we design an encoder layer with three attention blocks and our proposed Gated Residual Fusion block to facilitate harmonious interaction between instance features and weights, thereby generating informative weight-conditioned context. We further introduce a plug-and-play Residual Fusion block in the decoder to alleviate weight-signal dilution. Finally, we propose Efficient Preference Optimization, which constructs high-quality solutions, thereby generating more informative pairs to improve training effectiveness. Experimental results on four MOCOP variants across different problem scales and distribution patterns demonstrate that WeCon achieves HyperVolume (HV) performance comparable to the state-of-the-art (SOTA) solver POCCO-W, while requiring approximately 40% less inference time. Moreover, the variant WeCon-CCO, which adopts an enhanced decoder, achieves the best overall HV performance with increased inference time. Ablation studies validate the contributions of all proposed designs. --- ### RMA: an Agentic System for Research-Level Mathematical Problems Authors: Zelin Zhao, Bo Yuan, Jaemoo Choi, Yongxin Chen Published: 2026-05-20 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22875v1 We present $\textbf{Research Math Agents (RMA)}$, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies centered on competition mathematics or formal theorem proving, RMA targets research-level mathematical problems that require long-horizon reasoning, literature grounding, and iterative proof refinement. RMA decomposes research-level proof solving into specialized modules for problem analysis, literature search and understanding, fair comparison, knowledge-bank construction, and proof verification, all coordinated by initializer, proposer, and verifier agents through a shared structured memory. Within this unified framework, these agents operate in a multi-role, multi-round workflow, collaboratively generating, refining, and verifying candidate proofs through iterative feedback. We evaluate RMA on the First Proof benchmark, which consists of ten research-level problems contributed by expert mathematicians across diverse domains. Through comprehensive expert evaluation, RMA outperforms strong baselines on the First Proof benchmark, including GPT-5.2R and Aletheia, solving eight out of ten research problems and producing more logically sound and readable proofs. Our comprehensive ablation studies further show that performance gains arise from the interaction of structured reasoning modules, iterative refinement, and verifier-based feedback, rather than any single component. Our solutions and implementations will be made publicly available upon acceptance. --- ### NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic Authors: Paapa Kwesi Quansah, Ernest Bonnah Published: 2026-05-20 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2605.22874v1 Effectively translating between natural language (NL) and formal logics like Linear Temporal Logic (LTL) requires expertise that limits formal verification's reach in safety-critical development. Template-based approaches sacrifice expressiveness for reliability; neural methods achieve fluency but provide no correctness guarantees. We present NeuroNL2LTL, a neurosymbolic architecture unifying learned translation with formal verification. NeuroNL2LTL routes translation through an intermediate representation whose mapping to LTL is structure-preserving by construction. Generated specifications undergo satisfiability and non-triviality checking; a minimal-edit repair mechanism corrects near-miss outputs before they reach downstream tools. The central innovation is verifier-in-the-loop training: verification outcomes serve as reward signals for reinforcement learning, producing neural components that optimize directly for formal correctness. On 200,000+ requirements spanning aerospace, robotics, autonomous vehicles, and ten additional domains, NeuroNL2LTL achieves 28\% semantic equivalence with reference specifications while ensuring 86\% of outputs are verified satisfiable. The system also generates contextually grounded explanations from LTL, enabling domain experts to validate specifications without specialized training. This work demonstrates that formal verification can function as both training objective and runtime filter for neural specification systems, allowing us to build neural-based tools whose reliability derives from logical guarantees rather than statistical confidence. --- ### When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions Authors: Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.22873v2 Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial? Empirical evidence reveals a striking paradox: CoT often provides marginal or even negative gains on factual and open-ended tasks while multiplying token consumption. In this work, we show that LLM reasoning is not a static property of tasks or models, but a \emph{dynamic decoding state} that emerges during generation. Through systematic analysis, we find early-stage entropy dynamics provide a reliable signal of this state: tasks benefiting from CoT exhibit consistent entropy reduction, while others display unstable or increasing patterns. This behavior can be interpreted as a phase-transition-like shift from a high-entropy exploratory regime to a low-entropy structured reasoning regime. Based on these insights, we propose \textbf{EDRM} (Entropy Dynamics-based Reasoning Manifold), a lightweight and training-free routing framework that leverages early decoding entropy to adaptively select inference strategies. EDRM embeds entropy trajectories into a compact and interpretable manifold representation, enabling both zero-shot deployment and fine-grained instance-level adaptation. Across 15 benchmarks and 4 LLMs of varying scales and architectures, EDRM consistently outperforms static baselines. At the dataset level, EDRM achieves \textbf{41--55\%} token reduction while improving accuracy with as few as 50 calibration samples. At the instance level, it further improves accuracy by up to \textbf{4.7\%} while maintaining \textbf{27--45\%} token savings. These results suggest that reasoning should be invoked selectively rather than by default, and demonstrate the effectiveness of entropy-driven decoding control for efficient and adaptive LLM inference. --- ### MedExpMem: Adapting Experience Memory for Differential Diagnosis Authors: Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Yannian Gu, Winnie Chiu Wing Chu, Xiaofan Zhang, Qi Dou Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.22872v1 Experienced physicians develop diagnostic expertise through clinical practice, acquiring not only disease knowledge but also the ability to differentiate confusable conditions. Current medical vision-language models (VLMs) lack this capability -- their parameters encode static knowledge that does not evolve across diagnostic encounters. We propose MedExpMem, an experience memory framework enabling VLM-based diagnostic agents to accumulate differential diagnosis expertise. Unlike retrieval-augmented generation, which retrieves encyclopedic disease descriptions, MedExpMem memorizes discriminative experience derived from the agent's own diagnostic failures and organizes them as pairwise differential notes encoding key discriminators, actionable decision rules and reasoning error patterns. The framework adopts a two-phase construction process mirroring physician learning: initial practice exposes knowledge gaps, and reflective re-diagnosis refines understanding. When encountering new cases, the agent retrieves experience memory to guide differential reasoning. We evaluate MedExpMem on a radiology benchmark spanning 11 subspecialties. Results demonstrate consistent accuracy improvements, maximum 7.0%, across diverse models and scales. Analytical experiments validate experience quality and robustness, demonstrating MedExpMem as a competitive method addresses medical adaptation needs beyond the reach of parameteric learning. --- ### Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity Authors: Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Luoyu Chen, Shui Yu Published: 2026-05-20 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.22871v1 Machine unlearning is a fundamental mechanism that enforces the right to be forgotten. Existing unlearning studies that rely on label manipulation or task-gradient reversal often deliver limited unlearning effectiveness. Moreover, they can undermine the original learning objective and typically do not guarantee equivalence to standard unlearning by retraining. In this paper, we propose \textbf{ManiF-SMC} (\textbf{Mani}fold \textbf{F}orgetting with \textbf{S}elf \textbf{M}ode \textbf{C}onnectivity), motivated by the observation that a model retrained on the remaining data tends to classify erased samples by their semantic similarity to the retained data. We begin with systematically recasting the approximate unlearning as pushing each erased sample away from its original learned manifold representation centroid toward its nearest semantic neighbors in the retained data. This reformulation aligns unlearning with retraining behavior and operates purely in representation space, reducing reliance on labels and task-specific gradients. To tackle the manifold representation-based unlearning problem, ManiF-SMC encapsulates the unlearning and representation preservation goals in a margin-based triplet loss. Because finding a suitable margin for