# Research Papers — 2026-06 · bundle page 227 of 260

> Full-text markdown of papers #11301–11350 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-06/page/227
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/226.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/228.md)

### AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Authors: Zhangchen Xu, Junda Chen, Yue Huang, Dongfu Jiang, Jiefeng Chen, Hang Hua, Zijian Wu, Zheyuan Liu, Zexue He, Lichi Li, Shizhe Diao, Jiaxin Pei et al.
Published: 2026-06-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.05080v1

Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons. To address this gap, we introduce AutoLab, a new benchmark for ultra long-horizon closed-loop optimization. AutoLab consists of 36 realistic, expert-curated tasks spanning four diverse domains: system optimization, puzzle & challenge, model development, and CUDA kernel optimization. Each task begins with a correct but deliberately suboptimal baseline and challenges agents to improve it within a strict wall-clock budget. Evaluating 17 state-of-the-art models reveals the dominant predictor of success is not the quality of an agent's initial attempt, but its persistence in repeatedly benchmarking, editing, and incorporating empirical feedback. While claude-opus-4.6 exhibits strong long-horizon optimization capabilities, most frontier models, including several proprietary ones, either terminate prematurely or exhaust their budgets with minimal progress. These results underscore the importance of time awareness and persistent iteration in autonomous agents. We open-source the full benchmark, evaluation harness, and task artifacts, to accelerate research toward truly capable long-horizon agents.

---

### Fast & Faithful Function Vectors

Authors: Minh An Pham, Anton Segeler, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin, Patrick Kahardipraja, Reduan Achtibat
Published: 2026-06-03
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.05079v1

Function vectors (FVs) are task representations elicited during in-context learning that can be used to steer Large Language Models (LLMs). However, design choices in their formulation remain underexplored. In this work, we study the impact of varying FV definitions for instructions along two degrees of freedom: attention head selection and steering. For head selection, using gradient-based attributions with Layer-wise Relevance Propagation (LRP) substantially improves efficiency as well as accuracy. For FV steering, applying it in a distributed manner yields a higher accuracy compared to simple aggregation. Our code is publicly available.

---

### Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness

Authors: Lixing Zhang, Yidong Ouyang, Weifu Li, Shixiang Zhu, Guang Cheng, Liyan Xie
Published: 2026-06-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.05073v1

Missing value imputation is a fundamental task in machine learning, with most existing methods assuming that all missing entries correspond to unobserved regular values. In many real-world datasets, however, missingness may arise from two distinct sources: some entries are meaningfully missing (intrinsically absent and semantically valid), while others are missing due to the observation process and should be imputed. We formalize this distinction as a selective imputation problem, where the goal is to jointly infer which missing entries should be preserved and which should be recovered. To address this challenge, we propose Diff-Joint, a diffusion-based framework that jointly models tabular data together with a latent missingness mask. The method alternates between conditional sampling and uncertainty-aware aggregation to iteratively refine both imputed values and missingness labels. Empirical results on synthetic and real-world datasets demonstrate that Diff-Joint effectively identifies meaningfully missing entries while achieving competitive imputation accuracy and improved downstream task performance.

---

### InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space

Authors: Jiarui Wu, Yujin Wang, Ruikang Li, Fan Zhang, Mingde Yao, Tianfan Xue
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.05071v1

Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but often struggles with both fidelity issues due to its generative nature and efficiency because of its iterative sampling process. In this work, we propose an efficient and fidelity-preserving retouching method using bilateral space manipulation, which is both compact and content-decoupled. Specifically, instead of directly editing pixels or image latents, our model predicts a low-resolution bilateral grid of affine transforms, which are sliced using a learned guidance map and then applied to the full-resolution image. This approach yields both high fidelity and improved efficiency. To retain strong priors of a pretrained generative model, we distill a multi-step diffusion model into our bilateral grid framework using Variational Score Distillation, complemented by a prompt alignment loss to guide instruction-following behavior. Additionally, we introduce a new benchmark and evaluate our method across multiple dimensions: fidelity, instruction following, and efficiency. Compared to the latest retouch methods, like Gemini-2.5-Flash (Nano-Banana), our method can avoid content drift, significantly improve latency, and generate visually pleasing edits, while maintaining a high level of fidelity. Project page: https://openimaginglab.github.io/InstantRetouch/.

---

### RIDE: An Open Dataset and Benchmark for Train Delay Prediction

Authors: Clément Elliker, Mathis Le Bail, Clément Mantoux, Jesse Read, Sonia Vanier
Published: 2026-06-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.05070v1

Train delay prediction is an important problem for both passengers and railway operators, yet progress in the field remains difficult to assess due to the lack of standardized datasets, prediction targets, and evaluation protocols. To address this gap, we introduce RIDE, an open dataset and benchmark for train delay prediction built at nationwide scale over the Belgian railway network. RIDE covers 94.5M train events, 3.6M journeys, and 35.7M weather records from 2023 to 2025. It is organized as a layered data pipeline from raw railway and weather sources to two public releases: a reusable intermediate relational dataset and model-ready benchmark datasets. The benchmark standardizes the prediction task and the training and testing data. It also provides a unified evaluation protocol that supports direct comparison across models. Using this framework, we provide the first comprehensive comparative evaluation of non-learning, statistical learning, and deep learning models. We show that learning-based methods clearly outperform non-learning models, with graph neural networks achieving the best mean performance, while the strongest learning-based models remain relatively close to one another. Beyond aggregate mean absolute error (MAE) and root mean squared error (RMSE), the framework also provides breakdowns by prediction horizon and delay change, enabling more detailed analysis of model behavior across forecasting regimes.

---

### MaCo-GAN: Manifold-Contrastive Adversarial Learning for Single Image Super-Resolution

Authors: Daeyoung Han, Seongmin Hwang, Moongu Jeon
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.05068v1

Conventional Generative Adversarial Networks (GANs) for Single Image Super-Resolution (SISR) often struggle with hallucinated artifacts, largely because standard discriminators evaluate overall image naturalness rather than strict conditional realism. To address this, we propose MaCo-GAN, a novel manifold-contrastive GAN framework that replaces the conventional adversarial loss with a supervised contrastive objective. A core component of our method is a dynamic fake sample synthesizer that transforms ground truth (GT) data into a spectrum of challenging, perceptually plausible fake images that strictly maintain low-resolution (LR) correspondence. Utilizing these synthesized samples, we establish a robust contrastive minimax game: the generator is trained to attract its predictions toward on-manifold fakes (low distortion) and repel them from off-manifold fakes (high distortion), while the discriminator optimizes the exact opposite. By simply replacing the adversarial loss of a baseline SR model with our proposed objective, we demonstrate consistent improvements in the perception-distortion trade-off across various benchmarks. Extensive ablation studies validate the effectiveness of our framework and provide deep insights into the dynamics of this conditional contrastive game.

---

### FLAGG: Flexible Autoregressive Graph Generation

Authors: Samuel Cognolato, Alessandro Sperduti, Luciano Serafini
Published: 2026-06-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.05067v1

The Deep Graph Generation's panorama spans two extremes: one-shot and sequential models. The former generates nodes and edges jointly, while the latter samples them autoregressively. Each method performs better in different graph domains depending on size and topology, but neither is applicable to all graph categories. For instance, one-shot methods struggle with generating large graphs, while sequential methods underperform on smaller graphs. A possible way to overcome these limitations is to flexibly combine the two methods in a unique system. In this work, we propose the FLAGG (Flexible Autoregressive Graph Generation) framework, which sequentially generates portions of graphs with one-shot models. FLAGG can apply any one-shot model to make it autoregressive, allowing flexibility in choosing the sequential policy. This policy is specified through a stochastic node removal process, which an Insertion Model learns to reverse. We evaluate FLAGG with the DiGress one-shot model on several data sets of different graph sizes and domains. We show that the approach outperforms both one-shot and autoregressive baselines in terms of sampling quality.

