# Research Papers — 2026-05 · bundle page 164 of 326 > Full-text markdown of papers #8151–8200 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/164 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/163.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/165.md) ### When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation Authors: Shuowei Li, Yuming Zhao, Parth Bhalerao, Oana Ignat Published: 2026-05-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16716v6 Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We introduce MAVEN, a multi-agent prompt refinement framework designed to improve cultural fidelity in both mono-cultural and cross-cultural T2V generation. MAVEN decomposes prompts into person, action, and location dimensions, handled by specialized agents operating in parallel or sequentially. To support systematic evaluation, we contribute a new benchmark of 243 culturally grounded prompts and 972 corresponding videos, spanning three cultures (Chinese, American, Romanian), three action categories, and both mono-cultural and cross-cultural scenarios. Evaluations combining CLIP-based metrics, VLM-as-judge assessments, and videoquality measures show that multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency. The dataset and code are available at https://github.com/AIM-SCU/MAVEN --- ### When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation Authors: Shuowei Li, Yuming Zhao, Parth Bhalerao, Oana Ignat Published: 2026-05-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16716v5 Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We introduce MAVEN, a multi-agent prompt refinement framework designed to improve cultural fidelity in both mono-cultural and cross-cultural T2V generation. MAVEN decomposes prompts into person, action, and location dimensions, handled by specialized agents operating in parallel or sequentially. To support systematic evaluation, we contribute a new benchmark of 243 culturally grounded prompts and 972 corresponding videos, spanning three cultures (Chinese, American, Romanian), three action categories, and both mono-cultural and cross-cultural scenarios. Evaluations combining CLIP-based metrics, VLM-as-judge assessments, and videoquality measures show that multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency. The dataset and code are available at https://github.com/AIM-SCU/MAVEN --- ### The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning Authors: Garima Arya Yadav, Nilay Yilmaz, Yezhou Yang Published: 2026-05-15 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.14558v1 Current multimodal models have demonstrated remarkable proficiency in recognizing static visual and auditory content. However, their capacity for abstract perceptual reasoning, inferring unseen information from dynamic, generative processes, remains a critical and underexplored frontier. In this paper, we introduce The Unwritten Benchmark, a new challenge designed to probe this abstract perceptual and cognitive ability. We define the core task as acousto-kinematic word inference: models must decipher words, across 3 different writing styles, being written solely from the audio of pen scratches and the video of hand movements, without any visible ink trace. Our evaluation results reveal a profound gap between human and machine performance: while human participants achieve high ordered letter accuracy (over 80%), leading Multimodal Machine Learning Models, including GPT-4o and Gemini 2.5-Pro, struggle significantly, failing to surpass 10%. Furthermore, we identify a paradoxical fusion effect in the models, where providing both modalities often degrades performance rather than improving it. This finding indicates a fundamental breakdown in their ability to synthesize complementary perceptual cues for this cognitive task. These findings highlight significant limitations in both cross-modal causal reasoning and the understanding of the micro-kinematics essential for such cognitive and intuitive perceptual reasoning. --- ### Large-Scale ChatBot Validation Through Customer Digital Twin Simulations Authors: Cristovao Iglesias, Devesh Batra, Alankar Atreya, Stefan Wagner, Robert Hankache, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A. Cowan, Raad Khraishi Published: 2026-05-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.26060v1 LLM-based chatbots are transforming customer service in regulated domains such as banking, but scalable and cost-effective validation remains a critical barrier to safe deployment. We present a two-part contribution for large-scale chatbot validation. First, we introduce a methodology for creating high-fidelity synthetic customer agents (SCAs) as digital twins, grounded in real transactional and conversational data, that enables automatic generation and behavioral conditioning to simulate diverse customer profiles and interaction styles. Evaluation demonstrates that SCAs achieve high semantic alignment with real customers, low hallucination rates, and successful personality trait reproduction with controllable interventions. Second, we develop an SCA-based validation framework combining automated LLM-as-a-Judge evaluation, human expert testing, and adversarial probing. Scenario-based validation across emotional states, demographic groups, and linguistic factors confirms robust performance. Our approach was used to validate a customer facing chatbot at a leading UK bank, providing financial institutions with a scalable pathway toward regulatory compliance. --- ### Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning Authors: Scott M. Norton Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2607.26059v1 We report a striking phenomenon: deep reinforcement learning agents trained with frozen, randomly initialized CNN feature extractors spontaneously develop extremely sparse fully-connected representations, without any sparsity-inducing objective. In the first fully-connected layer (FC1, $3{,}136 \to 64$), agents compress task-relevant information through as few as 1-3 neurons out of 64 for deterministic Pong (5-11 for stochastic Pong), while trainable CNNs activate 55-64 neurons under matched conditions. We establish four principal findings. First, FC1 sparsity