unlearning is challenging, we propose a self-mode-connectivity module that rapidly reconstructs the local manifold to guide the adaptive margins generation for each unlearning case. Extensive experiments on four representative datasets show that ManiF-SMC achieves unlearning effectiveness comparable to state-of-the-art approximate methods while operating solely within the model's representation space. --- ### The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models Authors: Ming Liu Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.22870v1 Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does CoT contribute if not logical sequencing? In three 1-3B instruction-tuned LMs on GSM8K, we isolate the answer-readout stage via prefix completion and identify a positional shortcut: the model copies whichever number occupies the trailing position before the answer delimiter, regardless of intermediate reasoning. Gold-answer presence accounts for 54-92 pp of accuracy (89-92% of each model's teacher-forcing ceiling); even on incorrect items, the final answer matches the last CoT number 95-96% of the time. The copy channel takes precedence over retained-context completion: replacing the trailing number with a wrong value collapses accuracy to near-zero despite correct intermediates, yet removing it recovers 5-32 pp above that floor--even single-step arithmetic the model can otherwise perform is suppressed when a copyable number is present. Qwen and Llama copy novel distractors 87-95% of the time; Gemma gates selectively. Head-level ablation implicates architecture-specific head sets; the effect replicates on GSM-Symbolic. On non-arithmetic BBH tasks, shuffle retention drops sharply; at 7-8B, content-selective gating emerges. Step-level faithfulness evaluations risk conflating positional answer transport with genuine computation--a failure mode for CoT-based oversight. --- ### An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation Authors: Xiaofeng Liu, Qianru Zhang, Thibault Marin, Menghua Xia, Chi Liu, Georges El Fakhri, Jinsong Ouyang Published: 2026-05-20 Categories: eess.IV, cs.AI, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2605.21835v1 The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PET) is important to oncologic imaging. However, existing deep learning methods for PET/CT remain largely task-specific, are often trained on single-center cohorts, or adopt dual-branch fusion schemes that delay cross-modal interaction and underutilize early spatial correspondence between PET and CT. To address these limitations, we present an open-source, multi-center, whole-body FDG PET/CT foundation model utilizing 4,997 harmonized scans from four public datasets. Our framework employs hierarchical UNet-shaped backbones with early channel-wise concatenation, enabling anatomical and metabolic features to interact from the first embedding layer onward. We further introduce a masked autoencoding objective based on zero-mean imputation, combined with a weighted global reconstruction loss. This design avoids non-physical intensity discontinuities at masked-region boundaries that arise from learnable mask tokens. On downstream AutoPET lesion segmentation, the proposed models demonstrate strong label efficiency: with only 10\% of the labeled training data, they achieve performance comparable to models trained from scratch on the full dataset. Under extreme 5-shot linear probing, joint PET/CT pretraining also achieves higher Dice scores than separated-modality pretraining. This multi-center foundation model demonstrates label efficiency and cross-modality representation learning for PET/CT tumor segmentation. It provides a robust, open-source basis for advancing automated oncologic imaging, significantly reducing the need for large-scale manual annotations in clinical practice. --- ### On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation Authors: Andy Han, Kristina Fujimoto, Avidan Shah, Kiet Nguyen, Kai Xu, Chen Yueh-Han, Ilia Sucholutsky, Rico Angell Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21834v1 Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promising new alignment paradigm to mitigate such failures by training invariants into the model using contrastive input pairs. Existing consistency training procedures generate the supervision signal once, offline, and use supervised fine-tuning (SFT) to update the model. Unfortunately, the resulting models tend to merely memorize the surface forms of the training distribution and thus generalize poorly and regress in their capabilities. We introduce On-Policy Consistency Training (OPCT), a new consistency training approach where the objective is computed over the model's own responses to prompts, supervised by itself conditioned on corresponding contrastive prompts. We evaluate OPCT on three safety axes: sycophancy, jailbreaking, and safety awareness. Across three model families, OPCT outperforms its SFT counterpart on all safety desiderata. It nearly halves the sycophancy rate relative to baseline (8.1% vs. 15.4%, compared to 11.2% for SFT). Under an adaptive per-target attacker, OPCT holds jailbreak defense success near 99% on held-out jailbreak behaviors, whereas SFT achieves 87% on average. On safety awareness, OPCT outperforms SFT in two out of three models, and matches it on the other. OPCT also largely avoids the capability regressions that SFT induces, such as a 28-point drop on MATH-500. Our results suggest that consistency training is best implemented as OPCT rather than as SFT, especially when generalization beyond the training distribution is desired. --- ### FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation Authors: Xinhang Yuan, Zexi Huang, Anjia Cao, Xudong Lu, Zikai Wang, Penghao Zhou, Chang Liu, Wentao Guo, Qinglei Wang Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21832v2 Modern recommender systems rely heavily on ID-based collaborative filtering: each item is represented by a unique ID embedding that accumulates collaborative signals from user interactions. Livestreaming recommendation, however, faces a unique challenge in this paradigm: a live room typically broadcasts for only tens of minutes, so its item ID remains poorly learned in a persistent cold-start state and ID-centric ranking models fail to generalize. We present FLUID, the first framework to fully retire the candidate-side item ID from a production-scale livestreaming ranker. FLUID introduces a cross-domain multimodal encoder, jointly trained on short videos and livestreams, to produce discrete hierarchical semantic codes, called LUCID, for content-based item characterization. To adapt the ranker to LUCID, FLUID further employs a staged warmup scheme: it first incorporates cold, slice-level LUCID as an independent token alongside the ID embedding, and then replaces the ID embedding with warm, room-level LUCID before online incremental training. Deployed on our industrial livestreaming recommenders with a cross-platform combined user base of over one billion globally, FLUID delivers significant online gains of +0.55% Quality Watch Duration, +2.05% Cold-Start Room Views, and +0.05% Active Hours. --- ### Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions Authors: Daniel Tabach Published: 2026-05-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.21827v1 Do language models preserve the ordinal meaning of intensity words when those words must produce numeric actions? I study a researcher-constructed scale of 10 English degree modifiers, from slightly to drastically, informed by the Quirk et al. degree-modifier taxonomy, in a controlled resource-allocation environment where Claude Haiku receives a natural-language instruction, produces a numeric allocation, and a deterministic backend converts that allocation into a measurable outcome. The only variable that changes between runs is the intensity word or the starting system state, isolating their effects on the model's numeric output. Across 6,620 runs at T=0.0 and T=0.7, three patterns emerge. First, the model compresses 10 intensity words into 5 distinct median outputs: four lower-tier words all map to the same value, while stronger words break into higher regimes (Spearman rho = 0.845, p < 0.001). Second, when the current system state is supplied as context, separate Kruskal-Wallis tests show that grouping by starting allocation captures far more rank-based variance than grouping by word (epsilon-squared baseline = 0.782 vs. epsilon-squared word = 0.079), and lexical differentiation collapses to zero as the system approaches capacity. Third, near feasibility limits the model exhibits three behavioral modes: weak words hedge with small adjustments, strong words abstain entirely, and the word drastically pushes to the local ceiling. These patterns persist across temperature, with stochastic sampling broadening distributions but not restoring ordinal distinctions between words. In this model and domain, the model's numeric interpretation of vague intensity words is compressed, state-dependent, and discontinuous near operational boundaries. --- ### Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks Authors: Haichao Miao, Zhimin Li, Kuangshi Ai, Kaiyuan Tang, Chaoli Wang, Peer-Timo Bremer, Shusen Liu Published: 2026-05-20 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.21825v1 The ability to inspect, interpret, and communicate complex data is crucial for virtually any scientific endeavor, but often requires significant expertise outside the core domain