Artificial Intelligence
When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees
Fabian Denoodt and Sibylle Hess
Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from this finite sample. We propose the use of confidence sequences to dynamically determine how many samples are needed while maintaining statistical guarantees. We consider several ways in which predictive probabilities are used, including identifying the most likely class, approximating the full predictive distribution, and resolving probability-threshold decisions. Sampling stops once the corresponding decision can be made with the desired guarantee. Experiments show that the method allocates the computational budget efficiently, assigning more samples to ambiguous inputs than to easy inputs while preserving reliable decisions and reducing overall latency relative to a fixed Monte Carlo budget.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Ming Chen, Rong-Xi Tan, Ke Xue et al. (+8 more)
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large
language model (LLM)
agents offer a new way to approach BBO by combining task semantics, computation, optimization tools, and feedback-driven decision making, showing great potential due to the integration with mathematically rigorous tools. However, existing agentic BBO studies use different task domains and system configurations, making their results difficult to compare and the effects of individual design choices hard to isolate. We therefore introduce AgenticBBO-Bench, a cross-domain
benchmark for agentic BBO spanning synthetic functions, hyperparameter optimization, database tuning, chip design, and molecular design under a unified finite-budget evaluation protocol. In our experiments, agentic BBO achieves higher family-averaged scores than direct LLM-based methods in all five domains and outperforms the best numerical optimizers in four. We further study three factors shaping
agent performance: optimization tools, task information and prior knowledge, and the role of the LLM during search. Our results show that additional numerical tools do not consistently improve performance, task semantics are broadly useful while more specific priors are less reliable, and numerical optimizers can effectively absorb gains from search trajectories established by the
agent. Finally, we introduce a five-task frontier challenge within AgenticBBO-Bench and evaluate seven LLMs under the Codex
agent harness, where GPT-6 Astra and DeepSeek-V4.1-Flash lie on the Pareto frontier of performance and cost among the evaluated models. Our code is available at https://github.com/lamda-bbo/agentic-bbo.
Read the full abstract ▾
All authors Ming Chen, Rong-Xi Tan, Ke Xue, Yu-Jie Zhou, Taiye Lu, Zhi-Xuan Gao, Peng Xie, Zijun Shen, Chen Lu, Haopu Shang, Chao Qian
Artificial Intelligence · Cross-listed from cs.CV
AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware
Thomas Goudemant, Aurélien Bobey, Omar Hlimi et al. (+1 more)
Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime surveillance the vessels cover a tiny fraction of each scene. We study onboard vessel detection as a way to select what is downlinked, which reduces the data according to its content rather than coding every pixel; it is complementary to conventional onboard compression. The work follows three axes. (i) Data and
algorithm: a controlled
dataset is generated from 68 annotated Maxar scenes with 43 vessel classes, and a YOLOX-S detector is trained on it. (ii) Embedded deployment: the detector is quantized and deployed on the DPU of a Versal VC1902, with a limited loss of detection quality and a processing time of a few seconds per scene. (iii) Data reduction: we propose several downlink modes, from metadata only (box, class and score of each detection) to image crops around vessels, tiles holding detections, or the whole scene with a degraded background, and estimate from the measured detection errors the trade-off each offers between the vessels kept and the volume downlinked. On our dense harbor and coastal scenes, tiles keep 98% of the vessels with 29% of the scene volume, and crops 83% with 3%.
Read the full abstract ▾
All authors Thomas Goudemant, Aurélien Bobey, Omar Hlimi, Marjorie Bellizzi
Artificial Intelligence
Recursive Self-Improvement through Multi-Agent Self-Supervision
Hyunin Lee, Jinglue Xu, Jeffrey Seely et al. (+4 more)
Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human experts can reliably assess, leaving the model itself (optimizee) as the best available optimizer and evaluator. However, a single model instance struggles to critique and improve its own complex
reasoning under this homogeneous loop. To address this, we propose Multi-
Agent Self-Supervision (MASS), an RSI method that alternates between evolutionary workflow optimization and supervised fine-tuning on self-generated trajectories. Guided by early findings that multi-
agent topologies excel at complex
reasoning, MASS
prompts a single base model to iteratively propose, execute, and self-evaluate multi-
agent workflows. Through an evolutionary search constrained by structural guardrails, the model optimizes these computational-graph-like orchestrations, discovering the most effective distinct roles and information routing for a given task. Over two MASS cycles with Qwen3.6-27B, the model achieves 1.2-1.6x higher performance per output
tokens on four open-ended public
benchmarks. Because the improved model subsequently acts as a better optimizer and evaluator, this alternating framework enables a continuous, recursive bootstrapping of the model's capabilities. Moreover, multi-
agent traces are also more training-efficient: a student trained on them outperforms a single-
agent student trained on 1.4x more training
tokens. These findings suggest that jointly learning orchestration and bounded subagent execution from multi-
agent trajectories can provide an effective signal for RSI.