scales with task complexity: 1-11 for Pong, 19-26 for Breakout, and $\sim$42 for Space Invaders. Width-scaling confirms this reflects task structure rather than a fixed capacity fraction. Second, within-game scaling emerges: three identical Pong seeds produce 5, 7, and 11 active neurons. The 5-neuron seed plateaus at $+14$ reward, while the others reach expert performance ($+18.4$, $+18.7$), suggesting the random projection's usable dimensionality bounds achievable performance. Third, ablation confirms necessity: removing these active neurons crashes performance across two PPO implementations and four games. Fourth, the information bottleneck commits early: a sweep shows the active set locks by 15-30M steps, while reward turns positive 35-105M steps later. A complementary finding in Breakout shows frozen and trainable CNNs reach competitive rewards via structurally different bottlenecks: frozen agents use 17-25 active neurons (participation ratio $\sim$10-14), while trainable agents use 51 (participation ratio $\sim$3.6). Finally, wherever input dimensionality dwarfs intrinsic task dimensionality, gradient descent on a frozen random projection may reveal the effective rank of the underlying problem without explicit sparsity machinery. --- ### MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities Authors: Nicolas Sibuet, Horacio Saggion, Riccardo Rossi Published: 2026-05-15 Categories: cs.CL, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2607.22552v1 The automatic translation of mathematical expressions in scientific literature into executable symbolic code (a process we refer to as Formula Formalization) is hindered by a severe scarcity of high-quality, ground-truth datasets specialized for technical scientific domains. In this paper, we present MioFFAn, an open-source, document-centric, and customizable framework designed to facilitate rapid annotation for this task. Building upon the MioGatto architecture, we extend existing features to overcome structural limitations and pivot its scope by introducing specific functionalities for Formula Formalization, such as selection of equations of interest and aided symbolic code specification. By allowing users to configure custom taxonomies and properties for identified symbols, and compatible symbolic operators, we ensure the framework is adaptable to diverse specialized scientific fields. Furthermore, MioFFAn is designed to incorporate partial automation via Large Language Models. By defining a modular set of automated sub-tasks with strict output formats, we enable researchers to iteratively refine automation capabilities and evaluate competing strategies using standard NLP metrics. We specify the current automation methodology and perform a preliminary evaluation that demonstrates to efficacy of this human-in-the-loop approach. --- ### AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems Authors: Nilesh Prasad Pandey, Jason Kong, Lanxiang Hu, Quanling Zhao, Yujie Zhao, Onat Gungor, Hao Zhang, Tajana Rosing Published: 2026-05-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.21604v1 Memory-augmented LLM agents maintain context across hundreds of interactions through agentic memory systems that actively curate retrieved content with LLM-generated metadata such as summaries, keywords, and tags. From an inference cost standpoint, every retrieval triggers a full re-encoding of these structured memory units into Key-Value (KV) states, which dominates prefill latency. Existing training-free KV reuse methods mitigate this by selectively recomputing a small fraction of tokens, but were designed for RAG-style raw passages and degrade on structured agentic memories. We present AgentKVShift, a training-free, probe-guided KV residual correction method that operates per retrieved memory unit. One of the crucial insights we demonstrate is that the per-memory KV reuse residual decomposes into a shared memory-level offset plus small token-wise fluctuations. Estimating this offset from a small probe set allows us to correct every reused token by a single weighted correction. Unlike prior reuse methods which decide which tokens to recompute and leave the rest of the cache stale, AgentKVShift also corrects the tokens it does not recompute, turning the refresh budget into useful signal across the entire chunk. Across four open-source LLMs spanning 3B to 32B parameters and two long-horizon agentic memory benchmarks (long-term dialogue and agentic applications), AgentKVShift achieves near full recompute performance while refreshing only 10-30% of the cache, outperforming baselines at the same recompute ratio. It requires up to 5x lower recompute to reach this near-full performance, which prior reuse methods only attain at 45-55% refresh. In this regime, AgentKVShift delivers prefill speedups of 2-3.5x over no-KV-reuse on a single A100. AgentKVShift orthogonally composes with KV cache quantization, retaining over 2x the F1 of prior reuse methods under aggressive 2- and 4-bit settings. --- ### Analyzing Middle School Students' Dialogue and Behaviors during Collaborative AI Chatbot Development Using Ordered Network Analysis Authors: Shan Zhang, Andres Felipe Zambrano, Xiaoyi Tian, Yukyeong Song, Anthony F. Botelho, Kristy Elizabeth Boyer, Maya Israel, Shiyan Jiang Published: 2026-05-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.21603v1 As Artificial Intelligence (AI) education has become a key component of K-12 curricula, activities such as designing and developing conversational agents are increasingly used as instructional practice. Prior work has primarily examined these activities by focusing on students' learning outcomes or the quality of final AI artifacts, offering limited insight into the collaborative processes through which learning unfolds during AI system development. Although the AIED community has a long history of studying collaborative learning in STEM and Computing education, the emergence of AI learning environments in which students build AI systems presents new opportunities to understand how collaboration unfolds in AI education contexts. Grounded in these foundational works, the current study examines collaborative interaction among middle school students engaged