---

### UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD

Authors: Jingyuan Chen, Sheng Jin, Haopeng Sun, Wentao Liu, Chen Qian
Published: 2026-06-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.05058v1

Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in isolation, and multi-modal, multi-task learning for CAD is hindered by the absence of a unified benchmark. To address this gap, we introduce UniCAD, a comprehensive benchmark for multi-modal CAD learning that covers point-to-CAD reconstruction, text/image-to-CAD generation, and CAD question answering across diverse input modalities. Alongside the benchmark, we present UniCAD-MLLM, a universal multi-modal large language model that ingests text, images, sketches, and point clouds and performs these heterogeneous tasks in an end-to-end fashion within a single framework. Extensive experiments on the UniCAD and Fusion360 benchmarks demonstrate that UniCAD-MLLM achieves state-of-the-art performance across all tasks, outperforming existing task-specific and multi-task baselines. We will release the dataset, code, and pretrained models to accelerate future research.

---

### Boosting Self-Consistency with Ranking

Authors: Maria Marina, Daniil Moskovskiy, Sergey Pletenev, Mikhail Salnikov, Alexander Panchenko, Viktor Moskvoretskii
Published: 2026-06-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.05054v1

Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer, but majority voting often fails to recover correct answers that are already present among the samples. We address this limitation with Ranking-Improved Self-Consistency (RISC), which reformulates answer selection in self-consistency as a ranking problem. Instead of relying on a single uncertainty or confidence signal, RISC uses a lightweight LambdaRank model to score candidate answers with five carefully designed features that capture answer frequency, semantic centrality, and reasoning-trace consistency. We evaluate RISC on three datasets under a range of test-time budgets. Across datasets, RISC consistently achieves a better accuracy-efficiency trade-off than standard self-consistency and strong baselines, with particularly large gains on question answering benchmarks. Further analysis shows that the proposed features are individually useful and, more importantly, complementary, highlighting the value of learning to combine multiple informative signals for test-time answer selection.

---

### Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin

Authors: Zhilong Song, Zongmin Zhang, Lixue Cheng
Published: 2026-06-03
Categories: cond-mat.mtrl-sci, cs.AI, physics.chem-ph
arXiv: https://arxiv.org/abs/2606.05050v2

Theoretical heterogeneous catalysis promises rapid catalyst discovery, yet computational and machine-learning predictions often deviate from experiment and stay confined to narrow material families, for want of a faithful, condition-aware catalytic simulator. We present CatDT (Catalysis Digital Twin), a self-evolving multi-agent system that builds an autonomous digital twin of a working catalyst, unifying gas-solid and liquid-solid modeling. From only a bulk crystal and a natural-language reaction description, eight specialized agents and 27 scientific tools predict stable facets, reconstruct working surfaces, enumerate and rank reaction pathways, locate transition states, and compute kinetics in 5-30 min on a single GPU. Two innovations address the hardest steps: UniMech finds dominant pathways for novel materials at over $10^3\times$ lower cost than exhaustive enumeration by fusing agent-guided proposals with energy-cached graph search, and a memory-augmented reinforcement loop raises barrier-calculation success from 41% to 84% across 600 catalytic surfaces. Across seven gas-solid benchmarks -- stepped metals, single-atom catalysts, ordered intermetallics, vacancy-rich 2D sulfides and carbides, and a strong-metal--support-interaction (SMSI) interface -- every CatDT prediction lies within 0.5-2 times experiment over four orders of magnitude. For propane dehydrogenation, CatDT independently discovers non-precious candidates rivaling the Pt-based industrial benchmark, with a proposed Ni@ZrO$_2$ SMSI overlayer reaching a simulated TOF of $1.63~\text{s}^{-1}$ at $\sim$100% selectivity. More broadly, the decisive factor for a faithful catalyst digital twin -- or any multi-stage scientific simulator -- is not raw LLM capability but the engineered harness around it: deterministic tools, persistent memory, and verified self-improvement that compound across models, tools, and runs.

---

### Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning

Authors: Meher Chaitanya, My Le, Luana Ruiz
Published: 2026-06-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2606.05046v1

We introduce Graph Cascades, a mesoscopic rewiring strategy for Graph Neural Networks (GNNs) and Graph Transformers (GTs) that captures intermediate-scale graph structure beyond purely local edges or fully global attention. Using contagion-based diffusion processes, Graph Cascades constructs, in O(|V|+|E|) time, an auxiliary graph where node pairs supported by repeated multi-hop reinforcement are promoted to direct neighbors. We theoretically characterize when reinforcement-based rewiring helps: sufficient conditions under which reinforcement-based edge selection is more label-aligned than direct adjacency, an SBM witness in which two-hop reinforcement is perfectly homophilic, and a formalization of mesoscopic connectivity via graph effective resistance. Empirically, across node-classification benchmarks, Graph Cascades improves multiple GNN and sparse-GT backbones, with the most reliable gains observed on heterophilic and moderate- to high-degree homophilic graphs. The theoretical conditions also identify regimes where mesoscopic rewiring is unlikely to be beneficial -- low-degree regular graphs and graphs with structural bottlenecks -- and these predictions match the observed failures. We additionally observe tight correlations between performance and structural properties in the rewired graphs.

---

### Learning Control-Affine Reduced-Order Models via Autoencoders

Authors: Ali Mjalled, Martin Mönnigmann
Published: 2026-06-03
Categories: math.DS, cs.LG
arXiv: https://arxiv.org/abs/2606.05045v1

We present in this paper a framework for the identification of control-affine reduced-order models (ROMs). The proposed method utilizes autoencoders (AEs) to transform the high-dimensional states, and potentially the high-dimensional inputs, into reduced latent ones suitable for control-affine state-space dynamics. This is achieved by simultaneous training of the AE and the state-space model. In addition, we extend the discrete ROM formulation to a sequence-based model, which processes state and input histories to improve prediction accuracy while preserving the control-affine structure. We motivate our framework by applying feedback linearization to the derived models, and we present guidelines for its efficient use. The proposed framework is assessed on two numerical examples and its performance is compared to a baseline model, where the AE identifies a latent space with linear state-space dynamics. The assessment involves evaluating the prediction accuracy of the ROM on test data and its effectiveness in controlling the system to a desired state or trajectory.

---

### Strabo: Declarative Specification and Implementation of Agentic Interaction Protocols

Authors: Samuel H. Christie, Amit K. Chopra, Munindar P. Singh
Published: 2026-06-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.05043v1

The last few years have witnessed major advances in the modeling and implementation of multiagent systems based on declarative interaction protocols. Our contribution, Strabo, establishes the relevance of these advances to ongoing industry efforts in Agentic AI. Specifically, we consider UCP, the Universal Commerce Protocol, a recent Google-led effort to standardize e-commerce interactions for AI agents. Our exercise is in two parts. One, we model the part of UCP dealing with checkouts as a declarative Langshaw protocol and implement agents using Peach, a programming model for Langshaw. This part of the exercise brings out the advantages of formal, declarative specifications. Two, we show that Peach agents can interoperate with UCP agents implemented by Google, thereby establishing the fidelity of our approach with respect to UCP. Such interoperation enables the incremental introduction of declarative protocols and agents into a conventional setting, indicating a pathway by which EMAS ideas could influence practice without demanding a wholesale update.