ranging from data management and analysis to visualization design and implementation. We present an end-to-end agentic harness that, based on only the data and a high level description of the tasks, independently designs custom visual analysis applications (VIS apps). This represents an important step towards a general AI co-scientist envisioned by many as an autonomous system that can autonomously execute long horizon tasks based on high-level directions. Our proposed VIS co-scientist is an essential component of this broader AI co-scientist vision: a harness that can autonomously analyze data and design visualization solutions using a collection of agents and specialized skills that coordinate exploratory analysis, plan, configure the environment, implement, validate the interface, and most importantly evaluate the overall task completion. Each stage produces document and instruction artifacts that guide downstream work and enable iterative refinement. We validate this approach on IEEE SciVis Contests spanning multiple science and engineering fields. These contests serve as ideal proving grounds because they encode real-world complexity: ambiguous requirements, diverse data modalities, design trade-offs, and task-driven validation. Given only the data and target tasks, our system autonomously produces functional single-page VIS Apps with verified linked-view behavior, highly customized to domain experts' specified tasks and needs. --- ### Implicit Safety Alignment from Crowd Preferences Authors: Qian Lin, Daniel S. Brown Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21822v1 Reinforcement Learning from Human Feedback (RLHF) can reveal implicit objectives such as safety considerations that go beyond task completion. In this work, we focus on the common safety criteria embedded in crowd preference datasets, where different users may express distinct preferences or objectives, yet follow similar safety principles. Our aim is to discover shared safety criteria from crowd preferences and then transfer them to downstream RL tasks to regularize agent behavior and enforce safety. We first show that direct reward combination-optimizing a preference-learned reward model together with downstream task rewards-has inherent limitations. Motivated by this, we propose Safe Crowd Preference-based RL, a hierarchical framework that extracts safety-aligned skills from crowd preferences and composes them via a high-level policy to safely solve downstream tasks. Experiments across safe RL environments and a preliminary LLM-style task with diverse user goals and shared safety constraints demonstrate that our approach substantially lowers safety costs without access to explicit safety rewards, while achieving task performance comparable to oracle methods trained with ground-truth safety signals. --- ### Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale Authors: Ralph Bulanadi, Jefferey Baxter, Arpan Biswas, Hiroshi Funakubo, Dennis Meier, Jan Schultheiß, Rama Vasudevan, Yongtao Liu Published: 2026-05-20 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2605.21820v1 Self-driving laboratories or autonomous experimentation are emerging as transformative platforms for accelerating scientific discovery. Bayesian optimization (BO) is among the most widely used machine learning frameworks for these purposes, but these BO-based frameworks rely on predefined scalar descriptors to guide experimentation. In many situations, the determination of an appropriate scalar descriptor can be challenging, and may fail to capture subtle yet scientifically important phenomena apparent to experts with interdisciplinary insight. To overcome this limitation, here we develop deep-kernel pairwise learning (DKPL), an approach for autonomous microscopy experiments which incorporates human expertise and interdisciplinary scientific knowledge into an active learning loop. Instead of relying on explicit scalar objectives, DKPL enables experts to directly evaluate which experimental output is more promising using interdisciplinary knowledge. DKPL then learns a latent utility function from these expert judgements to guide subsequent autonomous microscopy experiments. We demonstrate DKPL's performance in learning physically meaningful nanoscale structures while effectively prioritizing high-information measurement regions using an experimental model dataset with known ground truth. We further apply DKPL to analyze the character of ferroelectric domain walls, where we find DKPL capable of distinguishing between high and low characteristic domain-wall angles in bismuth ferrite, and able to discover both head-to-head and tail-to-tail domain-wall character in erbium manganite. This development establishes an approach to integrate expert knowledge into autonomous microscopy experiments and demonstrates a pathway toward expert-guided self-driving laboratories capable of addressing scientific problems beyond the limits of scalar-metrics-driven learning. --- ### Symbolic Density Estimation for Discrete Distributions Authors: Ziwen Liu, Meng Li Published: 2026-05-20 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2605.21813v1 Discrete probability laws underpin statistical modeling, yet the catalog of interpretable distributions has expanded only gradually through centuries of case-by-case mathematical derivations. We introduce symbolic density estimation (SDE), an unsupervised framework that automatically recovers closed-form probability mass functions by composing elementary analytic operations within a structured search space. Our method integrates domain-specific structural priors with evolutionary search and a validity-aware inference stage, and it extends to richer distribution families such as zero inflation and finite mixtures. To support systematic evaluation and future research, we contribute a benchmark dataset spanning a broad collection of commonly used discrete distributions. The proposed algorithm recovers all benchmark families with accurate parameter estimates. A real data application shows that it identifies concise and interpretable mixture models that improve goodness-of-fit over standard models. --- ### Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents Authors: Zijian Du, Nathaniel Pinckney Published: 2026-05-20 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.21810v1 Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, making precise edits, and recovering from sparse hidden-verifier failures. We present Trace2Skill, a test-time scaling framework that improves a hardware agent without RTL-specialized model fine-tuning. Rather than training a new model or only sampling more candidate solutions, Trace2Skill treats the agent's natural-language skill as an evolvable policy. It mines repeated rollout traces for success and failure modes, converts them into dense diagnostics and oracle lessons, and uses an oracle, mutator, and selector loop to produce task-specific skills that guide later search, editing, validation, and recovery. Because final pass/fail labels are often too coarse for hard failures, Trace2Skill also supports bounded runtime dense verifier feedback that returns sanitized functional observations while keeping hidden harnesses and reference solutions inaccessible to the agent. This feedback helps guide skill evolution and agent execution by connecting skill text, verifier evidence, and downstream behavior. Across hard CVDP tasks that defeat the seed CVDP agent, including tasks that also defeat frontier coding agents, Trace2Skill with dense verifier feedback substantially improves task pass rates and produces breakthrough passes on previously unsolved tasks, without requiring high-quality fine-tuning data, specialized RTL model training, or model weight updates. The same framework provides a general test-time scaling strategy that can extend beyond digital design to other verifiable EDA tasks. --- ### When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering Authors: Doeun Lee, Muge Zhang, Yi Yu, Ashish Manne, Stephen Koesters, Frank Wen, Brady Buchanan, Lynda Villagomez, Oluwatoba Moninuola, James Lim, Kathryn Tobin, Andrew Srisuwananukorn et al. Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21807v1 Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These pathways routinely fall short for the long tail of real-world care not covered by guidelines. Most medical large language models (LLMs), however, are trained to encode common, guideline-focused medical knowledge in their parameters. Current evaluations test models primarily on recalling and reasoning with this memorized content, often in multiple-choice settings. Given the fundamental importance of evidence-based reasoning in medicine, it is neither feasible nor reliable to depend on memorization in practice. To address this gap, we introduce OGCaReBench, a free-form retrieval-focused benchmark aimed at evaluating LLMs at answering clinical questions that require going beyond typical guidelines. Extracted from published medical case reports and validated by medical experts, OGCaReBench contains long-form clinical questions requiring free-text answers, providing a systematic framework for assessing open-ended medical reasoning in rare, case-based scenarios. Our experiments reveal that even the best-performing baseline (GPT-5.2) correctly answers only 56% of our benchmark with specialized models only reaching 42%. Augmenting models with retrieved medical articles improves this performance to up to 82% (using GPT-5.2) highlighting the importance of evidence-grounding for real-world medical reasoning tasks. This work thus establishes a foundation for benchmarking and advancing both general-purpose and medical LLMs to produce reliable answers in challenging clinical contexts. --- ### Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models Authors: Kostas Tsampourakis, Víctor Elvira Published: 2026-05-20 Categories: stat.CO, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.21805v1 State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the estimation of latent states and parameters. In this work, we focus on parameter inference, which for SSMs is in general a very challenging problem due to the intractability of the likelihood. Recently, neural estimation methods, such as sequential neural likelihood (SNL), have shown promising results in Bayesian inference problems. In this paper, we show that SNL, when applied to the SSM setting, suffers important limitations, such as requiring a large amount of simulated samples to achieve a moderate performance, scaling poorly with sequence length, while not being amortized. We then introduce a novel inference algorithm called truncated-SNL (T-SNL), which addresses the limitations of SNL. Our algorithm is more accurate, more stable and robust during training, more scalable to longer temporal sequences, and can be amortized when new observations become available. Our experiments show that T-SNL is sample-efficient, robust, and flexible algorithm which outperforms other approaches. --- ### Mapping Tomato Cropping Systems in California Using AlphaEarth Geospatial Embeddings and Deep Learning Analysis Authors: Mohammadreza Narimani, Alireza Pourreza, Parastoo Farajpoor Published: 2026-05-20 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.21804v1 Field-scale crop maps support supply-chain forecasting and policy, yet statewide crop identification still often depends on retrospective surveys or remote-sensing workflows built around hand-engineered spectral features. Those pipelines can be accurate, but they require repeated preprocessing and often lose robustness across years. This study evaluated whether Google DeepMind's AlphaEarth geospatial embeddings can serve as an analysis-ready alternative for mapping processing tomato systems in California. LandIQ 2018 crop polygons were used to assemble a balanced reference dataset of 4,742 tomato and 4,742 non-tomato fields. For each polygon, 64-band AlphaEarth embedding chips were extracted and aligned with binary masks, then divided into spatially independent training (n = 6,638), validation (n = 1,422), and test (n = 1,424) sets. A U-Net segmentation model was trained on AWS SageMaker using a composite masked binary cross-entropy and soft Dice loss. To complement hard predictions, Monte Carlo dropout was retained at inference and repeated 100 times per chip to estimate predictive mean and variance. On the independent test set, the model achieved 99.19% pixel accuracy, 98.69% precision, 99.40% recall, 99.04% F1 score, 98.11% intersection over union, and 99.02% chip accuracy. Uncertainty maps were consistently highest near field edges and low within field interiors. The results show that AlphaEarth embeddings retain crop-relevant spatial and temporal structure and can support accurate, field-scale tomato mapping without manual feature engineering. --- ### Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws Authors: Nandan Kumar Jha, Brandon Reagen Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21803v1 Scaling laws have made language-model performance predictable from model size, data, and compute, but they typically treat the optimizer as a fixed training detail. We show that this assumption misses a fundamental axis of representation scaling: how effectively the optimizer converts added FFN width into utilized spectral capacity. Using eigenspectra of feed-forward network representations, measured through soft and hard spectral-ranks, we find that \emph{the same Transformer architecture realizes markedly different spectral scaling laws when trained with different optimizers}. Holding architecture and width schedule fixed, AdamW exhibits weak hard-rank scaling ($β$=0.44) on rare-token (TAIL) representations where learning is known to be hardest, whereas Muon achieves linear scaling ($β$=1.02) in the same regimes, a $2.3\times$ increase in the scaling exponent. This difference is not reducible to validation loss: AdamW configurations can match low-rank Dion variants in perplexity, under extended training, while exhibiting sharply different spectral geometry, demonstrating that matched loss does not imply matched representation structure. Hard--soft rank asymmetry further reveals that optimizers differ not only in how much capacity is realized, but also in how that capacity is structured across eigenmodes. To disentangle optimizer effects from architectural ones, we compare against architectural interventions (e.g., attention rank and positional encoding), and find that optimizer-induced spectral shifts often exceed the architectural effects. These results suggest optimization as a first-class axis of representation scaling, motivating optimizer--architecture co-design. --- ### Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization Authors: Zheyuan Zhang, Kaiwen Shi, Han Bao, Zehong Wang, Tianyi Ma, Yanfang Ye Published: 2026-05-20 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.21801v1 Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but lack principled mechanisms to distinguish informative from noisy signals. Recent approaches leverage response-level measures as uncertainty signals to regulate group-based optimization methods such as GRPO. Yet their empirical success remains unstable and unclear in how they influence optimization dynamics. In this paper, we provide, to our knowledge, the first principled formulation that interprets uncertainty signals as mechanisms for characterizing and regulating gradient variance and learning signal quality. Based on both empirical and theoretical analysis, we identify two critical gaps of current entropy-based estimators: The anisotropic gap and The calibration gap. Motivated by this analysis, we propose Geometric-aware Calibrated Policy Optimization (GCPO), a novel framework integrating geometry-aware measures to capture semantic disagreement with reward-based calibration to align uncertainty with learning signal strength. Experiments on multiple benchmarks show that our approach more faithfully tracks gradient variability and consistently improves post-training performance. Our results highlight the importance of designing uncertainty signals that are aligned with optimization dynamics, offering a principled perspective for robust post-training. --- ### stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation Authors: Lucas Maes, Quentin Le Lidec, Luiz Facury, Nassim Massaudi, Ayush Chaurasia, Francesco Capuano, Richard Gao, Taj Gillin, Dan Haramati, Damien Scieur, Yann LeCun, Randall Balestriero Published: 2026-05-20 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.21800v1 World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols hindering reproducibility and fair comparison. Current practice is further limited by three key bottlenecks: fragile one-off codebases, slow video data loading, and the lack of standardized generalization benchmarks. We present stable-worldmodel (swm), an open-source platform for standardized and reproducible world modeling research and evaluation. It delivers (1) a high-performance Lance-based data layer with native support and conversion tools for MP4, HDF5, and LeRobot datasets, (2) clean, well-tested implementations of modern world model baselines and planning solvers, and (3) a broad suite of environments and tasks extended with controllable visual, geometric, and physical factors of variation for systematic in-silico evaluation of dynamics understanding, control performance, representation quality, and out-of-distribution generalization. By unifying the full pipeline under a single, scalable framework, \texttt{swm} dramatically reduces research overhead and accelerates trustworthy progress toward reliable world models. --- ### Three Costs of Amortizing Gaussian Process Inference with Neural Processes Authors: Robin Young Published: 2026-05-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.21798v1 Neural processes amortize Gaussian process inference, replacing the exact $O(n^3)$ posterior with a learned $O(n)$ map from context sets to predictive distributions. For a class of latent neural processes, we bound the Kullback--Leibler (KL) divergence between the GP and LNP predictives, decomposing it into three interpretable sources, namely label contamination as the neural process uses label values to estimate a quantity that is label-independent in the exact GP, an information bottleneck because the finite-dimensional representation cannot resolve the full context geometry, and amortization error from a single encoder network shared across all contexts. The bottleneck truncation term decays in the representation dimension $d$ as $O(e^{-cd^{2/d_x}})$ for squared-exponential kernels on $\mathbb{R}^{d_x}$ where $c > 0$ is a kernel-dependent constant and as $O(d^{-2ν/d_x})$ for Matérn-$ν$ kernels, directly linking architecture sizing to kernel smoothness and input dimension. The label contamination term is $O(1)$ in general, with only the observation-noise component decaying as $O(1/n)$, identifying a persistent cost of routing uncertainty estimation through a label-dependent representation. These results characterize the costs of amortization within the analyzed class and yield architectural recommendations to predict variance from context locations alone in the GP-amortization regime, and replace mean aggregation with second-order pooling to close the dominant amortization gap. --- ### MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue Authors: Anna Deichler, Jim O'Regan, Fethiye Irmak Dogan, Lubos Marcinek, Anna Klezovich, Iolanda Leite, Jonas Beskow Published: 2026-05-20 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2605.21796v1 Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing (1) a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry, and (2) a two-stage grounding pipeline that explicitly resolves conversational ambiguity before visual localization. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types. Our contextual rewriting approach improves grounding performance by 11-22 percentage points on average, with a pure detector (GroundingDINO) reaching 56.7% on pronominals after rewriting, nearly double the best end-to-end baseline. Results demonstrate that decoupling linguistic reasoning from visual perception is more effective than end-to-end approaches for conversational grounding. --- ### Targeted maximum likelihood estimation of vaccine effectiveness and immune correlates in test-negative design studies with missing data Authors: Leah I. B. Andrews, Lars van der Laan, Peter B. Gilbert Published: 2026-05-20 Categories: stat.ME, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2605.21793v1 The test-negative design (TND) is a resource-efficient observational study design that can assess vaccine effectiveness and exposure-proximal immune correlates of disease. The TND enrolls symptomatic individuals seeking diagnostic testing and compares case status by an exposure variable, such as vaccination status or immune marker level, that is measured at testing. While the TND reduces confounding by healthcare-seeking behavior, other sources of confounding may remain. TND studies may also have missing data in the exposure variable due to incomplete records or two-phase sampling designs. We present a targeted maximum likelihood estimation approach involving a semiparametric logistic regression model that targets a causal conditional risk ratio of symptomatic disease in the healthcare-seeking population. Under causal and missing at random assumptions, our method produces an efficient, asymptotically linear estimator that provides flexible, data-driven confounding control and valid causal inference when analyzing TND studies with missing exposure variable data. We evaluate our method's finite sample properties using plasmode simulations of a two-phase TND immune correlates study. We also apply our method to assess COVID-19 vaccine effectiveness and antibody marker correlates of COVID-19 from TND study cohorts derived from the Moderna Coronavirus Efficacy phase 3 trial. --- ### Residual Skill Optimization for Text-to-SQL Ensembles Authors: Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant, Nikki Lijing Kuang, Seyedeh Baharan Khatami, Canwen Xu, Xiaodong Yu, Yingyu Lin, Zhewei Yao, Yuxiong He, Babak Salimi Published: 2026-05-20 Categories: cs.CL, cs.AI, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2605.21792v1 Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K. On Spider2-Lite, DivSkill-SQL improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline, with consistent gains across two base models (Opus-4.6 and GPT-5.4). Skills optimized on a single dialect transfer without retraining across dialects (Snowflake, BigQuery, SQLite) and to a different task formulation, such as BIRD-Critic (+2.6 pts). Error diagnostics show up to 3x fewer hallucinated schema references and function calls, indicating that gains come from genuinely reliable complementary skills rather than surface-form variation. --- ### Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging Authors: Aaron Wang, Zihan Zhao, Alan Xia, Chang Sun, Abhijith Gandrakota, Jennifer Ngadiuba, Richard Cavanaugh, Javier Duarte Published: 2026-05-20 Categories: hep-ex, cs.AI arXiv: https://arxiv.org/abs/2605.21789v1 Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems responsible for deciding which collision events to store impose strict latency and accuracy constraints. While transformer architectures achieve the highest jet tagging accuracy when compute is unconstrained, their quadratic self-attention cost makes inference restrictive on trigger budget. Existing efficient variants reduce the computational cost, but hinder the classification performance. To address this limitation, we introduce the Patch Hierarchical Attention Transformer (PHAT-JeT), which combines two mechanisms: a physics-inspired geometric message-passing module that encodes local detector-plane structure, and a hierarchical patch-based attention scheme that computes exact attention within small particle groups while preserving global context through lightweight patch-token communication. Within a restricted budget, PHAT-JeT achieves state-of-the-art accuracy and background rejection among all resource-constrained jet tagging models on four benchmarks (\textsc{hls4ml}, JetClass, Top Tagging, and Quark--Gluon). Our code is available at https://github.com/aaronw5/PHAT-JeT. --- ### SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching Authors: Xuefei Sun, Xujia Zhang, Brendan Crowe, Doncey Albin, Christoffer Heckman Published: 2026-05-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.21788v1 Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relationships from 2D views, which are subsequently lifted into a persistent 3D scene graph encoding both spatial and semantic relations. Given a query, we construct a query graph and perform constrained alignment with the scene graph, ensuring multi-view consistency and interpretable reasoning. Experiments on the ScanRefer benchmark demonstrate that our method achieves competitive performance among zero-shot approaches, using only RGB-D inputs. We further validate our framework through real-world deployment on a mobile robot, demonstrating robust spatial reasoning in long-horizon physical environments. We will make our code publicly available upon acceptance. --- ### MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation Authors: Ahanaf Hasan Ariq Published: 2026-05-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.21783v1 Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to prediction reliability. We develop a PAC-Bayesian framework yielding generalization bounds explicitly parameterized by the maximum mean discrepancy (MMD) between source and target distributions. Our principal contribution is interpreting MMD-balls around the source distribution as credal sets in Walley's imprecise probability theory, yielding natural epistemic uncertainty quantification. We establish: (i) a PAC-Bayesian bound with an MMD-dependent shift penalty under an RKHS-Lipschitz loss assumption; (ii) a finite-sample version via MMD concentration; (iii) a uniform worst-case risk bound over all distributions in the credal set, with a lower-upper risk decomposition; and (iv) geodesic preservation bounds explaining why kernel-guided adaptation protects local feature geometry. The credal set interpretation separates epistemic from aleatoric uncertainty and provides a principled decision criterion for when adaptation is warranted. --- ### Reflective Prompt Tuning through Language Model Function-Calling Authors: Farima Fatahi Bayat, Moin Aminnaseri, Pouya Pezeshkpour, Estevam Hruschka Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21781v1 Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive and highly sensitive to formatting, phrasing, and instruction order, motivating automated prompt optimization methods that reduce manual effort while preserving inference-time flexibility. However, existing methods often search over prompt candidates or use fixed critique-refine pipelines driven by individual examples or small batches, limiting their ability to capture systematic error patterns and make targeted edits grounded in failure history. We propose Reflective Prompt Tuning (RPT), a framework that uses LLM function calling to simulate the iterative workflow of human prompt engineers. An LLM optimizer calls a diagnostic function that evaluates the target model over an entire optimization set, summarizes recurring failure modes, and returns a structured diagnostic report. The optimizer uses this report, together with an accumulated memory of prior reports, to revise the prompt for the next iteration. RPT further supports confidence-aware optimization by using calibration signals in diagnostic feedback and final prompt selection. Across three reasoning tasks, RPT improves over initial prompts by up to 12.9 points, remains competitive with state of the art, and improves confidence calibration. Our analyses show that RPT is especially effective on multi-hop and mathematical reasoning, producing targeted prompt revisions that align with diagnosed failure patterns and lead to gains in task performance and calibration. --- ### Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy Authors: Aman Saxena, Jan Schuchardt, Yan Scholten, Stephan Günnemann Published: 2026-05-20 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2605.21780v1 Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor attacks, where training and test data are jointly perturbed, remains challenging because training- and test-time randomized mechanisms must be analyzed within a single robustness certificate. We address this by connecting randomized smoothing to the dual view of differential privacy through privacy profiles, which provide a numerical procedure for composing heterogeneous mechanisms. The resulting framework enables tight, modular, end-to-end certification of complex, composed mechanisms while leveraging existing analyses of differentially private mechanisms. We instantiate the framework for DP-SGD and Deep Partition Aggregation with inference-time smoothing, deriving joint robustness guarantees against both training-time and inference-time attacks. Experiments on MNIST and CIFAR-10 demonstrate the effectiveness of our framework. Overall, we provide a principled and general framework for using composite mechanisms to certify robustness under complex threat models that better capture the capabilities of real-world adversaries. --- ### What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct Authors: Meryl Ye, Lujain Ibrahim, Jessica Y. Bo, Myra Cheng, Ida Mattsson, Daniel Vennemeyer, Robert Kraut, Steve Rathje Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21778v1 AI sycophancy has become a prominent concern in large language model (LLM) research. Yet the term lacks a consistent definition and has been applied to behaviors ranging from agreeing with a user's false claim to excessively praising the user to withholding corrective feedback. When researchers, companies, and policymakers use the same term to describe different behaviors, evaluation results become difficult to compare, mitigation strategies fail to transfer, and systems that are resistant to one form of sycophancy continue exhibiting other forms. To address this, we make two contributions. First, we reviewed 70 papers on AI sycophancy to develop a taxonomy of how the behavior has been defined and measured. The taxonomy distinguishes (1) whether a model is sycophantic toward a user's positions and beliefs, or toward the user's broader personal traits and emotions, and (2) whether this occurs through explicit, direct language or more implicit, subtle behaviors such as framing, omission, or tone. Mapping existing literature to our taxonomy reveals that current research has focused on overt forms of sycophancy toward users' beliefs, leaving more subtle and person-directed behaviors relatively understudied. Second, we surveyed 106 experts in AI sycophancy and related fields to examine whether researchers agree on which model behaviors are sycophantic. While experts are nearly unanimous in believing that sycophancy is a significant problem in current AI systems (94.3% agree), they disagree substantially on which specific behaviors qualify. Together, these findings demonstrate that AI sycophancy is a broad family of behaviors with different measurement challenges, intervention requirements, and governance implications. Our taxonomy provides a shared vocabulary for understanding and addressing these behaviors. --- ### Understanding Perspectives of Patients, Caregivers and Clinicians towards Emerging Collaborative-decision Making Technologies Authors: Ray-Yuan Chung, Athena Ortega, Zixuan Xu, Daeun Yoo, Jaime Snyder, Wanda Pratt, Aaron Wightman, Ryan Hutson, Cozumel Pruette, Ari Pollack Published: 2026-05-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.21777v1 In pediatrics, patients, caregivers, and clinicians share responsibility for health decisions, but limited collaboration can undermine outcomes. We conducted a qualitative study examining decision-makers perceptions toward collaborative decision-making technologies, including interactive dashboards, VR simulators, and AI voice assistants. Findings reveal differences in user opinions across groups and indicate technology acceptance is linked to users trust of these technologies. Technology developers and researchers need to explore design and implementation strategies that build and facilitate trust or appropriate distrust between users and these novel technologies before these tools can effectively support collaborative decision-making. --- ### PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts Authors: Juliette Woodrow, Chris Piech Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21776v2 Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using only prompts and elicited probabilities. We construct a benchmark from three publicly available human-annotated datasets with ground-truth PMI, and evaluate five information-theoretic prompting-based estimators. Our main method, PromptNCE, frames conditional probability estimation as a contrastive task and augments the candidate set with an explicit OTHER category. The OTHER category allows the model to assign probability mass outside the candidate set, avoiding the closed-set normalization of standard contrastive prompts. PromptNCE gives the best conditional probability estimates on all three datasets. For full PMI, we find that estimating label base rates is the primary bottleneck on two of the three datasets, with the best methods reaching Spearman correlation up to 0.78. We also present a case study in computer science education showing how these estimators can be used to score student knowledge summaries in a low-data setting. We release our code and prompts. --- ### PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts Authors: Juliette Woodrow, Chris Piech Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21776v1 Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using only prompts and elicited probabilities. We introduce a benchmark with human-derived ground-truth PMI across three publicly available datasets, and evaluate five information-theoretic prompting-based estimators. Our main method, PromptNCE, frames conditional probability estimation as a contrastive task and augments the candidate set with an explicit OTHER category. We show theoretically that adding OTHER recovers the true conditional P(y | x) rather than just a ranking over listed candidates, turning a contrastive prompt into a general-purpose zero-shot probability estimator. PromptNCE is the best zero-shot method on all three datasets, reaching Spearman correlation up to 0.82 with human-derived PMI. We also present a case study in computer science education showing how these estimators can be used to score student knowledge summaries in a low-data setting. --- ### HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection Authors: Danyu Sun, Jinghuai Zhang, Yuan Tian, Zhou Li Published: 2026-05-20 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.21773v1 Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion detection from system logs, remains unexplored. In this work, we present a new benchmark to assess LLMs' capabilities in supporting host-based intrusion detection systems (HIDS). This task requires fine-grained reasoning over large-scale, noisy, and highly imbalanced system logs, where complex interactions between benign and malicious activities make reliable detection challenging. Our benchmark unifies three public system log datasets, DARPA-E3, DARPA-E5, and NodLink, and introduces a data construction pipeline that transforms raw host telemetry into LLM-compatible inputs, enabling systematic evaluation under realistic intrusion detection settings. Our evaluation of frontier LLMs reveals substantial performance gaps across datasets. While many models achieve high precision (often above 0.8) on simpler datasets, their performance degrades significantly as system logs become noisier and more complex, with MCC frequently dropping below 0.5 and false positive rates increasing sharply. We further analyze model behavior and identify distinct regimes, including conservative detectors with low false positive rates and over-sensitive models that generate excessive alerts. Overall, our results highlight that while LLMs show strong potential for HIDS, their effectiveness is highly sensitive to data complexity, and robust system design is essential for reliable deployment. --- ### Manifold-Guided Attention Steering Authors: Ian Li, Kapilesh Guruprasad, Raunak Sengupta, Ninad Satish, Loris D'Antoni, Rose Yu Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21770v1 Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation steering. However, existing activation steering approaches apply fixed, pre-computed correction vectors, ignoring where the model currently sits along its generation trajectory; the result is indiscriminate perturbation that disrupts already-correct steps as freely as erroneous ones. We propose Manifold-Guided Attention Steering (MAGS), a trajectory-aware inference-time intervention grounded in a geometric observation: the output activations of specific attention heads diverge from a low-dimensional correctness manifold at the point of error, and this deviation compounds through subsequent steps. For each identified attention head, we learn a low-dimensional subspace from contrastive pairs of correct and incorrect traces that capture the directions along which error behavior deviates from correct behavior. During inference, we monitor each head's proximity to this manifold and apply a targeted projection correction when deviation exceeds a learned threshold, steering the attention output back toward the correct subspace before the error propagates. MAGS consistently outperforms both