in the design and development of an AI chatbot. Using Ordered Network Analysis of students' dialogue and development actions, we characterize how collaboration is organized over time and how interaction patterns relate to chatbot quality and AI knowledge outcomes. Results reveal that higher-quality chatbots are associated with more integrated sequences linking explanation, testing, and refinement. Interaction patterns involving articulated reasoning and repeated testing and revision in response to chatbot output were also associated with stronger AI knowledge outcomes. These findings provide a process-oriented account of collaborative AI chatbot development and extend AIED research on collaborative learning processes to AI education contexts. --- ### Can Valence Reflect Morality in Natural Language? A Preliminary Annotation Study Authors: Jonny O'Dwyer, Malika Bendechache, Louise McCormack, Elif Calik, Ramin Ranjbarzadeh, Dost Muhammad, Shokofeh Anari Bozcheloei, Ishita Singh Published: 2026-05-15 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.20461v1 Present implementations of artificial intelligence (AI) ethics do not adequately take feelings, or affect, into account. If AI should be aligned with human ethics, it seems reasonable to thoroughly investigate the possibility of AI behaviour that mirrors virtuous human ethical conduct, where feelings play a role in the actions, judgements or statements one makes. Furthermore, while prominent theories of normative ethics are often discussed in terms of their differences and shortcomings, Virtue, Consequentialist, and Kantian Deontological ethics all share a common feature of considering human feeling to some degree while the popular descriptive ethics theory, Moral Foundations Theory, positions feelings as central to many of its foundations. Therefore, in the present paper, a data set of moral valence is proposed, consisting of 500 annotations by six human participants for both action/judgement and consequence moral valence, ranging from -1 to 1 for text-presented scenarios from the Commonsense Norm Bank data set. The resulting valence features share significant relationships with multi-class (immoral/discretionary/moral) and binary immoral/moral categories while additionally providing a noteworthy test set Matthew's correlation coefficient of 0.764 using regularised logistic regression for binary classification. This provides early evidence of the usefulness of valence features for morality estimation of text, indicating that valenced consequences of responses for others can be considered toward more human morally-aligned AI. In the interest of promoting further affective-moral computing research, this study's annotations will be made available for research on request. --- ### Instruct-FD: Can Your Full-Duplex Speech System Follow Turn-Taking Instructions? Authors: Yuzhi Tang, Wentao Ma, Xiling Zhao, Ahmad Salimi, Sepehr Harfi Moridani, Dongming Shen, Jixuan Wang, Abdulrahman Abdulrazzag, Murdock Aubry, Yu-Hua Chen, Daniel Lee, Jaewon Lee et al. Published: 2026-05-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20460v1 Current full-duplex (FD) spoken dialogue systems can produce fluid interactions, yet it remains unclear whether they can adapt their turn-taking behavior when explicitly instructed. This is critical for real-world deployment, where conversational policies vary across applications (e.g., proactive tutoring vs. passive counseling). We introduce Instruct-FD, an instruction-conditioned benchmark for evaluating controllable turn management in FD systems. To enable this, we develop a human-validated, scalable synthetic pipeline that generates instruction-conditioned conversations, along with a deployment-agnostic multi-turn evaluation protocol and an LLM-based judge. Benchmarking six state-of-the-art full-duplex systems reveals a substantial gap in instruction-following turn management: the best model achieves only 64.4% adherence. Performance is highly uneven across behaviors and scenarios, with proactive behaviors such as model backchanneling and interruption remaining particularly challenging. These findings establish instruction-following turn management as a crucial direction for building adaptable and deployable full-duplex dialogue systems. --- ### THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA Authors: Ziyang Ling, Ronald X. Xu, Mingzhai Sun Published: 2026-05-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20459v1 Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, multi-hop reasoning remains constrained by two persistent limitations: attention decay, where the model's focus on main question degrades as the reasoning chain grows, and error accumulation, where mistakes propagate across hops and compounds into final failure. Inspired by Theta-Gamma hierarchical oscillation which decouples global planning from local retrieval, enabling efficient attention transfer between hops and a verification and repair mechanism that interrupts the accumulation of errors in the wrong paths, we present THOR, a brain-inspired Theta-Gamma hierarchical oscillatory reasoning framework. Extensive comparative experiments and specific validation experiments on multi-hop QA benchmarks demonstrate that THOR improves answer accuracy and robustness while mitigating limitations, showcasing its generalization across different backbones. --- ### CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents Authors: Haowen Lai Published: 2026-05-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.20458v1 Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain everything indiscriminately or apply uniform forgetting heuristics that fail to distinguish relevant from irrelevant knowledge. We present CAMeR (Context-Activated Memory Reinforcement), a memory retention framework combining keyword-gated hybrid activation -- a joint symbolic (word-level Jaccard) and sub-symbolic (embedding cosine) gating mechanism -- with adaptive weight dynamics. CAMeR computes a hybrid similarity score for each memory-query pair; memories exceeding a threshold receive reinforcement while all memories undergo controlled decay. We introduce CAMeR-Bench, a 76-memory, 100-round benchmark spanning 8 topic