---

### In-Context Graphical Inference

Authors: Zehua Cheng, Wei Dai, Jiahao Sun
Published: 2026-06-03
Categories: cs.LG, cs.CL, cs.SC
arXiv: https://arxiv.org/abs/2606.05042v1

Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth graphs, while iterative approximations (Belief Propagation, variational methods) sacrifice convergence guarantees on frustrated topologies. We argue that this dichotomy stems from a mismatched inductive bias: iterative methods abandon the sequential elimination structure that makes exact inference correct. We introduce In-Context Graphical Inference (ICG-I), an autoregressive Graph Transformer that restores this structure by mimicking Variable Elimination with learned, Tensor- Train-compressed intermediate factors, paired with a Dirichlet output layer and Weighted Conformal Prediction for calibrated, distribution-free coverage guarantees under topological shift. We prove that TT compression errors propagate at most lincarly through the autoregressive chain, that the Dirichlet-Multinomial loss is a proper scoring rule, and that WCP maintains coverage with a quantifiable degradation under estimated density ratios. We conducted intensive experiments to evaluate ICG-I and achieved state-of-the-art performance across all benchmarks. ICG-I reduces MAE from 0.041 (best baseline) to 0.020 on standard instances and achieves 0.048 on N=500 frustrated spin glasses where BP diverges entirely.

---

### Self-Reflective APIs: Structure Beats Verbosity for AI Agent Recovery

Authors: Arquimedes Canedo, Grama Chethan
Published: 2026-06-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2606.05037v1

When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recovery\_feedback.suggestions() payload sufficient for the agent to repair the request and retry without external reasoning. On a leak-audited pilot ($N{=}30$ per cell, 3 LLMs, 10 adversarial tasks), structured suggestions lift task-completion rate by $+36.7$--$40.0$pp over plain-English diagnoses on Anthropic models (Fisher's exact $p \le 0.0022$), at $1.8$--$2.2\times$ better per-success token efficiency. The lift is not significant on gpt-4o-mini ($p{=}0.435$); a second-domain replication on a billing API confirms the pattern. The comparison only holds after auditing two undocumented classes of answer leakage in LLM benchmarks. We shipaudit\_prompt\_leakage.py as reusable CI infrastructure. Code and data: https://github.com/arquicanedo/self-reflective-apis.

---

### Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping

Authors: Peilin Tao, Chong Cheng, Yuansen Du, Caiwei Song, Zhengqing Chen, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Hainan Cui, Shuhan Shen
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.05035v2

Long-horizon online visual mapping requires continuous camera-motion and scene-geometry estimation under bounded computation. Recent feed-forward 3D reconstruction models provide strong geometric priors, but streaming variants often predict poses in a fixed or historically maintained coordinate system, leading to train--test mismatch, early-anchor attention bias, and accumulated drift. We propose \emph{Anchor3R}, a current-centric streaming 3D reconstruction framework that predicts window-relative poses and local geometry in the current-frame coordinate system. Overlapping predictions form a dense relative-pose graph, supporting online pose updates and loop-aware motion averaging for global reconstruction. Experiments on indoor, outdoor, driving, and RGB-D benchmarks demonstrate improved long-horizon pose accuracy and dense reconstruction quality over existing streaming baselines. Despite being trained only on 48-frame sequences, Anchor3R directly generalizes to streams exceeding 10,000 frames while maintaining bounded GPU memory during online inference. Code is available at https://github.com/polar-explorer/Anchor3R.

---

### Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping

Authors: Peilin Tao, Chong Cheng, Yuansen Du, Caiwei Song, Zhengqing Chen, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Hainan Cui, Shuhan Shen
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.05035v1

Long-horizon online visual mapping is a core capability for robot perception, requiring continuous camera-motion and scene-geometry estimation from visual streams under bounded memory and computation. Recent feed-forward 3D reconstruction models provide strong geometric priors, but their streaming variants often predict poses in a fixed coordinate system tied to the first frame or a persistent scene memory. This fixed-gauge design leads to train--test mismatch, attention bias toward early anchors, and accumulated drift on sequences much longer than those seen during training. We propose \emph{Anchor3R}, a streaming 3D reconstruction framework that treats feed-forward reconstruction as current-centric local measurement prediction rather than persistent global-gauge regression. At each time step, Anchor3R predicts window-relative poses and a local pointmap in the current-frame coordinate system, turning streaming reconstruction into relative-pose measurement generation. These measurements support online pose updates, while loop-closure reinsertion and motion averaging align the trajectory and transform local pointmaps into a coherent global reconstruction. Experiments on indoor, outdoor, driving, and RGB-D benchmarks show that Anchor3R improves long-horizon pose accuracy and dense reconstruction quality over existing streaming baselines, while supporting bounded-memory online inference.

---

### MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation

Authors: Dewei Zhou, Xinyu Huang, Xun Wang, Ji Xie, Yabo Zhang, Liang Li, Kunchang Li, Zongxin Yang, Yi Yang
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.05031v1

Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight approach enables pixel-level control of an object's position with one token or its bounding box with two, all without requiring architectural changes or bespoke attention masking. The MetaPoint tokens are designed to be compositional, serving as spatial primitives. This allows a planner agent to decompose a high-level user request into a structured sequence of primitives for the generator. By providing a simple, precise, and scalable building block for spatial control, MetaPoint unlocks more powerful compositional generative agents and enables intuitive, interactive editing systems.

---

### Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair

Authors: Zehua Cheng, Wei Dai, Jiahao Sun, Thomas Lukasiewicz
Published: 2026-06-03
Categories: cs.CL, cs.SC
arXiv: https://arxiv.org/abs/2606.05030v1

Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior tokens. This unidirectional inductive bias renders even capable models susceptible to error snowballing, wherein a single logical or arithmetic mistake in an early step irreversibly corrupts the entire reasoning chain. We introduce Teleological Reasoning Infilling (\TRI{}), a training framework that endows decoder-only transformers with a native \emph{goal-conditioned bridging} capability. The key insight is to reframe erroneous reasoning segments as fill-in-the-middle (FIM) tasks: given a verified prefix premise $P$, a verified downstream milestone $S$, and the original query $Q$, the model must synthesise the logical bridge $M$ that connects $P$ to $S$ rigorously and completely. To achieve this with standard causal architectures, we introduce a Prefix-Suffix-Middle (PSM) sequence rearrangement with three non-overlapping sentinel tokens, enabling $M$ to attend to both $P$ and $S$ without any structural modification to the self-attention mechanism. Training proceeds in two stages: (i) Supervised Fine-Tuning (SFT) on symbolically verified $(P, S, M)$ triples extracted from formal mathematics corpora, and (ii) Direct Preference Optimisation (DPO) with a deterministic symbolic verifier (Lean 4 / Python) as the sole reward oracle, eliminating LLM-judge sycophancy. At inference, TRI operates as a surgical repair module within a dual-system loop: a causal draft model generates an initial trace, the verifier pinpoints failures, and TRI infills only the damaged segment, leaving verified sections intact. Comprehensive experiments on three benchmarks demonstrate that TRI achieves state-of-the-art performance across all tasks, while reducing per-problem token expenditure by 31.2%.