unsteered baselines and static steering approaches across benchmarks spanning mathematical reasoning (MATH-500, GSM8K), code generation (HumanEval, MBPP), and molecular generation (SMILES), suggesting that correctness manifolds are a general feature of LLM attention geometry. --- ### Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents Authors: Sikuan Yan, Ahmed Bahloul, Ercong Nie, Susanna Schwarzmann, Riccardo Trivisonno, Volker Tresp, Yunpu Ma Published: 2026-05-20 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.21768v1 Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments is challenging because memory turns the agent's past actions into part of its future environment. Once different rollouts write, update, or delete different memories, they no longer share the same intermediate memory state, making trajectory-level comparisons fundamentally unfair. This violates a key assumption behind group-relative methods such as GRPO, where rollouts are compared as if they were sampled from the same effective environment. Consequently, trajectory-level rewards provide noisy or biased credit signals for long-horizon memory operations. To address this challenge, we introduce Memory-R2, a training framework for long-horizon memory-augmented LLM agents. Its core algorithm, LoGo-GRPO, combines local and global group-relative optimization. The global objective preserves end-to-end learning from long-horizon trajectory-level rewards, while local rerollouts compare different memory-operation outcomes from the same intermediate memory state, yielding fairer group comparisons and more precise supervision for memory construction. Beyond credit assignment, Memory-R2 jointly optimizes memory formation and memory evolution with a shared-parameter co-learning design, where a fact extractor and a memory manager are instantiated from the same LLM backbone through role-specific prompts. To stabilize multi-step RL over long memory horizons, we adopt a progressive curriculum that increases the training horizon from 8 to 16 to 32 sessions. Together, these components provide an effective training paradigm for memory-augmented LLM agents in long-horizon multi-session settings. --- ### BodyReLux: Temporally Consistent Full-Body Video Relighting Authors: Li Ma, Mingming He, Xueming Yu, David M. George, Ahmet Levent Taşel, Paul Debevec, Julien Philip Published: 2026-05-20 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2605.21766v1 Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appear to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances. --- ### Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning Authors: Emanuel Sommer, David Rügamer Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21765v1 The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has achieved computational parity with optimization-based methods and is at the verge of superseding such methods for effective and efficient inference in BNNs. This development should be in the interest of the whole community, promoting BNNs as a principled paradigm with its long-standing yet unfulfilled promise of providing principled uncertainty quantification for neural networks. SAI can even do more -- yielding superior prediction performance through model averaging, serving as the foundation for a plethora of possible downstream tasks, and providing crucial insights into the landscape of BNNs. In order to make such a change happen and unfold the potential of sampling, overcoming current misconceptions is a necessary first step. The next step is to realign research efforts toward addressing remaining challenges in SAI. In particular, the community must focus on two core problems: sufficient exploration of the posterior landscape and high-fidelity distillation of posterior samples for efficient downstream inference. By addressing conceptual and practical obstacles, we can unlock the full potential of SAI and establish it as a central tool in Bayesian deep learning. --- ### On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents Authors: Oliver Mortensen, Mohammad Sadegh Talebi Published: 2026-05-20 Categories: cs.LG, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2605.21763v1 We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures called the optimized certainty equivalent (OCE), which includes important risk measures such as entropic risk, CVaR, and mean-variance. Our focus is on the sample complexities of learning the optimal state-action value function (value learning) and an optimal policy (policy learning) under recursive OCE. We provide an exact characterization of utility functions $u$ for which the corresponding OCE defines an objective that is PAC-learnable. We analyze a simple model-based approach and derive PAC sample complexity bounds. We establish that whenever $u$ does not have full domain $\text{dom}(u)\neq \mathbb{R}$, the corresponding problem is not PAC-learnable. Finally, we establish corresponding lower bounds for both value and policy learning, demonstrating tightness in the size $SA$ of state-action space, and for a more restricted class of utilities, we derive lower bounds that makes the dependence on the effective horizon $\frac{1}{1-γ}$ explicit. Specifically, for $\text{CVaR}_τ$ we show that the correct dependence on $τ$ is $\frac{1}{τ^2}$, thus improving by a factor of $\frac{1}τ$ over state-of-the-art although our bound has a suboptimal dependence on $\frac{1}{1-γ}$. --- ### Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans Authors: Juhwan Lee, Ammar Hoori, Tao Hu, Justin N. Kim, Mohamed H. E. Makhlouf, Michelle C. Williams, David E. Newby, Robert Gilkeson, Sanjay Rajagopalan, David L. Wilson Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21762v1 Non-contrast computed tomography calcium scoring (CTCS) is a cost-effective imaging modality widely used to detect coronary artery calcifications. This study aimed to develop an advanced machine learning framework that utilizes quantitative analyses of coronary calcium and epicardial fat from CTCS images to predict obstructive coronary artery disease (CAD). The study population consisted of 1,324 patients from the SCOT-HEART clinical trial who underwent both CTCS and coronary CT angiography. We extracted and analyzed a broad range of features, including 24 clinical variables, 189 calcium-omics, and 211 epicardial fat-omics features from the CTCS images. Feature selection was conducted using the CatBoost algorithm combined with SHapley Additive exPlanation (SHAP) values. Predictive modeling utilized the CatBoost gradient boosting method, focusing on the most informative features. From an initial set of 424 candidate features, 14 were identified as most predictive through the CatBoost-SHAP method. The top two predictive features originated from fat-omics, with the remaining 12 features derived from calcium-omics. The optimized model achieved robust predictive capabilities, demonstrating a sensitivity of 83.1+/-4.6%, specificity of 93.8+/-1.7%, accuracy of 85.3+/-2.0%, and an F1 score of 73.9+/-3.3%. Inclusion of calcium-omics and fat-omics data significantly improved predictive performance. Notably, the model also showed reliable predictive accuracy in patients with diverse coronary calcium scores, including cases with obstructive CAD despite a zero-calcium score. This innovative approach holds promise for improving clinical decision-making and potentially reducing dependence on contrast-enhanced or invasive diagnostic procedures, particularly within low-to intermediate-risk patient groups. --- ### A Causal Argumentation Method for Explainability of Machine Learning Models Authors: Henry Salgado, Meagan R. Kendall, Martine Ceberio Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21758v1 Explainable AI (XAI) methods identify which features are relevant to a model's predictions but often fail to clarify why certain decisions are made. In this work, we present a novel method that integrates causality with argument-based reasoning to explain why models may be making predictions. Our approach first identifies causal relationships among variables using causal discovery methods and then translates these into a Bipolar Argumentation Framework (BAF) to represent supportive and opposing interactions among features. By using semi-stable semantics, we find extensions of features that explain why certain outcomes may have been chosen. We demonstrate our method on two benchmark datasets and compare its results against standard post-hoc explainability approaches. --- ### PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation Authors: Blake Gella, Wei Wu, Yuhao Yin, Zexi Huang, Zikai Wang, Emily Liu, Junlin Zhang, Wentao Guo, Qinglei Wang Published: 2026-05-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.21752v1 Recommender systems trained on user interaction data are susceptible to behavioral intensity imbalance--a systematic distortion arising from heterogeneous engagement patterns across users. This imbalance skews feedback signals such that observed interactions no longer faithfully reflect true preferences, causing models to disproportionately amplify signals from highly active users while underrepresenting others, which ultimately degrades recommendation quality and robustness at scale. To address this issue, we propose a nonparametric contrastive percentile approximation framework, PEARL, that models relative preference signals instead of absolute engagement magnitudes. Building upon relative advantage debiasing, PEARL leverages