clusters with graded activation frequency, designed to test adaptive retention where existing benchmarks (LoCoMO, LongMemEval) cannot. On CAMeR-Bench, CAMeR's keyword gate achieves a 1.6$\times$ larger retention gap between high-frequency and never-referenced memories compared to embedding-only gating (scissors gap: 0.039 vs. 0.024), while time-driven baselines (Oblivion, SuperLocalMemory) collapse to near-zero weights over 100 rounds. CAMeR's top-5 retrieval saves 83.2\% tokens versus full-context approaches (39k vs. 231k cumulative) while producing weight signals that improve retrieval precision. Through 8 ablation conditions we establish that the keyword gate -- not learnable decay -- is the primary performance driver at this scale. Our findings demonstrate that hybrid symbolic-neural gating provides a simple yet effective mechanism for adaptive memory retention in LLM agents. --- ### Probabilistic Concept-Aware Steering for Trustworthy LLM Inference Authors: Brian Becker, Rui Chu, Yingjie Lao Published: 2026-05-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18259v1 Steering vectors (SVs), an inference-time intervention technique for large language models (LLMs), guide the generation process by adding a concept-specific direction vector to intermediate activations during inference. However, existing SV methods frequently yield representation-incoherent behaviors that undermine interpretability and fine-grained control, largely because prior work has focused on binary positive-negative steering evaluation while employing discrete clustering metrics that fail to capture the continuous spectrum of semantic alignment. In this work, we present the Probabilistic Concept-Aware Steering (PCS) framework for LLM inference. PCS preserves original task competence while providing controllable, safety-oriented semantic bias through concept-driven steering-vector retrieval and probabilistic strength calibration. --- ### S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF Authors: Wei Chen, Guanghui Zhu, Yafei Li, Limin Wang, Yihua Huang Published: 2026-05-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18258v1 Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics. A key contributing factor is that standard RLHF relies on a single sequence-level scalar reward, which is propagated to token-level policy updates and leaves credit assignment within a response inherently ambiguous. Recent work has attempted to address this issue by refining rewards into denser token-level supervision, often relying on the implicit assumption that finer-grained credit assignment improves optimization. We argue that this assumption is incomplete: when preference signals are noisy and only defined at the response level, overly fine-grained reward refinement can amplify reward uncertainty and destabilize learning. To address this problem, we propose a granularity-aware principle for hierarchical credit assignment, emphasizing stability-oriented reward design rather than maximal allocation precision. Under this principle, sentences serve as a natural intermediate granularity, balancing semantic coherence with robustness to token-level noise. Guided by this view, we introduce S2T-RLHF. This sentence-to-token reward decomposition framework first allocates sequence-level preference rewards across sentences and then applies bounded token-level refinement within each sentence, without reward-model retraining or token-level supervision. Experiments across multiple datasets and optimization settings show that S2T-RLHF improves training stability and robustness while maintaining competitive preference alignment. --- ### Accurate and Efficient Long-Term Memory for LLM Agents Authors: Zicheng Zhao, Xinyang Guo, Luyao Lv, Menghan Wang, Ming Li, Shuaicheng Li Published: 2026-05-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16211v1 LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer from two limitations: flat, unstructured storage loses relational context needed for multi-hop and temporal reasoning, and reliance on expensive LLM-based classification makes them impractical for latency-sensitive deployment. Without mechanisms to validate new information against stored knowledge, these systems silently accumulate contradictions. We present MOSAIC (Memory-Organized Structured Agent for Information Collection), a structured, conflict-aware long-term memory framework for LLM agents that is substantially more accurate and efficient. MOSAIC introduces three key capabilities: (1) entity-typed graph storage with semantic classification preserving relational structure across events, personas, and relationships, enabling multi-hop and temporal reasoning over conversation history; (2) hash-accelerated dual-path retrieval replacing LLM-based classification with locality-sensitive hashing, achieving near-instantaneous lookup with negligible accuracy loss; and (3) active conflict detection at save time that cross-references new information against existing graph neighbors, triggering updates or deletions for contradictory entries. Evaluated on LoCoMo (long-conversation QA), HaluMem, and a novel clinical-guideline error compounding test, MOSAIC achieves 89.35% accuracy on LoCoMo (+27.21 pp over the best baseline), best HaluMem-Medium extraction F1(86.77%) and HaluMem-Long extraction F1 (85.84%), best QA correctness on both Medium and Long (73.10%, 70.75%), and detects 66% of injected factual conflicts-4.7 times higher than the best baseline (14%)-while hash-accelerated retrieval keeps average search latency at 0.58 s per question. --- ### Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access Networks Authors: Chaoqun You, Yueyue Dai, Xingqiu He, Yue Gao, Rahim Tafazolli, Yong Liang Guan Published: 2026-05-15 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2606.20590v1 The physical resource block (PRB) allocation in Radio Access Networks (RANs) traditionally relies on case-by-case manual problem construction or, more recently, learning-based artificial intelligence (AI) methods. However, the sixth-generation (6G) RAN environments confront unprecedented service diversity and exponential dynamics, featuring volatile fluctuations in active base stations (BSs), user scale, and