---

### Validity Threats for Foundation Model Research

Authors: Gunnar König, Martin Pawelczyk, Ulrike von Luxburg, Sebastian Bordt
Published: 2026-06-03
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2606.05029v1

Controlled experiments are the backbone of machine learning research, but at the scale of modern foundation models, they have become prohibitively expensive. Instead, the community increasingly relies on research strategies that approximate the ideal experiment at a fraction of the cost: proxy experiments and scaling laws, observational studies with publicly available models, and single-run designs that leverage variation within individual training runs. In this work, we argue that there is no free lunch when approximating large-scale experiments on a compute budget. Specifically, savings in compute come at the cost of validity threats -- hidden and sometimes untestable assumptions that, when violated, can invalidate research claims. To help navigate such threats, we propose an evaluation framework that casts foundation model research as a causal inference problem. Within this framework, we evaluate different research strategies through four types of validity adapted from the empirical social sciences -- statistical, internal, external, and construct validity. We find that each strategy comes with a characteristic validity profile: proxy experiments trade external and construct validity for statistical and internal validity; observational studies face confounding and effect heterogeneity; and single-run designs are strained by interference between treated units. This analysis reveals several validity threats that have received insufficient attention in the literature. Overall, our evaluation framework provides researchers with a practical toolkit for scrutinizing validity threats in foundation model research~designs.

---

### Invariant Gradient Alignment for Robust Reasoning Distillation

Authors: Zehua Cheng, Wei Dai, Jiahao Sun
Published: 2026-06-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.05025v1

Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differs from training data, even when the logical structure is identical. This undermines knowledge distillation pipelines that transfer chain-of-thought reasoning to smaller students. We introduce Invariant Gradient Alignment (IGA), a training framework that aligns gradient updates across semantically diverse but logically isomorphic examples via three innovations: (i) Logical Isomer Sets, groups of problems sharing identical logical structure across distinct semantic domains (mathematics, medicine, law, science); (ii) a differentiable \emph{Continuous Gradient Conflict Mask}, that suppresses parameter dimensions with high cross-domain gradient variance while preserving invariant directions; and (iii) a truncated SVD projection of the masked gradient back onto the LoRA low-rank manifold, maintaining parameter efficiency throughout. Theoretically, IGA yields tighter OOD generalization bounds than ERM, scaling with the number of isomer domains, and converges at the standard SGD rate under mild regularity. Empirically, IGA outperforms eight baselines across four benchmarks with accuracy gains up to 14.3 pp over ERM-SFT and a Logical Consistency Score of 0.031 versus 0.142 -- a fourfold improvement in representational invariance.

---

### Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling

Authors: Marc Walden, Jason Liu, Shaashwath Sivakumar, Ryan Liu, Hamza Khan
Published: 2026-06-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.05021v1

We investigate multi-agent deep reinforcement learning and propose two enhancements to the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. First, we introduce a novel Action Inference mechanism that enables each agent to predict other agents' intended actions, thereby improving the accuracy and stability of its own policy. Second, we apply an importance sampling strategy, using geometric distribution, in the replay buffer to prioritize more recent and informative experiences, which helps mitigate the non-stationarity inherent in multi-agent environments. We evaluate both modifications on the discrete-action Predator-Prey task provided by the PettingZoo library, a flexible Python interface for general multi-agent reinforcement learning benchmarks. Our results indicate that Action Inference is effective in improving learning stability and inter-agent cooperation and that importance sampling using geometric distribution can lead to significant improvements in exploration efficiency over standard MADDPG. Code available at https://github.com/shaashwathsivakumar/MARL_Proj

---

### Handwriting Extraction and Analysis of Signature Lists in Swiss Popular Initiatives

Authors: Marco Peer, Thomas Gorges, Mathias Seuret, Vincent Christlein, Andreas Fischer
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.05018v1

Popular initiatives and referendums are central to Swiss democracy, yet the validation of handwritten signature lists remains a labor-intensive manual process. This paper investigates the potential of automated document analysis methods, including OCR and AI-based handwriting analysis, to support this task. We propose a pipeline combining template-based line segmentation with text recognition and writer retrieval techniques, evaluated on a dataset of 443 handwritten entries from 418 writers. Results show that OCR struggles with out-of-vocabulary handwriting, with a CER of 29.6% for first names. In contrast, writer retrieval performs more robustly, reaching an mAP of 50.6%. Furthermore, our experiments indicate that off-the-shelf OCR systems are not sufficiently reliable for transcription of handwritten signature data, particularly for short, out-of-vocabulary entries such as names or addresses. However, writer retrieval methods can effectively identify visually similar entries across signature lists, making them a suitable tool for supporting the detection of potential duplicate submissions based on handwriting similarity.

---

### TaDA: Calibrated Probe Gating for Task-Domain LoRA Merging

Authors: Huy Quoc To, Fuyi Li, Guangyan Huang, Ming Liu
Published: 2026-06-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.05016v1

Combining a task LoRA adapter with a domain LoRA adapter into a single unified model is a practical yet largely unexplored challenge. Existing methods treat both adapters as symmetric peers, applying uniform weights across all layers. We argue that task and domain adapters exhibit a consistent depth-dependent asymmetry across transformer architectures. Domain dominance increases with layer depth, while shallower layers retain stronger task-relevant signals. Motivated by this observation, we propose $\textbf{TaDA}$ ($\textbf{Ta}$sk-$\textbf{D}$omain LoR$\textbf{A}$ Merging), a training-free algorithm that exploits this structure through calibrated probe-guided per-layer gating and per-component subspace-aware merging. The gating assigns individual weights per layer and projection type using a probe signal proved invariant to adapter weight magnitude. The merging discards conflicting singular directions before combining the remaining components. $\textbf{TaDA}$ produces a standard rank-$r$ LoRA adapter with zero inference overhead. On six scientific QA benchmarks with Llama-2-7B, TaDA achieves an average accuracy of 0.452, outperforming DARE-TIES by +3.6 percentage points and obtaining the best result on all six benchmarks. On six image classification benchmarks with ViT-L/16, TaDA reaches 85.9\% average accuracy, improving over the strongest merging baseline while leading in three of the six individual benchmarks.

---

### Depth-Attention: Cross-Layer Value Mixing for Language Models

Authors: Boyi Zeng, Yiqin Hao, Zitong Wang, Shixiang Song, He Li, Feichen Song, Yifan Liu, Ziwei He, Xinbing Wang, Zhouhan Lin
Published: 2026-06-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.05014v2

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference--a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache--the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

---

### CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation

Authors: Yurim Jeon, Dongseong Seo, Seung-Woo Seo
Published: 2026-06-03
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2606.05011v1

Cross-view geo-localization estimates the geographic location of a ground image by matching it against an aerial image database. Existing methods tackle this through either large-scale retrieval or precise pose estimation, but not both: retrieval-based methods enable wide-area search at the cost of localization accuracy, while pose estimation methods achieve high precision within only a narrow search space. Naively cascading these pipelines introduces error propagation and inconsistent feature representations. We formulate cross-view geo-localization as a unified problem requiring simultaneous city-scale retrieval and precise 3-DoF pose estimation. We propose CIPER (Cross-view Image-retrieval and Pose-estimation transformER), a single architecture that jointly performs both tasks through mutually beneficial feature learning. CIPER uses a shared transformer encoder with task-specific tokens to disentangle global retrieval features from spatial localization cues. To bridge the large domain gap between ground and aerial views, we introduce a two-way transformer pose decoder that uses ground features as spatial queries for bidirectional cross-attention. A set prediction strategy further enables stable 3-DoF regression under a unified multi-task objective. Experiments on VIGOR, KITTI, and Ford Multi-AV demonstrate competitive performance, especially under limited field-of-view and arbitrary orientation conditions. Code is available at https://github.com/yurimjeon1892/CIPER.