Read the full abstract ▾
All authors Hyunin Lee, Jinglue Xu, Jeffrey Seely, Donghyun Lee, Somayeh Sojoudi, Matei Zaharia, Yujin Tang
Artificial Intelligence · Cross-listed from cs.RO
Unifying Policy Learning and State Prediction through Spatial Language Modeling
Minye Wu, Zehao Wang and Tinne Tuytelaars
Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial
Language Modeling, which represents scene contours, goals, action targets, and future states with a shared vocabulary of discrete coordinates and semantic
tokens. A task-specific grammar organizes these elements into spatial sequences, allowing one autoregressive
Transformer to learn action generation and action-conditioned state prediction through a common next-
token objective. We train the model from scratch using random-play transition pretraining followed by joint action and state training on expert demonstrations. During pretraining, recorded action coordinates condition subsequent state predictions and are excluded from the prediction loss. During control, the model decodes only executable action targets and updates its history with newly observed states. We evaluate the approach on Push-T in simulation and on a real
robot. The model achieves competitive simulation performance and higher task success and target coverage than the evaluated real-
robot policy baselines. Training ablations show improved control with joint action and state sequences, with further gains from random-play pretraining. Given supplied action trajectories, the same model also predicts successive scene states, capturing the
geometric effects of pushing.
Read the full abstract ▾
Artificial Intelligence
Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models
Lars Simon, Holger Eble and Manuel Radons
We introduce a self-improvement loop for
reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abilities, an additionally supplied solution might enable the model to extract useful solution ideas in hindsight. We operationalize this by jointly training the same model to exhibit the following three capabilities: predicting solution ideas from problems alone, reverse-engineering ideas from problems and known solutions, and solving problems using provided ideas. The loop alternates between reverse engineering such ideas from problems with supplied solutions and using these ideas as additional supervision for joint training of all three capabilities. We give a formal specification of our method and a concrete instantiation for interactive
theorem proving in the Lean
theorem prover; empirical evaluation remains future work.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Scalable Hierarchical Graph Generation via Soft Community Structure
Ahmet Tüzen, Helge Langseth and Kjetil Nørvåg
Generating large attributed graphs requires reproducing the
topology, generating attributes jointly with the structure, and remaining scalable. Many real-world graphs exist as a single large graph, so a generative model has to generalize from the one graph it is fit on, without independent samples. We present Schema, which recursively decomposes a reference graph into a hierarchy of soft communities, assigning each node a membership distribution. Generation is then split into three stages, each trained independently: (1) synthesizing node attributes conditioned on soft memberships, (2) generating intra-community edges from local structural context, and (3) modeling inter-community connections over bridge nodes whose membership mass is distributed across several communities. No stage forms the full adjacency
matrix, and each stage operates on a subgraph bounded by the community size. We also introduce an evaluation protocol that covers structural fidelity, memorization, downstream utility, and scalability. On four real-world attributed graphs, Schema recovers the balance between local and long-range structure more closely than any other model that generates attributes, while reproducing only a small fraction of the reference edges. It retains the downstream accuracy of the reference graph without raising it artificially above that level. Baselines that match its structural fidelity memorize the reference, while those with higher downstream accuracy either exceed the reference accuracy or fail to complete on the larger graphs. We measure scalability on six additional graphs with up to 10 million nodes.
Read the full abstract ▾
Artificial Intelligence
Instruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization
Lei Zhai, Zhihao Chang, Shuyuan Yang et al. (+1 more)
Electromagnetic spectrum monitoring increasingly requires flexible analysis beyond task-specific recognition and detection.
Multimodal large
language models offer a unified interface, but extending
vision-
language models (VLMs) to raw I/Q signals requires tokenization that balances fidelity against a strict budget. For signals, dense encoding causes
token costs to grow with observation length, whereas fixed-resolution compression may discard short-duration or localized signal evidence. Thus, we propose BATok, a budget-adaptive signal tokenizer that adjusts
token capacity to the input length while allocating that capacity according to the signal content. BATok constructs candidate representations from signal-derived features using lightweight multi-resolution branches, then combines a local energy prior with learnable queries to resample these representations into compact signal
tokens. The number of
tokens adapts to the input length while remaining strictly bounded. The resulting
tokens are projected into the
language embedding space of VLMs. We further introduce EMSpec-Instruct, a
multimodal instruction
dataset aligning raw I/Q signals, waterfall images, and
language supervision for modulation recognition, structured detection, and
language-conditioned signal grounding. Experiments show that BATok learns effective signal representations and achieves competitive performance across all tasks.