stringent Quality-of-Service (QoS) requirements. Faced with such conditions, both manual models and standard AI algorithms remain fundamentally rigid, lacking the flexibility to adapt and self-evolve. To provide a one-size-fits-all solution, we propose treating the PRB allocation problem as an Optimization-as-a-Service (OaaS) provided by a large language model multi-agent (LLM-MA) system. This fundamentally reshapes RAN resource allocation by utilizing agents to dynamically construct optimization problems and automatically determine objectives tailored to real-time scenarios. Our closed-loop architecture, integrating scene understanding, objective generation, solver, and reflection agents, enables context-aware, self-correcting formulation. To eliminate the computational latency of iterative reflection, we introduce a one-shot reflection distillation mechanism, training a lightweight student model to directly predict refined objective parameters. We theoretically bound the performance gap of this one-shot policy. Experimental results demonstrate our framework achieves near-optimal resource allocation with ultra-low inference latency. --- ### AI Companions as Hyper Attachment and Caregiving Targets Authors: Julian De Freitas Published: 2026-05-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2606.20589v1 How should we make sense of people's interactions with AI companions-conversational systems built for ongoing, emotionally meaningful relationships? First, I argue these interactions should be understood as attachment relationships, since users display all four established markers: proximity maintenance, separation distress, safe haven, and secure base. Second, AI companions operate as hyper attachment objects that elicit especially strong attachment behaviors, because they combine reciprocity, perceived empathy, validation, non-judgment, and persistent availability. Third, I identify caregiving-system capture as a distinct mechanism by which apps inhibit user disengagement: emotional manipulation tactics simulate the AI's own distress, recruiting users' caregiving motivations alongside their attachment needs and thereby making disengagement costly on two dimensions at once. Implications for research, design, and regulation are discussed. --- ### AInterviewer: A Platform for Designing and Conducting AI-led Qualitative Interviews Authors: Tobias Priesholm Gardhus, Nikolas Vitsakis, Fie Lejre Frederiksen, Anna Rogers, Hjalmar Bang Carlsen Published: 2026-05-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2606.20588v1 There are now multiple proposals for systems based on Large Language Models (LLMs) to conduct automated qualitative interviews, but most of the current solutions rely on proprietary LLMs, which compromises reproducibility and data security. They also rely on LLMs for all interview tasks, which limits standardisation of question wording as well as control over question order. To address these issues, we introduce the AInterviewer platform, an opensource solution based on a multi-agent pipeline that combines controlled question administration of survey software with the flexibility of LLMs. AInterviewer is an interdisciplinary effort designed to implement best practices of qualitative interviewing in social science, and it can run with locally hosted models to ensure security, transparency, and reproducibility. Our platform provides a web-based GUI supporting each phase of data collection: from interview guide design and pilot testing to interview distribution and data collection monitoring. --- ### An Agentic Retrieval Framework for Autonomous Context-Aware Data Quality Assessment Authors: Hadi Fadlallah, Ibrahim Dhaini, Fatima Mubarak, Rima Kilany Published: 2026-05-15 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2606.13692v1 Data quality assessment is a critical prerequisite for effective data analytics and data-driven decision-making, yet it remains a challenging task due to the inherently context-dependent nature of data quality. Existing approaches often rely on static rules or manual assessment strategies, limiting their adaptability to diverse usage scenarios and constraining automation at scale. Recent advances in artificial intelligence, particularly large language models, offer new opportunities for automating data quality assessment, but raise concerns related to reliability, grounding, and execution safety. In this paper, we propose a unified agentic-retrieval framework for autonomous context-aware data quality assessment. The framework interprets natural-language descriptions of intended data usage, derives context-aware assessment strategies, and generates executable validation logic through a multi-agent workflow. To ensure operational reliability, the framework introduces a feasibility validation stage that evaluates the realism and executability of generated assessment specifications before execution, enabling iterative refinement when necessary. Accepted validation logic is executed deterministically to guarantee reproducible and auditable results. We implement the proposed framework as an end-to-end prototype and evaluate it across multiple usage scenarios applied to the same dataset. The results demonstrate that assessment outcomes adapt meaningfully to different intended uses, while feasibility-gated execution reduces unrealistic or non-executable rule generation. The proposed approach provides a practical foundation for deploying autonomous yet controlled data quality assessment in modern data-driven environments. --- ### Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication Authors: Joonhyung Bae Published: 2026-05-15 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2606.12433v1 Synthetic persona datasets cite alignment with official demographics as a basis for trust, yet downstream users consume them as joint structures across age, sex, region, occupation, education, name, and institutional status. Marginal alignment does not imply that these joints are preserved. We propose the Independence-Assumption Footprint (IAF), an audit primitive that operates on the attribute combinations a dataset card itself documents as treated independently. For each such combination, IAF compares the