---

### DAR: Deontic Reasoning with Agentic Harnesses

Authors: Guangyao Dou, William Jurayj, Nils Holzenberger, Benjamin Van Durme
Published: 2026-06-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.05009v1

Deontic reasoning is the task of answering questions by applying explicit rules and policies to case-specific facts, for example computing tax liability under a statute or determining the outcome of an immigration appeal. A key technical challenge for LLM-based deontic reasoning is that the relevant ruleset can be long and cross-referenced, so models may still fail to locate the rules needed for a particular reasoning step. We introduce Deontic Agentic Reasoning (DAR), an agentic reasoning setup in which the model interacts with the statutes on demand. We evaluate DAR under multiple harnesses on hard subsets of DeonticBench. Across these settings, we find that agentic harnesses can push the frontier on deontic reasoning tasks, but improvements are not uniform: weaker models often degrade on numerical tasks while consuming far more tokens.

---

### M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks

Authors: Jie Huang, Ruixun Liu, Sirui Sun, Xinyi Yang, Yin Li, Yixin Zhu, Yiwu Zhong
Published: 2026-06-03
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.05008v1

As multi-modal models advance towards long-form video understanding, memory emerges as a critical capability. Despite substantial efforts in developing video datasets and benchmarks, existing works primarily focus on perception and reasoning, without systematically evaluating memory: what models retain, how faithfully information is preserved, and how robust memory remains under interference. To address this gap, we introduce M$^3$Eval, the first comprehensive evaluation framework and benchmark for probing different memory dimensions in multi-modal models. Grounded in cognitive psychology, our design features carefully constructed tasks that isolate key aspects of memory. Leveraging M$^3$Eval, we conduct extensive experiments across representative multi-modal models, revealing consistent weaknesses and distinctive behaviors. We find that models struggle to maintain disentangled representations when processing parallel video streams, exhibit interference patterns differing substantially from those observed in human memory, ground memory sources more reliably in the spatial domain than the temporal domain, and demonstrate limited symbolic memory. Collectively, our benchmark provides a valuable resource for future research, while our findings highlight memory as a fundamental yet underexplored capability and offer insights for designing more effective memory mechanisms in multi-modal models. Our code and dataset are available at https://pku-value-lab.github.io/m3eval-homepage.

---

### SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

Authors: Peihua Mai, Xuanrong Gao, Youlong Ding, Xianglong Du, Wei Liu, Yan Pang
Published: 2026-06-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.05004v1

With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-preserving inference methods sacrifice either utility or efficiency, and often require model-specific modifications that limit their compatibility. In this paper, we propose SharedRequest, a model-agnostic framework for privacy-preserving LLM inference that reformulates privacy protection at the batch level rather than the individual-prompt level. The key idea is to obscure sensitive information by mixing original prompts with noisy variants, while grouping semantically equivalent instructions to amortize the inference cost over a large batch of queries with minimal impact on LLM response quality. This design is independent of the LLM architecture, requiring no access to model parameters or architectural modification. Empirical results demonstrate that SharedRequest achieves over $20\%$ higher utility compared to prior differential privacy baselines, and its shared-prompt mechanism reduces query cost by up to $5\times$ compared to non-batched inference.

---

### GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation

Authors: Yuxiao Ye, Yiwen Zhang, Huiyuan Xie, Yuqin Huang, Zhiyuan Liu
Published: 2026-06-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.05002v1

LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also on the policies by which agents interact and adapt. Multi-agent reinforcement learning can optimise these interaction policies, but its reward design often remains task-specific and weakly grounded in interaction structure. To address this gap, we propose GARL, a GAme-theoretic Reinforcement Learning framework for multi-agent strategic prioritisation. GARL formalises strategic prioritisation as a two-stage game: competing agents first allocate strategic resources over a shared candidate set, and a higher-level arbiter then produces the final ranking. The resulting game-theoretic utilities are converted into role-specific reinforcement signals, allowing policy optimisation to be guided by structured interaction. We instantiate GARL on issues-in-dispute ranking, where the goal is to prioritise core issues in legal proceedings. Experiments show that GARL improves ranking performance, enables small open-source LLMs to become competitive with a strong closed-source LLM under the same candidate-ranking setting, and yields gains in legal-domain competence and broader strategic decision-making. Overall, GARL demonstrates how game-theoretic interaction structure can be turned into reinforcement-learning objectives, providing a principled approach to policy optimisation in multi-agent strategic prioritisation.

---

### New Benchmarking Shows Limited Generalization Power of TCR Antigenic Epitope Prediction Models

Authors: Yiming Liao, Yiheng Li, Ning Jiang, Bo Li, Keke Chen
Published: 2026-06-03
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2606.04994v1

Accurate computational prediction of T cell receptor (TCR) antigen specificity would transform the study of T cell biology and enable scalable immune engineering, yet existing models lack sufficient sensitivity and specificity for broad applications. A major limitation is the absence of rigorously defined, unseen benchmark datasets that allow unbiased evaluation of model performance and generalizability. Here, we describe two complementary classes of datasets that meet this criterion and argue that they provide both a robust framework for model assessment and a foundation for next-generation TCR-antigen prediction algorithm development.

---

### Multi-Camera AR Guidance System for Surgical Instrument Handling and Assembly: Investigating Workload and Efficiency

Authors: Shiyu Li, Julian Kreimeier, Hannah Schieber, Dirk Müller, Bernhard Kainz, Rüdiger von Eisenhart-Rothe, Daniel Roth
Published: 2026-06-03
Categories: cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2606.04992v1

The handling and assembly of instruments during surgery imposes high cognitive demands on scrub nurses, particularly when instruments are unfamiliar. We present a supporting guidance system for surgical instrumentation that combines multi-camera 6D pose estimation with augmented reality in-situ visualization on a head-mounted display without the requirement for additional markers. Pose estimation and consecutive camera calibration are achieved through known objects. The 6D pose estimation network is trained purely on synthetic data, aiming for better generalizability and real-world applicability. The AR guidance displays tooltip localization cues and step-wise assembly animations. Via gaze-based selection and a foot pedal, users can switch between assembly steps in intraoperative use. In a technical evaluation, our approach outperforms state-of-art 6D pose estimation. A user study with 29 scrub nurses was conducted in a surgical simulation of knee arthroplasty, comparing the system against a paper manual. AR guidance significantly reduced the perceived workload compared. Objectively, AR guidance reduced task completion time by 21.3\% (4.76 minutes). Specifically, scrub nurses less experienced with the instrument set benefited when using the system. Error frequencies were comparable between conditions. Qualitative feedback highlighted improved process clarity, reduced information overload, and perceived independence. To summarize, our marker-free multi-camera AR guidance approach for surgical instruments can, subjectively and objectively, improve intraoperative instrumentation performance, particularly for untrained scrub nurses.