Read the full abstract ▾
All authors Lei Zhai, Zhihao Chang, Shuyuan Yang, Zhixi Feng
Artificial Intelligence
Q-Shaped Options for Hierarchical Reinforcement Learning
Clarisse Wibault, Antoine Gorceix, Antonio Léon Villares et al. (+5 more)
Learning to tackle long-horizon, goal-conditioned tasks requires an
agent to reason over extended timescales and act across a broad range of states. In principle, Hierarchical Reinforcement Learning (HRL) addresses both challenges through the interaction between action (temporal) and state (spatial) abstraction. First, using an action abstraction to represent temporally extended behaviour as options reduces the effective decision horizon. Second, enabling different state abstractions at each level of the decision process permits greater data aggregation for learning. However, realising these two benefits of a hierarchical policy depends on learning an appropriate action abstraction. Current HRL
algorithms fail in one of two ways. Some discard distinctions between options needed for optimal control, undermining hierarchy altogether. Others retain unnecessary distinctions, preserving horizon reduction, but forfeiting coarser state abstraction. In this work, we characterise three desiderata for an action abstraction. We introduce Q-Shaped Options (QSO) to address all three. QSO builds on an architecture with distinct state-value functions, Q functions and policies at each level of the hierarchy. It learns the action abstraction between consecutive levels as a shared encoder shaped by their respective Q functions. The low-level Q function uses the option as a goal, encouraging the abstraction to retain distinctions necessary for optimal control. The high-level Q function uses it as an action, encouraging unnecessary distinctions to be discarded. Across offline goal-conditioned locomotion and manipulation environments, QSO learns semantically meaningful option spaces and outperforms baselines, achieving non-zero performance in tasks where all other evaluated
algorithms fail.
Read the full abstract ▾
All authors Clarisse Wibault, Antoine Gorceix, Antonio Léon Villares, Alexey Zakharov, Evangelos Chatzaroulas, Michael Matthews, Eduardo Pignatelli, Jakob Foerster
Artificial Intelligence
OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression
Sixu Chen, Mingrui Yang, Qiang Guan et al. (+1 more)
Knee osteoarthritis (KOA) progression prediction can support patient monitoring, requiring the integration of
multimodal data and multidomain expertise. Moreover, isolated risk estimates provide limited insight underlying a prediction. To automate the progression assessment workflow and reduce manual effort while providing interpretable findings and supporting evidence, we present OA-MAP, an autonomous multi-
agent framework for evidence-grounded assessment of structural and pain progression in KOA. The system incorporates modality-specific
agents including MRI, X-ray, and clinical
agents, together with a coordinator
agent. This framework can autonomously recruit specialist
agents, select tools for prediction and analysis, and retrieve literature as external evidence based on user request and available patient information. An uncertainty-informed human-in-the-loop mechanism enables clinicians to review and correct intermediate findings, triggering recomputation of affected results. We evaluate the prediction models using 600 participants from the FNIH Osteoarthritis Biomarkers Consortium cohort. On the test set of 100 participants, the fusion models achieve AUROCs of 0.80 for structural progression and 0.68 for pain progression. A case study illustrates how OA-MAP combines risk estimates with intermediate findings, cross-modal conflicts, literature support, and uncertainty indicators to support interactive review.
Read the full abstract ▾
All authors Sixu Chen, Mingrui Yang, Qiang Guan, Xiaojuan Li
Artificial Intelligence
An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling
Robert Graham, Yariv Barsheshat, Phil Blandfort et al. (+1 more)
A large body of research measures model coherence based on output variance without adequately considering competing causes. We identify two such causes, ambiguity and indifference, and we introduce a set of 175 questions where contradicting answers cannot easily be explained by either. We then measure incoherence in terms of contradictions when resampling answers to the same question. In contrast to other methods our metric has high specificity, and only ranks models as incoherent when the issues are glaring. Even so, we find narrow finetunes score poorly. Inspecting inconsistencies flagged by our method, we find that model organisms from the literature display severe issues such as identity conflation, introspection failures and rationalizations. These findings suggest that the pathologies induced by narrow finetuning may limit what these models can tell us about coherent misaligned behaviour.
Read the full abstract ▾
All authors Robert Graham, Yariv Barsheshat, Phil Blandfort, Sabri Alouache
Artificial Intelligence · Cross-listed from cs.CV
LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views
Qizhou Huo, Xuan Sun, Yongfei Guo et al. (+2 more)
Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content. Conventional 3D Gaussian Splatting nevertheless renders each target view, leaving this image overlap unexploited. Reusing rendered images offers an alternative.
Geometric warping alone cannot recover newly exposed content and remains sensitive to depth errors. We propose a per-scene framework that replaces repeated scene rendering for nearby views with relative-pose-guided RGB-D image reuse.
Geometric warping uses depth and relative pose to transport source content, while a lightweight multiscale network predicts RGB residuals to correct artifacts and infer missing appearance. Cached source features further reduce repeated computation. On GS-render, residual refinement improves PSNR by 0.72~dB over pure warping; evaluations on captured and rendered scenes demonstrate low query latency. This separation of scene rendering from local view updates supports responsive scene exploration, with potential applications in augmented and virtual reality.