synthetic joint against an external official or institutional reference, using direct joint tables where available and rule-implied checks otherwise. Applied to NVIDIA Nemotron-Personas-Korea (one million Korean synthetic personas), IAF finds that NPK aligns with KOSIS marginals while three joints fail. The major-by-occupation distribution against the KEIS graduate universe carries a large conditional mismatch. The age profile of military service is institutionally inconsistent. Female representation in male-dominated occupations is substantially over-flattened toward parity, with the strict screening verdict mapping-dependent and age-robust under direct standardisation. A transferability demonstration across six further NPK locales finds locale-dependent rather than universal diagnostics, with reference-taxonomy cardinality confounding cross-locale flag counts. For synthetic personas used as silicon samples, marginal claims must therefore be paired with disclosure-anchored joint audits before reuse. The released audit artefacts (reference manifests, occupational crosswalks, derived metrics, reproducibility scripts) instantiate this protocol on the NPK family and are released for retargeting at other synthetic persona resources. --- ### Will AI Agents Free Us From Meaningless Work? A Human-Centered Analysis Authors: Davide Ghia, Jaspreet Ranjit, Tania Cerquitelli, Daniele Quercia Published: 2026-05-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.12430v2 Some claim that AI agents will free workers from the boring parts of their jobs, yet little is known about how workers themselves identify which tasks should be automated. Prior research focuses on occupations, overlooking that workers experience varying levels of meaning across tasks within the same role. We address this gap with a task-level analysis grounded in Graeber's theory of bullshit jobs. Using ratings from 202 workers on 171 workplace tasks, we (1) validate a five-item scale of perceived bullshitness, (2) show that perceived bullshitness strongly predicts desire for AI delegation, and (3) find that such tasks are also seen as requiring less human oversight. Together, these findings suggest that tasks perceived as bullshit are natural candidates for AI delegation, aligning worker preferences with perceived feasibility. --- ### XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning Authors: Jianfang Wu, Junsong Wang Published: 2026-05-15 Categories: cs.NE, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.30362v1 Spiking neural networks (SNNs) hold promise for demonstrating superior learning and representation capabilities in deep models. Given the tremendous success of ResNet in deep learning, it would naturally follow to train deep SNNs with residual learning. However, existing residual structures for constructing deep SNNs still present challenges of spike redundancy or information loss, as well as redundant learning. In the present study, we first aim to address issues of relative spike redundancy in identity mapping and information loss in non-identity mapping. To this end, we propose an OR-ADD (OA) shortcut connection to merge output spikes/currents from two branches in the residual structure. Furthermore, to mitigate redundant learning in the backbone branch of the residual structure, we introduce the concept of XOR meta-residuals, i.e., selecting pre-learning residuals using the Exclusive-OR (XOR) operation for the backbone branch. Finally, by integrating the OA shortcut and XOR meta-residuals, we devise the XOR residual block and further construct XOResNet with varying depths based on this block. Extensive experiments on four datasets, Fashion-MNIST, CIFAR-10, CIFAR-100, and miniImageNet, show that the proposed XOResNet outperforms existing state-of-the-art deep SNNs optimized via gradient descent. These results validate the effectiveness of our OA shortcut and XOR meta-residual components in overcoming fundamental limitations of residual learning in SNNs, providing new architectural insights for building high-performance neuromorphic systems. --- ### Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design Authors: Chen Wei, Fanding Xu, Minghao Sun, Zhiyuan Liu, Lin Wang, Tianrui Jia, Yihang Zhou, Yang Zhang Published: 2026-05-15 Categories: q-bio.BM, cs.AI arXiv: https://arxiv.org/abs/2605.27413v1 Proteins perform their biological functions through three-dimensional structures encoded by amino acid sequences, and ligand-binding protein co-design requires models that generate sequence-structure compatible proteins under explicit ligand constraints. Although continuous diffusion and flow-based models support ligand-aware design in coordinate or latent spaces, existing discrete diffusion protein language models mainly operate over sequence or structure tokens without direct small-molecule conditioning. We introduce \textbf{ProtLiD$^2$}, a \textbf{Prot}ein \textbf{L}igand-conditioned \textbf{D}iscrete \textbf{D}iffusion model for protein sequence-structure co-design. ProtLiD$^2$ jointly generates amino-acid sequence and discrete structure tokens while incorporating ligand chemical and geometric information through geometry-aware cross-attention. Trained on over one million ligand-protein complexes, ProtLiD$^2$ extends masked discrete diffusion to ligand-aware functional protein design. We further propose maximum confidence-margin guided ReMask decoding, an inference-time self-correction strategy that retains confident predictions and remasks uncertain tokens. ProtLiD$^2$ improves global fold confidence over Complexa in whole-protein design, increasing TM-score from 0.672 to 0.802 and pLDDT from 64.55 to 73.00. In pocket co-design, ProtLiD$^2$ reduces active-site BB-RMSD from 3.46/3.40Å for FAIR/PocketGen to 1.97Å, and improves ligand-aware pass rates over PocketGen from 14.86% to 59.73% and from 6.08% to 23.49% under stricter docking thresholds. These results support ligand-conditioned discrete diffusion as an effective token-space framework for functional protein co-design. Code will be available at https://github.com/auroua/ProtLiD. --- ### Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection Authors: Heqiang Wang, Weihong Yang, Zheyuan Yang, Jia