---

### From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents

Authors: Yiqi Wang, Jiaqi Zhang, Zhangkai Wu, Taotao Cai, Zirui Liu, Zequn Sun, Manqing Dong, Mingkai Zheng, Yiqun Duan, Xuefei Yin, Yanming Zhu
Published: 2026-06-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.04990v5

Large language model (LLM)-based agents are evolving from passive text generators into autonomous systems capable of planning, tool use, retrieval, memory access, environmental interaction, and multi-agent collaboration. These capabilities expand agent autonomy, but also make agent behavior harder to verify, debug, and audit. Final-answer accuracy alone cannot explain how an output was produced, which evidence supported each claim, whether tool calls were justified, how memory influenced later decisions, or where failures originated. This survey examines evidence tracing and execution provenance as foundations for process-level accountability in trustworthy LLM agents. We define execution provenance as the typed graph of an agent execution and evidence tracing as its projection onto evidence-support relations. This perspective connects retrieval grounding, claim support, tool-use safety, memory lineage, observability, debugging, audit, and recovery within a unified framework. We introduce a taxonomy covering trace sources, evidence and execution units, provenance relations, tracing granularity and timing, representation forms, and trust functions. We then review key methodological directions, including provenance representation, evidence attribution, tool-use provenance, runtime guardrails, provenance-bearing memory, observability, and failure diagnosis. Finally, we discuss benchmarks, datasets, metrics, and open challenges for building provenance-aware, auditable, and recoverable agent systems.

---

### From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents

Authors: Yiqi Wang, Jiaqi Zhang, Taotao Cai, Zirui Liu, Qingqiang Sun, Zequn Sun, Zhangkai Wu, Manqing Dong, Mingkai Zheng, Xuefei Yin, Yanming Zhu
Published: 2026-06-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.04990v4

Large language model (LLM)-based agents are evolving from passive text generators into autonomous systems capable of planning, tool use, retrieval, memory access, environmental interaction, and multi-agent collaboration. These capabilities expand agent autonomy, but also make agent behavior harder to verify, debug, and audit. Final-answer accuracy alone cannot explain how an output was produced, which evidence supported each claim, whether tool calls were justified, how memory influenced later decisions, or where failures originated. This survey examines evidence tracing and execution provenance as foundations for process-level accountability in trustworthy LLM agents. We define execution provenance as the typed graph of an agent execution and evidence tracing as its projection onto evidence-support relations. This perspective connects retrieval grounding, claim support, tool-use safety, memory lineage, observability, debugging, audit, and recovery within a unified framework. We introduce a taxonomy covering trace sources, evidence and execution units, provenance relations, tracing granularity and timing, representation forms, and trust functions. We then review key methodological directions, including provenance representation, evidence attribution, tool-use provenance, runtime guardrails, provenance-bearing memory, observability, and failure diagnosis. Finally, we discuss benchmarks, datasets, metrics, and open challenges for building provenance-aware, auditable, and recoverable agent systems.

---

### DeliChess: A Multi-party Dialogue Dataset for Deliberation in Chess Puzzle Solving

Authors: Xiaochen Zhu, Georgi Karadzhov, Tom Stafford, Andreas Vlachos
Published: 2026-06-03
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2606.04987v2

Multi-party dialogue is a critical setting for studying collaborative reasoning and decision-making, yet existing datasets rarely focus on structured, reasoning-intensive tasks. We introduce DeliChess, a dataset of group deliberation dialogues in which participants collaboratively solve multiple-choice chess puzzles. Participants first answer independently, then engage in multi-party deliberation and revise their individual answers. The dataset comprises 107 dialogues with full transcripts, pre- and post-deliberation choices, and utterance-level annotations of communicative function, epistemic stance, and usefulness for supporting deliberation. Our analyses show that greater diversity in initial solution quality is associated with larger gains, while answer trajectories reveal how deliberation can recover, discover, or lose strong answers. Cases in which groups surpass every independent answer are associated with sustained reasoning and epistemic openness. We further propose a diagnostic action-selection task and find that the tested LLMs show only weak agreement with human-attested helpful actions. Together, our dataset provides a testbed for modelling group reasoning, dialogue dynamics, and conditions for effective deliberation.

---

### Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning

Authors: Yu Zhu, Yongkang Li, Wenjie Zhu, Haoyi Jiang, Wenyu Liu, Wei Yang, Bin Li, Xinggang Wang
Published: 2026-06-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.04986v1

Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reasoning and generalization capabilities. Moreover, high-quality large-scale nutritional annotations remain scarce. To address these issues, we introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations. To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning. We also propose Food-R1, a unified food VLM trained in a multi-task learning paradigm to equip the model with broad capabilities. Food-R1 undergoes CoT-based cold-start instruction tuning, followed by reinforcement fine-tuning (RFT) using Group Relative Policy Optimization (GRPO) to improve reasoning and performance. Experiments on CalorieBench-80K and representative benchmarks show that Food-R1 consistently outperforms strong baselines across food-related tasks. The code, model weights, and benchmark annotations are available at the project repository.

---

### AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization

Authors: Wanqi Yang, Yuexiao Ma, Alexander Conzelmann, Xiawu Zheng, Michael W. Mahoney, T. Konstantin Rusch, Shiwei Liu
Published: 2026-06-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.04980v1

Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory. Mixed-precision quantization can substantially reduce this footprint by assigning different bit-widths to different experts. Existing approaches, however, typically rely on calibration data to estimate expert importance and determine bit allocation. For frontier MoE LLMs, the original training data, and hence the true training distribution, is proprietary and inaccessible. As a result, calibration sets are inevitably imperfect surrogates, and this can misestimate expert utilization and lead to suboptimal bit allocation. Motivated by the substantial cross-expert quality variability observed in modern MoE models, and by the success of Heavy-Tailed Self-Regularization (HT-SR) theory at predicting neural network model quality without access to training or testing data, we propose AlphaQ, a calibration-free bit-allocation method for MoE quantization. AlphaQ draws on HT-SR theory and follows a simple principle: experts with more heavy-tailed weight spectra are typically better trained and hence should receive higher bit-widths, while experts with weaker heavy-tailed structure can be quantized more aggressively. AlphaQ operationalizes this principle by measuring expert-wise spectral heavy-tailedness and solving a budget-constrained optimization problem that minimizes total quantization error under a global bit-budget constraint. Across several MoE models, AlphaQ consistently outperforms calibration-based baselines under matched bit budgets. Notably, on Qwen1.5-MoE, AlphaQ achieves near full-precision accuracy with an average expert precision of only 3.5 bits, while delivering more than 4$\times$ memory compression. Our code is available at https://github.com/Superone77/AlphaQ.

---

### Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game

Authors: Chensong Huang, Changyu Chen, Chenwei Lin, Hanjia Lyu, Xian Xu, Jiebo Luo
Published: 2026-06-03
Categories: cs.CL, cs.CY, econ.GN
arXiv: https://arxiv.org/abs/2606.04978v1

LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making mechanisms. We investigate this distinction using the St. Petersburg game as a controlled testbed, a classical paradox in which the expected payoff is infinite, yet humans typically report low, finite willingness to pay. We evaluate 28 LLMs with a structured prompt suite that includes the original game; controlled decision variants that perturb truncation, repeated play, numeric endowment, and occupational identity; a human-perspective prompt that asks models to reason as human decision makers; and paired comparisons between base models and their instruction-tuned counterparts. In the original game, most models generate finite bids, creating the appearance of human-like risk behavior. However, this outcome-level resemblance masks substantial mechanism-level differences. The controlled variants reveal that rather than maintaining human-like behavior seen in the original game, models often shift to conditionally and computationally rational behavior. Human-cue prompting and instruction tuning often lower bids and reduce some visible pathologies, but most mechanism-level response patterns remain largely unchanged. These findings show that behavioral alignment in risk decision-making can be surface-level: LLMs may produce human-like risk decisions without exhibiting human-consistent mechanisms. High-stakes evaluations of LLM decision-making should therefore move beyond outcome similarity and examine whether the alignment is supported by mechanism-level consistency.