real contrastive interaction samples to approximate percentile relationships directly, without relying on auxiliary distribution estimation models. We provide theoretical justification demonstrating that such pairwise comparisons yield unbiased estimates of percentile-based preference signals. For broader applicability, we introduce a prediction-based bootstrapping mechanism for percentile smoothing to handle sparse and discrete feedback, alongside a generalized value-weighted formulation and a co-training strategy to enhance both modeling flexibility and representation learning. Extensive offline experiments demonstrate that PEARL effectively mitigates behavioral bias and consistently improves recommendation performance across multiple ranking targets. Deployed in a production livestream platform with a combined user base of billions, online A/B testing confirms substantial real-world gains: +2.10% Watch Duration, +0.80% Consumption Amount, +1.49% Interaction Rate, and -6.91% Report Rate. --- ### Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization Authors: Zhiqi Gao, Albert Ge, Alexander Berenbeim, Nathaniel D. Bastian, Frederic Sala Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21751v2 Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data. We study this via Text2Opt-Bench, a scalable benchmark of solver-verified optimization problems spanning 12 categories, from textbook linear programs to stochastic and multi-objective formulations with up to thousands of variables. Across 10+ models, we find that accuracy collapses as instance data grows, even when the formulation itself is simple. We call this the effective binding limit. We study it with a family of techniques, BIND, that externalize numeric data to structured files so the model binds data programmatically rather than transcribing from the prompt. When using an oracle for externalizing data, we recover between 12 and 27 accuracy points, confirming binding as a key -- but recoverable -- failure mode. In a deployable setting without oracle access, we validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories, with a 1.5B binding specialist alone matching a 7B end-to-end baseline. --- ### RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator Authors: Zhenwei Tang, Zhaoyan Liu, Rasa Hosseinzadeh, Tongzi Wu, Keyvan Golestan, Jesse C. Cresswell Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21748v1 As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human evaluation may be practical, but in complicated systems like conversational chatbots, the amount of generated text can overwhelm human annotation resources. Model developers have begun to rely heavily on auto-evaluation, where LLMs are also used to judge generation quality. However, existing LLM-as-a-judge benchmarks largely focus on simple Q\&A tasks that do not match the complexity of multi-turn conversations. We introduce RankJudge, a benchmark generator for evaluating LLM-as-a-judge on multi-turn conversations grounded in reference documents. RankJudge creates pairs of conversations where one conversation has a single flaw injected into one turn. This construction allows paired conversations to be labeled unambiguously as better or worse, and precisely isolates failure categories to individual turns, enabling a strict joint correctness criterion for judging. We implement RankJudge across the domains of machine learning, biomedicine, and finance, evaluate 21 frontier LLM judges, and rank those judges via the Bradley-Terry model. Our formulation also allows ranking each conversation pair with difficulty ratings, which we use to dynamically curate the evaluation slice to reduce label noise, as confirmed via human annotation. We find that judge rankings are stable under partial observability, coarser correctness criteria, and an alternative random-walk rating algorithm. --- ### Improving 3D Labeling in Self-Driving by Inferring Vehicle Information using Vision Language Models Authors: Steven Chen, Shivesh Khaitan, Nemanja Djuric Published: 2026-05-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.21747v1 We present an approach to improve 3D vehicle labeling in self-driving applications through zero-shot inference of vehicle information, leveraging Vehicle Make and Model Recognition (VMMR) methods. The proposed approach utilizes a Vision Language Model (VLM) to both infer a vehicle's make, model, and generation from image crops, and output accurate 3D bounding box dimensions to seed manual labeling. We evaluate the impact of iterative prompt engineering and the choice of different VLMs on both vehicle bounding box inference and make/model/generation recognition. When compared to strong baselines, the proposed approach not only shows high accuracy, but also excels in mitigating specific failure modes where VLMs provide better dimensions than initial lidar-aided human annotated labels (e.g., in cases of significant vehicle occlusion). Experiments on both public and proprietary data strongly suggest that our conclusions are generalizable across different labelers and datasets. The results demonstrate that integrating VLMs into the labeling process can reduce manual labeling time while increasing label quality. --- ### Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring Authors: Juhwan Lee, Sadeer Al-Kindi, Ammar Hoori, Tao Hu, Hao Wu, Justin N. Kim, Robert Gilkeson, Sanjay Rajagopalan, David L. Wilson Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21745v1 Non-contrast computed tomography calcium scoring (CTCS) is widely recognized as an effective tool for cardiovascular risk stratification. This study aimed to develop a novel machine learning framework for predicting myocardial ischemia from routine non-contrast CTCS scans using quantitative coronary calcium assessment. This study analyzed 1,375 patients who underwent both non-contrast CTCS and regadenoson stress cardiac positron emission tomography myocardial perfusion imaging within one year at University Hospitals Cleveland Medical Center. A total of 74 variables, including clinical variables, Agatston score, and calcium-omics features, were evaluated. Relevant features were identified using XGBoost with Shapley Additive exPlanations (SHAP). Predictive models were trained and evaluated using 5-fold cross-validation. Among 987 patients, 89 (9%) were positive for myocardial ischemia. The final model incorporated the Agatston score, eight calcium-omics features, and age. The proposed model achieved a precision of 98.9+/-3.0%, sensitivity of 79.2+/-8.4, and F1 score of 87.7+/-5.3%. The addition of calcium-omics features significantly improved predictive performance compared with models using clinical variables alone or clinical variables with the Agatston score (p<0.05). Interestingly, the number of calcified arteries, despite being the lowest-ranked feature based on SHAP analysis, showed the strongest association with myocardial ischemia in logistic regression analysis (odds ratio: 3.63, 95% confidence interval: 2.80-4.77, p<0.00001). We developed a machine learning approach for predicting myocardial ischemia using routinely acquired non-contrast CTCS scans. Calcium-omics features provided incremental predictive value beyond conventional risk factors and Agatston scoring and may support more accessible cardiovascular risk stratification. --- ### Who Uses AI? Platform Selection and the Measurement of Occupational AI Exposure Authors: Michelle Yin, Burhan Ogut Published: 2026-05-20 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2605.21743v2 Conversation logs from AI platforms are increasingly used to measure occupational exposure to artificial intelligence, but the users observed in these logs are not the workforce. We show that platform-derived exposure scores combine task-level AI applicability with the occupational composition of the platform's user base. Holding the empirical design fixed, changing only the platform input changes the post-ChatGPT employment coefficient by a factor of 1.9, and consumer and enterprise channels within the same vendor disagree in sign. We formalize the resulting non-classical measurement error, decompose it into between- and within-occupation selection, and construct workforce-reweighted partial-identification bounds. Reweighting to Bureau of Labor Statistics employment shares attenuates estimates by 42 to 93 percent. The bias captures augmentation among observed users more directly than substitution in the workforce. --- ### Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification Authors: Samuel McDowell, Nathan Stromberg, Lalitha Sankar Published: 2026-05-20 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2605.21742v1 Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performance can suffer under the effect of class imbalance, resulting in poor performance for rare classes. Several techniques exist which attempt to mitigate the deleterious effect of class imbalance on classification performance, but the in-context learning (ICL) dynamic of PFNs means that loss-based strategies are impossible, and other techniques are unproven. We have adapted several classical techniques addressing class imbalance and analyzed their performance on PFN classification. We observe that thresholding performs exceptionally well because of the calibration characteristics of PFNs, and downsampling performs comparably because of PFNs exceptional limited-data performance, with the additional benefit of reduced computation cost for inference. ---