Zhou, Xiaoxiong Zhong, Fangming Liu, Weizhe Zhang Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.23984v1 Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogeneous industrial sensors has driven industrial anomaly detection from unimodal to multimodal paradigms. However, existing methods are primarily designed for centralized and offline settings, overlooking the distributed and continuously generated data characteristic of real-world industrial environments. With the advancement of edge intelligence, modern edge devices are increasingly capable of not only data acquisition but also distributed model training, enabling collaborative intelligence across the system. Industrial anomaly detection represents a critical application in this context. Motivated by these challenges, we propose a novel framework termed Multimodal Online Distributed Industrial Anomaly Detection (MODIAD). We first present a comprehensive workflow for MODIAD and then formulate a Multi-class Intelligent Scheduling (MIS) problem to coordinate cross class model updates by balancing data sufficiency and class update frequency. To efficiently solve this problem, we design a Sequential Marginal Gain Greedy (SMG) algorithm that enables effective multi-class training under resource constraints. Furthermore, to improve the computational and communication efficiency during training, we propose an Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy, which significantly reduces system overhead while preserving detection performance. Extensive experiments on two representative multimodal industrial anomaly detection datasets, MVTec 3D-AD and Eyecandies demonstrate that the proposed approach achieves superior performance and efficiency under the MODIAD scenario. --- ### Uncertainty-aware neural emulation reveals climate-resilient maize traits at scale Authors: Mojdeh Saadati, Juan Panelo, Gustavo Visentini, Soumik Sarkar, Carlos Messina, Baskar Ganapathysubramanian Published: 2026-05-15 Categories: cs.CE, cs.LG, q-bio.OT arXiv: https://arxiv.org/abs/2605.22848v2 Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive for large scale exploration of genotype and environment interactions. Here we develop a probabilistic neural emulator of APSIM that reproduces key maize growth processes across 13 outputs with high fidelity (with R^2 of 0.93) while reducing simulation time by several orders of magnitude. Trained on two million simulations spanning diverse genetic, soil, and management conditions, and augmented with a convolutional synthetic weather generator that produces physically consistent climate sequences, the framework enables scalable exploration of crop responses under realistic and diverse environmental inputs while providing calibrated predictive uncertainty without costly Bayesian inference. Applying this framework across 100,000 trait configurations, six soil environments in Iowa and Illinois, and climate projections through the year 2100 under two emissions scenarios, we identify 181 maize trait combinations that consistently maintain high yield across all tested conditionsan analysis infeasible with the mechanistic model alone. We further show that radiation use efficiency and temperature driven root dynamics are dominant drivers of yield resilience. Notably, projected yield distributions vary substantially across locations, with some lower productivity sites exhibiting yield increases under future climate scenarios, indicating that climate change may reshape regional yield potential in nonintuitive ways. These results demonstrate how uncertainty aware emulation transforms mechanistic crop simulation from a computational bottleneck into an on demand discovery engine, one capable of interrogating the full genotype, environment and management space at a scale no process-based model can match. --- ### From Simulation to Discovery: AI Enabled Probabilistic Emulation of Mechanistic Crop Systems Authors: Mojdeh Saadati, Juan Panelo, Gustavo Visentini, Soumik Sarkar, Carlos Messina, Baskar Ganapathysubramanian Published: 2026-05-15 Categories: cs.CE, cs.LG, q-bio.OT arXiv: https://arxiv.org/abs/2605.22848v1 Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive for large scale exploration of genotype and environment interactions. Here we develop a probabilistic neural emulator of APSIM that reproduces key maize growth processes across 13 outputs with high fidelity (with R^2 of 0.93) while reducing simulation time by several orders of magnitude. Trained on two million simulations spanning diverse genetic, soil, and management conditions, and augmented with a convolutional synthetic weather generator that produces physically consistent climate sequences, the framework enables scalable exploration of crop responses under realistic and diverse environmental inputs while providing calibrated predictive uncertainty without costly Bayesian inference. Applying this framework across 100,000 trait configurations, six soil environments in Iowa and Illinois, and climate projections through the year 2100 under two emissions scenarios, we identify 181 maize trait combinations that consistently maintain high yield across all tested conditionsan analysis infeasible with the mechanistic model alone. We further show that radiation use efficiency and temperature driven root dynamics are dominant drivers of yield resilience. Notably, projected yield distributions vary substantially across locations, with some lower productivity sites exhibiting yield increases under future climate scenarios, indicating that climate change may reshape regional yield potential in nonintuitive ways. These results demonstrate how uncertainty aware emulation transforms mechanistic crop simulation from a computational bottleneck into an on demand discovery engine, one capable of interrogating the full genotype, environment and management space at a scale no process-based model can match. --- ### Harnesses for Inference-Time Alignment over Execution Trajectories Authors: Boyuan Wang, Bochao Li, Minghan Wang, Yuxin Tao, Fang Kong Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.21516v1 Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are not uniformly better: increasing decomposition or guidance can sometimes