---

### SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding

Authors: Na Li, Chengda Wang, Mingju Gao, Hao Tang
Published: 2026-06-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.04974v1

Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quality generation. We propose SAID, a Scaffold-Aware Iterative Decoding framework that accelerates DLLMs by reallocating computation across tokens. SAID first spends denoising computation on scaffold tokens to establish the coarse semantic structure, and then completes predictable detail tokens with fewer steps. We further adapt SAID to block-wise diffusion decoding and introduce Confidence-Hierarchical Layered Generation (CHLG), which assigns additional steps only to low-confidence tokens. Experiments on LLaDA-8B and LLaDA 1.5 across math, coding, and knowledge benchmarks show that SAID significantly accelerates DLLM inference with a maximum speedup of 9.1x while maintaining competitive performance. Our code is publicly available: https://github.com/TH-AI-Lab-PKU/SAID.

---

### Be Fair! Can Machine Learning Engineering Agents Adhere to Fairness Constraints?

Authors: Anna Richter, Julia Stoyanovich, Sebastian Schelter
Published: 2026-06-03
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2606.04971v1

Machine learning engineering (MLE) agents promise to automate end-to-end ML pipeline development from raw data and natural language instructions, potentially making ML accessible to non-technical domain experts. However, in sensitive and regulated domains, this abstraction creates a responsibility gap: end-users may lack visibility into design choices that affect correctness, robustness, fairness, and regulatory compliance. We argue that existing benchmarks are insufficient to assess whether MLE agents can be safely applied in such settings. We propose desiderata for a responsibility-centered evaluation framework and conduct an exploratory study on melanoma classification, focusing on fairness across skin tones as a responsibility constraint. When evaluating two recent MLE agents, we find that agent-generated pipelines show high variance and consistently underperform manually designed baselines in both predictive quality and fairness, despite fairness-oriented prompts. These preliminary results suggest that further research is needed towards redesigning MLE agents to allow humans to guide the search process and reliably assess the compliance and quality of the generated ML pipelines.

---

### Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance

Authors: Kaustav Kundu, Ritvik Shrivastava, Maxim Arap, Nanshu Wang, Xianhui Zhu, Quintin Fettes, Gautam Tiwari, Parth Suresh, Théo Moutakanni, Alejandro Castillejo Munoz, Allen Bolourchi, Pascale Fung et al.
Published: 2026-06-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.04970v1

We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{how} to coach. However, progress is limited by the absence of large-scale, cross-domain benchmarks that reflect realistic conditions, particularly the common case in which users deviate from the expected step sequence. We address this gap with four contributions: \textbf{(1)}~we release \textbf{EgoProactive}, a large-scale wearable-egocentric dataset for proactive procedural assistance with explicit Out-of-Plan (OOP) annotations and recovery steps; \textbf{(2)}~we augment five established benchmarks (Ego4D, EPIC-KITCHENS, EgoExo4D, HoloAssist, HowTo100M) into \textbf{Pro\textsuperscript{2}Bench} under a unified proactive-guidance schema; \textbf{(3)}~we propose a \textbf{decoupled planner--interaction architecture} specialized for procedural state, visual cues, and recovery injection; \textbf{(4)}~we introduce a post-training recipe that transfers across model families, validated by cross-backbone replication on Llama~4 and Qwen-3.6-VL. In extensive experiments, our trained Llama-4 system substantially improves objective intervention quality over strong proprietary baselines (Claude Opus~4.6, Gemini~3.1~Pro, GPT~5.2) and open-weight baselines (Qwen3~VL~235B) baselines across all six datasets. Oracle-plan experiments further show that, when plan quality is controlled, the trained duplex model produces high-quality guidance and large gains on Out-of-Plan recovery.

---

### From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents

Authors: Sanderson Oliveira de Macedo
Published: 2026-06-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2606.04967v1

AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles, artifacts and verification. Recent surveys map agents and LLMs for software engineering, but a study centered on the operational frameworks that turn these capabilities into process is missing. We ran a directed search of primary sources, with a functional inclusion criterion and traction measurement, and selected six frameworks: GitHub Spec Kit, OpenSpec, BMAD Method, Get Shit Done (GSD), Spec Kitty and Reversa. Each attacks AI development through a different path: spec-driven development in full and lightweight variants, agent-driven agile planning, context engineering over the agent, worktree isolation and review, and recovery of operational specifications from legacy systems. Our central contribution is a six-dimension process taxonomy: specification, context, roles, execution, validation and portability, with a scoring rubric that turns it into a replicable instrument. We apply it to the six frameworks and an out-of-sample case, Spec-Flow. Two results stand out. Among frameworks that already adopt some process there is convergence: the isolated prompt loses centrality, and persistent artifacts, work contracts, traceability and human review become mechanisms that reduce ambiguity and coordinate agents. And no framework strongly covers all six dimensions, exposing a structural trade-off between process depth and portability across agents. We also found recurring risks: drift between specification and code, excessive trust in generated artifacts, fragility of community extensions, platform dependence and a lack of benchmarks for the complete process. We close with a research agenda for empirical evaluation, focused on intermediate-quality metrics, context governance, installation security and reproducibility.

---

### SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs

Authors: Xinrui Song, Zhuoran Wang, Mingju Gao, Hao Tang
Published: 2026-06-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.04964v1

Diffusion language models (DLMs) generate text through iterative denoising, and blockwise decoding improves their practicality by committing tokens in local blocks. However, existing blockwise methods typically rely on fixed block sizes or delimiter-based runtime signals, which do not necessarily align with semantic boundaries. In this paper, we propose SemBlock, a semantic-boundary-driven dynamic block decoding framework for diffusion LLMs. SemBlock formulates dynamic block construction as semantic boundary prediction and trains lightweight predictors on frozen LLaDA hidden states. To provide supervision, we construct SemBound, a semantic-boundary dataset that derives boundary labels from discourse units, reasoning steps, and implementation spans across natural language, math, and code tasks. During inference, SemBlock uses predicted boundary probabilities to select the ending position of each dynamic block. Experiments on GSM8K, IFEval, MATH, and HumanEval show that SemBlock consistently improves over fixed-block decoding and AdaBlock. Our code is publicly available: https://github.com/TH-AI-Lab-PKU/SemBlock.

---

### NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting

Authors: Samuel Ndichu, Tao Ban, Seiichi Ozawa, Takeshi Takahashi, Daisuke Inoue
Published: 2026-06-03
Categories: cs.CR, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2606.04957v1

System-generated logs underpin security monitoring, yet their rigid template-based format hinders both automated analysis and human comprehension. We present NLLog (Natural-Language Log), a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences, pools them with term-frequency-inverse-document-frequency weighting, classifies sessions with tree ensembles, and back-projects evidence with TreeSHAP for analyst review. On Hadoop Distributed File System (HDFS) and Blue Gene/L (BGL) corpora, NLLog exceeds two reproduced matched-protocol baselines; across HDFS, BGL, and the AIT Alert Data Set, it sustains low false-positive rates with commodity-hardware latency suitable for security operations center triage. Coverage, sparse-versus-dense, faithfulness, and adversarial ablations show that fallback sufficiency is corpus-dependent, that an enrollment-time coverage check can surface refinement requirements before deployment, and that an auditable deterministic rewrite combined with lightweight dense encoding provides a measurable representation layer for log-anomaly detection and triage.