Read the full abstract ▾
All authors Qizhou Huo, Xuan Sun, Yongfei Guo, Zhipeng Wang, Yuanhao Gong
Artificial Intelligence
Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents
Xiangyi Zeng, Baihang Liu, Xutong Wang et al. (+3 more)
The
evolution of Large
Language Model
agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical
memory and continual learning architecture. Hippocam draws inspiration from two characteristics of human
memory: cognitive processes selectively maintain information relevant to current goals, while long-term
memories form gradually through repeated consolidation. Accordingly, Hippocam structures an
agent's ongoing work as nested intents. The active context remains centered on the current intent, while completed intents are consolidated into the task-relevant outcomes and state needed for subsequent work, rather than carrying forward their full working details. Concurrently, a recursive prefix consolidation mechanism repeatedly consolidates earlier history, causing long-unused experiences to become increasingly abstract. Original interactions are preserved, allowing the
agent to progressively recover finer-grained details through the hierarchy and stop once sufficient information is available. Crucially, when past experiences are recalled and reintegrated into active work, they undergo subsequent consolidation alongside new experiences, thereby being reinforced, supplemented, and updated. Through this
memory dynamic of use and disuse, Hippocam connects working context, long-term
memory, knowledge accumulation, and skill learning within a single continuously evolving experiential process. This enables
agents to learn and evolve capabilities through their own experiences without parameter updates.
Read the full abstract ▾
All authors Xiangyi Zeng, Baihang Liu, Xutong Wang, Ze Jin, Yunpeng Li, Qixu Liu
Artificial Intelligence · Cross-listed from cs.LG
Using Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation
Alessio Pellegrino and Jacopo Mauro
Algorithm Selection is essential for efficient Constraint Programming. Over the years, many
algorithm selectors based on machine learning methods have been successfully applied, yet traditional feature extraction methods often rely on manually decided instance-level statistics that fail to capture the underlying problem structure. In this paper we aim to bridge this gap by introducing a novel, automated feature extraction methodology that integrates graph conversion and Weisfeiler-Lehman graph kernels to generate robust structural representations of problem instances. The 1-WL test bounds the graph-distinguishing power of standard message-passing Graph Neural Networks (GNNs), and suitable GNN architectures match this bound \citep{Xuetal2018}. WL-based features offer an alternative that does not require training a GNN. Our primary contribution is a cut-based representation (WLc) designed to model structural partitions and provide a more nuanced predictive signal. We evaluate our approach on instances from the 2023–2025 MiniZinc Challenges across two tasks: maximizing Borda count scores and maximizing predictive accuracy. Experimental results across Support Vector Machines, Random Forests, and Multi-Layer Perceptrons demonstrate that cut-based features outperform fzn2feat with SVMs, while results with RFs and MLPs are closer.
Read the full abstract ▾
Artificial Intelligence
Universal Textual Teaching for LLMs
Zhanyi Lu and Huan Wang
Knowledge
distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific architecture and checkpoint. This implicit representation is difficult to interpret or reuse across models and limits KD for API-only or costly-to-train models. This paper studies knowledge transfer for large
language models (LLMs). We introduce Universal Textual Teaching (UTT), a parameter-update-free framework that distills observed Teacher-Student knowledge gaps into a textual, interpretable, and reusable natural-
language artifact called Primer. Specifically, UTT first identifies representative gap cases through paired evaluations, and iteratively updates the Primer via multi-role interactions: the Student attempts each task, the Prompter turns evaluation feedback into a teaching instruction, the Teacher provides a targeted demonstration, and the Synthesizer consolidates validated lessons. Empirically, on the challenging math (Omni-MATH-2) and code generation (KernelBench) tasks, extensive results confirm the effectiveness of the method: UTT remarkably raises the Student's accuracy from 9.4% to 48.6% and Fast1 accuracy from 9% to 35% on KernelBench, while increasing mathematical
reasoning accuracy from 27.6% to 51.7%. UTT also performs better than representative
prompt engineering and parameter-based KD methods. Of note, UTT is shown to be generalizable across different Teachers and Students: a Primer synthesized for one Teacher-Student pair can generalize to other Students that do not participate in the synthesis.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
Panagiotis Roditis, Panagiotis P. Filntisis and Petros Maragos
Off-policy actor–critic methods control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, regardless of how the critics disagree. We propose GeZo-SAC, which uses auxiliary
geometric representations to adapt critic pessimism to the state and action. Alongside its scalar value, each critic predicts a set of generators defining a zonotope. Probing this zonotope along sampled directions provides a
geometric width, "subtracted from each critic value as a pessimistic offset, and a measure of disagreement between the two critics, aggregated with log-sum-exp. This disagreement controls how the critics are combined, moving from a width-weighted average toward the usual minimum as disagreement increases. At inference, the deployed policy is an unmodified SAC actor, since the generators are used only on the critic side during training.Across four MuJoCo-v5 locomotion
benchmarks and six off-policy baselines, GeZo-SAC achieves the highest mean return on Ant-v5 and Hopper-v5 and remains competitive with other methods on the remaining tasks. Our analysis further shows that GeZo-SAC achieves the lowest average actuator work and action effort per metre among the evaluated methods, while maintaining near-zero measured overestimation frequency across all four environments.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
Leigang Qu, Feng Cheng, Ziyan Yang et al. (+7 more)
Building a capable
video editor remains significantly harder than a
video generator: editing requires (source, instruction, edited) triplets that are prohibitively expensive to annotate and difficult to synthesize at scale, whereas image editing has already reached maturity with millions of such pairs readily available. In this work, we introduce VINCIE-NExT, a unified framework that transfers editing capability from images to
videos through in-context visual demonstrations, alleviating the need for large-scale paired
video editing data. VINCIE-NExT decomposes
video editing into a structured chain of composable sub-tasks (
Video -> Image -> Image ->
Video), routing editing intent through the image domain and enabling scalable joint training from heterogeneous image and
video corpora under a unified
diffusion objective. An image editing pair, synthesized by the model or supplied by the user, is prepended as an in-context visual demonstration that serves as a spatial appearance blueprint for every output frame. To ground appearance edits across the interleaved context, we introduce a novel position encoding that links image demonstrations and
video frames in a shared spatial coordinate system, enabling pixel-faithful propagation of appearance changes to every output frame. Chain-of-Editing further provides principled test-time scaling: by executing the sub-task chain as progressive
diffusion stages, editing quality can be improved by investing additional compute without retraining. Comprehensive experiments on OpenVE-Bench demonstrate the state-of-the-art performance across diverse editing categories, with ablations confirming the effectiveness of each component.
Read the full abstract ▾
All authors Leigang Qu, Feng Cheng, Ziyan Yang, Bangbang Yang, Zhaoyang Huang, Wei Chow, Yicong Li, Wenjie Wang, Tat-Seng Chua, Yan Zeng
Artificial Intelligence
Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models
Hongyu Shi, Sen Zhao, Zuyu Zhang et al. (+5 more)
Latent
reasoning enables
vision-
language-action (VLA) models to transform
multimodal observations into task-relevant internal states before generating continuous
robot actions. While existing methods learn to generate or refine such states for each policy query, they discard successful
reasoning after execution and therefore reconstruct similar computation from scratch. We present
Reasoning and Flow
Memory (FLOWMEM), a unified VLA model that turns successful latent computation into reusable
reasoning experience. Rather than appending a fixed retrieved context, FLOWMEM dynamically retrieves and recomposes compatible latent fragments as the embodied context evolves, forming a
reasoning route that follows the temporal structure and progress of successful computation. The route is then refined using current visual and proprioceptive evidence before it conditions action generation. Experiments on RoboMME and LIBERO-Plus show that FLOWMEM attains 48.0% and 77.3% success, outperforming
memory-free policies by 1.7 and 4.1 percentage points, respectively. These results demonstrate the value of reusing successful latent computation for closed-loop VLA control.
Read the full abstract ▾
All authors Hongyu Shi, Sen Zhao, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Qinghua Zhang
Artificial Intelligence
EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution
Yanning Dai, Yuhui Wang, Nanbo Li et al. (+2 more)
LLM-based program
evolution relies on evaluation feedback to guide the iterative search for high-performing programs. However, evaluation is often computationally expensive, making it essential to allocate limited resources to candidates that can most effectively advance the search. Existing LLM-based methods typically rely on fixed allocation strategies throughout the search, potentially wasting resources on low-value candidates while overlooking promising ones. We propose EvoAlloc, a self-evolving resource-allocation
agent that learns from search experience to revise its strategy for allocating computational resources across candidates. EvoAlloc periodically consolidates prior search and allocation outcomes into reusable experience, which informs subsequent strategy revisions. It further uses a counterfactual exploration mechanism to occasionally evaluate candidates denied resources by the allocator, revealing their outcomes to enrich its experience for future strategy updates. Across coding and
agent-harness optimization
benchmarks, EvoAlloc requires 59-82% fewer full evaluations and 61-89% fewer total LLM
tokens to reach baseline-level performance. Moreover, under the same full-evaluation budget, EvoAlloc achieves 8.7-12.0% higher final performance.
Read the full abstract ▾
All authors Yanning Dai, Yuhui Wang, Nanbo Li, Wenyi Wang, Jürgen Schmidhuber
Artificial Intelligence
Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes
Ali Satvaty, Narjes Sharafi, Jirui Qi et al. (+2 more)
Large
language models (LLMs) can expose memorized training sequences under prefix-based extraction: given a prefix from a training example, the model may assign high probability to the original continuation. In deployed systems, however, prefixes are rarely evaluated in isolation. They often appear together with instructions, retrieved documents, or other task-specific context, as in
retrieval-augmented generation (RAG). This motivates examining whether contextual conditioning mitigates memorization or merely changes the set of memorized samples that become extractable. We investigate this issue through paired item-level measurements of probabilistic suffix extraction. For each prefix-suffix pair, we score the target suffix under an empty
prompt and under retrieved contexts of varying relevance, across three open-weight instruction-tuned models. We find that context does not simply erase memorization. Instead, extractable memorization consists of a context-robust core and a context-sensitive boundary. Many samples that are extractable without context remain extractable under the retrieved context, especially as the prefix length increases. At the same time, context mainly affects marginal samples near the extraction threshold: it suppresses some exposures, but also enables new ones that are missed by prefix-only evaluation. These findings qualify the view that RAG reduces memorization risk. Context can lower aggregate extraction by suppressing boundary cases, yet robustly extractable samples persist, and context-enabled extractability remains security-relevant.