---

### Clinical Assistant for Remote Engagement Link (CARE-link): A Web-Based Electronic Health Records Software for Managing Diabetes

Authors: Prince Ebenezer Adjei, Joshua Teye Tettey, Toufiq Musah, Audrey Agbeve, John Amuasi
Published: 2026-06-03
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2606.04952v1

CARE-link is an open-source, web-based clinical support platform designed to improve the management of gestational diabetes by linking clinicians and patients through an LLM-mediated workflow. The system aggregates patient-generated data outside the hospital, summarizes relevant clinical information, and delivers context-aware decision support to clinicians. For patients, CARE-link provides clear explanations of management plans and delivers timely lifestyle guidance through a WhatsApp interface. The integrated dual-facing design aims to promote continuous monitoring, support individualized care, and reduce the burden of in-clinic follow-ups. Built with a modular architecture, the platform can be adapted to other chronic conditions requiring longitudinal tracking and behavioral support. CARE-link has the potential to enhance clinical oversight, promote patient compliance, and strengthen continuity of care particularly in resource-constrained settings.

---

### A General Framework for Dynamic Consistent Submodular Maximization

Authors: Paul Dütting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Ola Svensson, Morteza Zadimoghaddam
Published: 2026-06-03
Categories: cs.DS, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2606.04946v1

Consistency is an important property in dynamic submodular maximization and entails maintaining a near-optimal solution at all times, making only a small number of adjustments to the solution in each step. Prior work has explored this question for the insertion-only case, where the algorithm faces a stream of $n$ insertions, and has established lower and upper bounds for the cardinality-constrained version of the problem. We consider this question in the fully dynamic setting, where the stream of operations may contain both insertions and deletions. We develop a general framework for designing algorithms for this setting, and instantiate it to obtain the first constant-factor approximations with sublinear consistency. For cardinality constraints, we propose a $\frac 12 - O(\varepsilon)$ approximation that is $O\left(\frac{1}{\varepsilon^2}\right)$ consistent. For rank-$k$ matroid constraints, we construct a $\frac 14 - O(\varepsilon)$ approximation to the dynamic optimum that is $O\left(\frac{\log k}{\varepsilon^2}\right)$ consistent.

---

### STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models

Authors: Xin Yan, Aqiang Wang, Zhenglin Wan, Xingrui Yu, Ivor Tsang
Published: 2026-06-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.04945v2

Diffusion large language models (DLLMs) have recently emerged as a promising alternative to autoregressive LLMs by generating text through iterative masked denoising with bidirectional context. However, their large model sizes and iterative denoising process introduce substantial memory and computational overhead, motivating post-training quantization for efficient deployment. In this paper, we identify two key challenges for low-bit DLLM quantization: state-dependent activation disparity and temporal error accumulation. Masked and unmasked tokens exhibit different activation distributions within each denoising step, while quantization errors can accumulate across steps during iterative decoding. To address these challenges, we propose STaR-Quant, a state-time consistent PTQ framework for DLLMs. STaR-Quant introduces State-Guided Activation Transformation (SGAT) to assign masked and unmasked tokens to different activation transformation spaces with a unified static weight-side transformation. It further introduces Temporal Attention Compensation (TAC) to correct the quantized attention representation via a lightweight block-diagonal affine mapping. Experiments on representative DLLMs demonstrate that STaR-Quant consistently improves low-bit weight-activation quantization over strong PTQ baselines, while delivering up to 1.69x speedup and 3.14x memory saving over FP16 deployment.

---

### What Type of Inference is Active Inference?

Authors: Wouter W. L. Nuijten, Mykola Lukashchuk, Thijs van de Laar, Bert de Vries
Published: 2026-06-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.04935v4

Active inference casts decision-making as inference, with the Expected Free Energy (EFE) unifying goal-directed and information-seeking behavior. Recent work showed that EFE minimization can be written as Variational Free Energy (VFE) minimization on a generative model augmented with epistemic priors. We prove that the VFE of the augmented model can be rewritten as the VFE of the predictive model plus explicit entropy-correction terms, making the EFE contribution transparent. We then show that proper EFE-based planning requires combining these epistemic corrections with a planning correction that turns marginal inference into policy optimization, yielding a full variational characterization of EFE-based planning. This clarifies which corrections are needed for cross-entropy planning and for full EFE-based planning. The same entropy-corrected formulation leads to a detailed message-passing scheme for EFE-based planning together with simpler ablations. Experiments on three grid-world environments show that full EFE-based planning outperforms ablations that omit either the planning correction or the epistemic corrections.

---

### Mean-based algorithms: A lower bound and regret

Authors: Julius Durmann, Amelie Kleber
Published: 2026-06-03
Categories: cs.LG, cs.GT
arXiv: https://arxiv.org/abs/2606.04931v1

Mean-based algorithms are a class of online learning algorithms that assign low probability to actions with low average rewards. Recent work indicates these algorithms converge favorably to serially undominated actions, which approximate Nash equilibria in economic games. However, empirical studies also show slower convergence compared to established algorithms in bandit-feedback scenarios. We study mean-based algorithms when the time horizon is unknown and only bandit feedback is available. In this setting, we provide the first lower bound on the algorithm-defining sequence $γ_t$ that formally establishes a limit on how fast these algorithms can learn. Additionally, we propose two mean-based algorithms: one generalizes $ε$-greedy, and the other extends the mean-based Exp3 to unknown horizons. Our experiments show that mean-based algorithms, although slightly slower, can perform competitively with other bandit-feedback algorithms. We further analyze the relationship to no-regret algorithms. Depending on the choice of $γ_t$, the intersection with no-regret algorithms is non-trivial, and we show that algorithms exist that are both mean-based and no-regret. This adds context to the "exploitability" of this class of algorithms that previous contributions suggest.

---

### AdaKoop: Efficient Modeling of Nonlinear Dynamics from Nonstationary Data Streams with Koopman Operator Regression

Authors: Naoki Chihara, Ren Fujiwara, Yasuko Matsubara, Yasushi Sakurai
Published: 2026-06-03
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2606.04930v1

Real-time data analysis requires the ability to accurately and adaptively address nonlinear dynamics in a nonstationary data stream while preserving computational efficiency. However, nonlinear dynamics are so complex that capturing dynamically changing nonlinear patterns and utilizing them for downstream tasks under strict time constraints is nontrivial. To bridge the gap between nonlinear complexity and computational tractability, this study applies Koopman operator theory, which states that nonlinear dynamics can be represented as linear transitions in an infinite-dimensional space. Building upon finite-dimensional approximations of this operator, we present AdaKoop, an efficient streaming algorithm for modeling nonlinear dynamics over nonstationary data streams. Our approach utilizes a probabilistic framework grounded in Koopman operator theory, treating both raw observations and reproducing kernel Hilbert space (RKHS) features as emissions from latent vectors. This dual-view formulation allows nonlinear dynamics to be expressed as a tractable linear system. Therefore, AdaKoop enables the efficient and stable modeling of nonlinear dynamics in a streaming fashion, avoiding the prohibitive computational costs of iterative nonlinear optimization. Furthermore, to address nonstationarity in data streams, AdaKoop adaptively detects the switching of patterns via statistical hypothesis testing for abrupt pattern shifts and incrementally updates model parameters to handle continuous changes. Extensive experiments on a total of 71 practical benchmark datasets across various domains demonstrate that AdaKoop outperforms state-of-the-art methods in terms of real-time forecasting accuracy and computational efficiency.

---