Read the full abstract ▾
All authors Ali Satvaty, Narjes Sharafi, Jirui Qi, Suzan Verberne, Fatih Turkmen
Artificial Intelligence · Cross-listed from cs.CL
All Verdicts are Not Equal: Rethinking LLM Judge Reliability
Vineet Kumar, Darshita Rathore and Anindya Moitra
LLM-as-a-Judge is the standard paradigm for NLP evaluation, yet its systemic reliability remains poorly understood despite being widely treated as a deterministic ground truth. We present a comprehensive reliability audit, stresstesting six frontier models across four
benchmarks, five
prompt formats, two presentation orders, three sampling temperatures, and ten repetitions per condition. Our empirical analysis reveals severe vulnerabilities: verdicts change across identical replications at temperature zero, position-order swaps flip the majority of verdicts on challenging tasks, and the most deterministic judge achieves perfect consistency by trivially repeating incorrect verdicts, agreeing with ground truth only 51% of the time. To formalize these multi-faceted failure modes, we introduce the trustworthy verdict rate (T ), a unified metric capturing the joint probability that an evaluation is reproducible, order-invariant, and accurate. UsingT , we derive a theoretical upper bound on accuracy imposed by position bias and show that reliability is item-specific rather than modellevel. Finally, we demonstrate that shifting from pairwise win-rate to holistic rubric scoring improves trustworthiness more than any single-format prompting intervention, offering an actionable framework for robust NLP evaluation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.chem-ph
MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
Chenghao Jia, Mengdi Liu, Hong Chang et al. (+2 more)
Elucidating molecular structures from spectra is a foundational problem in chemical and materials characterization, yet remains challenging due to spectral ambiguity and the vast molecular space. Although recent
diffusion-based generators show strong promise for spectra-conditioned elucidation, existing methods struggle to learn robust spectra-structure relationships from limited paired data when relying solely on global spectral representation. Moreover, the repeated full sampling inference strategy incurs substantial computation overhead. To address these limitations, we propose MAST, a Motif-Augmented
diffusion framework with Search Tree, for joint 2D-3D spectroscopic molecular structure elucidation. MAST introduces explicit, interpretable motif priors as intermediate evidences throughout denoising, reducing conditional ambiguity and facilitating spectra-conditioned optimization. We further cast
diffusion sampling as reward-guided tree search to prioritize high-reward denoising trajectories, yielding a compact set of spectra-consistent candidates under limited budgets. On the QM9S multi-spectra
benchmark, MAST achieves 94.89% exact recovery and improves 3D fidelity, while preserving high chemical validity and stability. Code is available at https://github.com/Jia040223/MAST.
Read the full abstract ▾
All authors Chenghao Jia, Mengdi Liu, Hong Chang, Shiguang Shan, Xilin Chen
Artificial Intelligence
When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation
Yiruo Cheng, Shen Huang, Xiaoshuai Song et al. (+5 more)
Large
language model (LLM)-based
agents have demonstrated strong capabilities on complex tasks. They typically perform
reasoning before each action throughout an interaction trajectory. However,
reasoning may not be necessary at every turn, as
reasoning produced earlier can continue to support subsequent actions. A key challenge is therefore to determine when existing
reasoning remains sufficient and when a new
reasoning step is needed, without relying on costly generation-based verification. We find that decreases in the likelihood of subsequent reference actions after removing additional
reasoning closely track whether those actions remain recoverable given earlier
reasoning, providing an effective and lightweight signal for estimating cross-turn action support. Based on this observation, we propose
Reasoning Adaptation through Cross-Turn Estimation (RACE), a training approach for adaptive
agent reasoning. RACE introduces a Likelihood-Guided Progressive
Reasoning Cover Detection (LoGiC) procedure that progressively identifies
reasoning turns whose removal has limited impact on the current and subsequent reference actions. The resulting removal signals are incorporated into both supervised fine-tuning and agentic reinforcement learning, enabling the policy to learn when to reason and when to act directly. Extensive experiments on four representative
agent benchmarks show that RACE substantially reduces
reasoning cost while maintaining or improving task performance.
Read the full abstract ▾
All authors Yiruo Cheng, Shen Huang, Xiaoshuai Song, Jiejun Tan, Guanting Dong, Pengjun Xie, Ji-Rong Wen, Zhicheng Dou
Artificial Intelligence
Structure Tax: How Structured Output affects LLMs Performance
Vineet Kumar, Kanishka and Bhuvanesh Mandora
Deploying large
language models in production often requires constraining outputs to structured formats such as JSON or XML, and prior work treats the resulting accuracy loss as an inherent `structure tax'. We re-examine this claim by evaluating a battery of models,
datasets and schemas, measuring task accuracy, confidence calibration, and hidden-state geometry. The tax turns out to depend on schema design rather than on structure per se:
reasoning-first field ordering matches or exceeds free-form accuracy, while answer-first ordering causes steep drops, particularly in smaller models. Format sensitivity scales inversely with a task's own structural constraints, and schemas that preserve
reasoning order also improve calibration with CKA showing greater separability between correct and incorrect representations in middle
transformer layers. Our findings indicate that properly designed structured formats can match or exceed free-form performance, reframing the critical question from `whether to structure' to `how to structure' for optimal
reasoning preservation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
MPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation
Mahtab Sarvmaili
Graph neural networks (GNNs) predict molecular properties from chemical graph data, but predictive accuracy does not explain how graph information supports an individual decision. A compact prediction-preserving rationale does not necessarily reveal which changes reverse the decision or which modifications the model tolerates. We propose the Multi-Perspective Graph Explainer (MPGE), unifying factual support, counterfactual sensitivity, and exemplar tolerance for a frozen classifier. The factual view, originally termed prototype (PT), seeks a compact retained edge set with the same label and required confidence. Counterfactual (CF) explanations seek bounded prediction-changing deletions; exemplar (EXE) explanations seek non-trivial bounded deletions that preserve the label and confidence. A shared constrained formulation connects prediction behavior, compactness, and edit cost, while separate objectives generate the three views. Our graph-classification extension of CF-GNNExplainer learns symmetric edge rankings and verifies discrete candidates, recording unsuccessful searches. A separate BBBP fragment backend returns RDKit-sanitized molecules. We evaluate the primary GCN implementation on MUTAG, Mutagenicity, AIDS, COX2_MD, and BBBP using semantic coverage, conditional quality, stability, and runtime. Successful factual masks retained 8.6%–15.5% of input edges on average across
datasets; bounded counterfactual coverage was 4.8%–67.6%, and exemplar preservation coverage was 98.9%–100.0%. Exploratory controls reveal the influence of hard projection and retained node information. Quantitative comparisons and molecular visualizations characterize model support, sensitivity, and tolerance without treating them as validated chemical mechanisms.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Traceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems
Zoe Li
Robotic systems operating over extended tasks must maintain a world state assembled from observations arriving at different times, with varying confidence and potential revisions. Conventional representations emphasize latest estimates, hindering fact provenance, decision reproduction, or execution auditing. We present Traceable World State (TWS), a middleware-neutral semantic representation and reference runtime for provenance-aware
robot world state. A TWS snapshot captures entities, relations, observations, confidence, and revision metadata. Validated update operations transform snapshots immutably, ordered updates support deterministic replay, and a canonical SHA-256 hash chain ensures tamper-evident logs. We evaluate TWS through schema conformance, complete state lifecycles, deterministic replay, and fault injection. Passing 38 tests across Python 3.10-3.14, the framework detects record corruptions, broken hash links, sequence discontinuities, and world mismatches. Across ten public BEHAVIOR-1K task definitions, TWS imported 153 entities and 146 relations with successful validation. On 103 NVIDIA Unitree G1 simulated trajectories containing 78,369 frames, TWS achieved exact terminal-state replay in all episodes and detected 412/412 injected corruptions with a 1.72% storage overhead over Plain JSONL.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
HWAM: Humanoid World Action Model With Joint State–Action Generation
Yan Yang, Jikun Rong, Minzhao Zhu et al. (+7 more)
Humanoid
robots are a promising platform for general-purpose manipulation. Recent
Vision-
Language-Action (VLA) policies learn actions directly from
multimodal observations, while World Action Models (WAMs) further incorporate future visual prediction to improve action generation. However, in hierarchical humanoid systems, VLA and WAM policies output reference actions that are subsequently realized through whole-body control,
robot dynamics, balance, and contact. This hierarchy creates an action–execution gap: the reference produced by the policy can differ from the motion realized by the
robot. Without explicitly modeling the realized body state, future visual prediction must jointly explain scene
evolution and discrepancies between reference actions and executed motion, making it difficult to associate an action with its physical outcome. We propose HWAM, a Humanoid World Action Model with joint state–action generation, which makes the
robot's post-execution proprioceptive state an explicit prediction target. By jointly generating reference actions and their realized body states, HWAM directly incorporates supervision of executed motion into action learning. HWAM is trained through three complementary conditional paths. The Policy path jointly denoises state–action trajectories conditioned only on current observations, matching deployment conditions. Forward Dynamics Modeling (FDM) predicts future visual observations conditioned on actions and post-execution states, while Inverse Dynamics Modeling (IDM) reconstructs the joint trajectory from visual transitions. Together, these paths connect policy references, realized body motion, and visual outcomes. HWAM achieves the highest success rate among evaluated baselines on three real-
robot tasks on the LimX OLI humanoid. On Candy Picking, HWAM achieves a 70.6% success rate, compared with 43.3% for Fast-WAM.
Read the full abstract ▾
All authors Yan Yang, Jikun Rong, Minzhao Zhu, Zheyi Zhao, Qirui Hu, Zihan Lan, Weixin Mao, Yinhao Li, Zhen Fu, Hua Chen
Artificial Intelligence
InterviewPlayground: A Validated Simulation Environment for Evaluating AI Interviewers
Jonathan Ivey, Aimee Liang, Arthur Y.S. Wang et al. (+3 more)
Increasingly, AI interviewers are being developed to elicit open-ended responses in applications like
market research, public polling, preference elicitation, and social science research. However, evaluating AI interviewers is challenging because they function in extended, multi-turn interactions where they must adapt to participant behaviors. To address this need, we develop InterviewPlayground, a simulation environment for evaluating AI interviewers using simulated study participants whose behaviors are grounded in social theory. Simulated studies in InterviewPlayground produce an InterviewReportCard, which assesses the performance of AI interviewers using a suite of validated measures. To test whether our simulation-based evaluations predict performance with human participants, we conduct 15 real qualitative studies with five AI interviewers, three interview topics, and 450 human participants and compare them to simulated studies in InterviewPlayground. We find that AI interviewer performance in InterviewPlayground predicts performance in human studies with an average Pearson correlation of 0.86 across 12 measures, and the simulated interactions from InterviewPlayground reproduce key findings from behavioral analysis of AI interviewers in the human studies. Together, these findings support the validity of InterviewPlayground in assessing AI interviewer performance and examining potential failure modes. Our work contributes a simulation environment for AI interviewers supported with empirical validation, and more broadly, a roadmap for future work to develop validated, simulation-based evaluations of conversational AI systems.
Read the full abstract ▾
All authors Jonathan Ivey, Aimee Liang, Arthur Y.S. Wang, Madeline Mandell, Ziang Xiao, Anjalie Field
Artificial Intelligence · Cross-listed from cs.CL
Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology
Zhaoxin Yu, Qingchao Kong, Dajun Zeng et al. (+1 more)
Large
language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the
reasoning process attributing external events to the causes and reasons of
agents' social behaviors, plays a critical role. These processes involve judgments of social cause, responsibility, and blame/credit to
agents. Although attributional models are well-studied in social psychology and cognition through Attribution Theory, social attribution remains underexplored in AI, particularly LLM social
reasoning. This paper provides the first systematic exploration of LLM social attribution. Our work focuses on responsibility and blame attributions, examining current LLMs' judgments and their underlying internal mechanisms. Guided by attribution theory, we construct a social attribution
benchmark consisting of a Vignette subset based on classic scenarios from attribution theory research and a Reality subset based on real-world social narratives, yielding 7,639 responsibility/blame judgment questions. On this basis, we evaluate 32 representative LLMs and 5 basic non-LLM baselines. To further explore the internal mechanisms underlying the LLM judgment process, we develop a probing-based methodology to investigate the latent-space representations of 5 key attribution dimensions and the consistency of their influences on LLM judgments compared to those in human social attribution. Our research findings reveal that current LLMs exhibit measurable but incomplete agreement with human responsibility and blame judgments, and meanwhile, this agreement is positively correlated with model size. Some attribution dimensions are systematically decodable from specific positions in LLM hidden states, and their influences on the final judgment are consistent with those indicated by human Attribution Theory. The
dataset and associated code are available at https://github.com/Yuzhaoxin946/SAB-Bench.
Read the full abstract ▾
All authors Zhaoxin Yu, Qingchao Kong, Dajun Zeng, Wenji Mao
Artificial Intelligence
PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary
Chenyang Xu, Donglin Xie, Xi Xiang et al. (+12 more)
Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal
attention, as normalization, nonlocal transforms, or companion views may depend on withheld samples. We introduce PulseBound, a PPG representation learner combining physiologically structured future-beat prediction with an explicit stored-window information boundary. A content-independent cutoff separates the visible prefix from the prediction target. Prefix-only normalization, suffix replacement before derived-view construction, and aligned masking ensure that encoder inputs depend only on the visible prefix and cutoff. This yields stored-suffix invariance: with fixed model state, randomness, prefix, and cutoff, changing the stored suffix cannot change the forecast context. A shared horizon-conditioned head predicts nine rhythm and morphology descriptors for up to four extractor-valid future beats, using elementwise validity masks; optional ECG-derived pulse-arrival-time supervision is restricted to training. On MIMIC and VitalDB groups held out from PulseBound backbone pretraining, PulseBound reduces nine-state transformed-space MAE relative to last-visible-beat persistence by 28.06% and 22.22%, respectively, with gains in MAE, MAE-Skill, and Spearman correlation across all 40 source-cutoff-horizon
cells. In a separate comparison of seven models on 13 downstream tasks, PulseBound achieves the best mean on nine frozen linear-probe and seven full-fine-tuning tasks. Stored-suffix interventions cause zero recorded changes in forecast contexts or predictions, with zero suffix-input gradients at audited precision under the stored-window interface. These findings separate three testable aspects of predictive physiological representation learning: information access, supervised future structure, and transfer.
Read the full abstract ▾
All authors Chenyang Xu, Donglin Xie, Xi Xiang, Xiaoyu Li, Yufan Lu, Jiqiun Gao, Yi Zhao, Xin-Yi Li, Guangpu Zhu, Zijian Wang, Xiwen Yang, Dezhen Wang, Lin Chen, Shenda Hong, Yelei Li