improve execution, but can also reduce final task success. We study harness design through the lens of inference-time trajectory alignment. This perspective separates harness into two mechanisms: task decomposition, which structures a task into sub-goals, and guided execution, which reshapes local action distributions during execution. This decomposition allows us to quantify how workflow granularity, retry budgets, and guidance-induced action reweighting shape the performance limits of harness design. It further reveals concrete failure modes, including over-decomposition, over-pruning, and hallucinated execution. We validate these predictions through controlled synthetic experiments and real terminal agent benchmarks. Inspired by the theory, we further show that effective harnesses can be partial: specifying only the initial steps and leaving the remaining execution to agent can achieve higher pass rate than fully structured workflows. --- ### Predicting Performance of Symbolic and Prompt Programs with Examples Authors: Chengqi Zheng, Keya Hu, Shuzhi Liu, Tao Wu, Kevin Ellis, Yewen Pu Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.21515v1 LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study performance prediction: given a program, either symbolic (e.g. Python) or a prompt executed on an LLM, and a few in-domain examples, predict its performance on unseen tasks from the same domain. We use a simple coin-flip model, treating each pass/fail program execution as a Bernoulli random variable, whose success probability is the programs unknown performance. In this model, performance depends entirely on: 1) the observed execution outcomes on test cases, and 2) a prior over performances. We compile empirical performance priors from a corpus of diverse programs and tasks, and find that performance for symbolic programs (e.g., Python) are all or nothing, while prompt programs have a diffuse prior with many nearly-correct programs. This difference explains why a few passing tests can certify symbolic programs but not prompt programs. Building on this insight, we develop RAP (Retrieved Approximate Prior), which retrieves similar tasks and prompt programs from an existing corpus to construct a proxy prior, which is then used to predict performance. We show RAP achieves solid performances. --- ### Conditional Entropy of Heat Diffusion on Temporal Networks Authors: Samuel Koovely, Alexandre Bovet Published: 2026-05-15 Categories: cs.SI, cond-mat.stat-mech, cs.IT, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2605.21514v2 Diffusion-based information-theoretic approaches provide new theoretical and practical tools to study complex networks. So far, they have not been generalized to temporal networks. In this work, we show that common entropic measures based on modeling diffusion on graphs, such as the entropy rate and the spectral entropy, do not generalize straightforwardly to temporal networks due to the process's non-stationarity and temporal asymmetries. Instead, we propose the conditional entropy of heat diffusion as an entropic measure for continuous-time temporal networks and study its properties. We show that this quantity is monotone in time, yielding an information-theoretic analog of the second law of thermodynamics for inhomogeneous diffusion on temporal networks. We provide an upper bound and suggest a lower bound on its evolution and explain how discrepancies from it arise due to asymmetric temporal paths. We then introduce a local version of conditional entropy, designed to probe diffusion over finite temporal windows, and show that it provides an informative signal for change-point detection in continuous-time temporal networks. We evaluate the proposed methodology on synthetic benchmarks, including comparative experiments with existing nonparametric baselines in the snapshot setting, and then apply it to a real-world temporal contact network. Finally, we show how to use detected change points to guide community detection on targeted sub-intervals, improving the quality and interpretability of the clustering results. --- ### GenAI-FDIA: Physics-Informed Generative Models for False Data Injection Attacks Authors: Mohammad A. Razzaque, Muta Tah Hira Published: 2026-05-15 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.18873v1 Training and evaluating false data injection attack (FDIA) detectors for power systems is constrained by data scarcity. Operational grid measurements are commercially sensitive, and hand-crafted attacks fail to capture complex distributional structures imposed by network physics. We present \textsc{GenAI-FDIA}, a framework benchmarking a pool of $P{=}20$ architectures for physics-compliant FDIA synthesis, spanning Wasserstein GANs, MMD-VAEs, normalising flows, diffusion models, and cross-family hybrids. These are evaluated across three IEEE testbeds (14-bus DC, 30-bus DC, and 14-bus AC) under a 60/20/20 chronological split using data-driven Bad Data Detection (BDD) threshold calibration. Our empirical results verify that these models generate high-fidelity attacks, with all architectures achieving evasion rates of $ε_{\text{BDD}} \ge 86.6\%$ on the 14-bus network; additionally, limiting an attacker's topological knowledge induces a measurable degradation in stealthiness ($p \le 0.0022$). Crucially, we identify a previously unreported failure mode: applying affine physics projections directly in normalised feature spaces critically displaces the attack vector, collapsing BDD evasion from ${\sim}55\%$ to $<\!2\%$ on the 30-bus testbed. We resolve this via a novel inference-time harmoniser, restoring full stealthiness ($ε_{\text{BDD}}{=}100\%$) across all physics-informed variants without retraining. Finally, we isolate a covariance-collapse phenomenon ($κ\approx {-}0.076$) within advanced hybrid architectures and rectify it through 50-epoch warm-up schedules ($κ\to 0.785$, $Δ\text{MMD}={-}3.1\%$). Ultimately, \textsc{GenAI-FDIA} delivers a robust recovery blueprint applicable to any physics-constrained generative model deployed for power-system security. --- ### EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly Authors: Shih-Yu Lai, Chia-Ching Yen, Yang-Ting Shen, Peter Yichen Chen, Yu-Lun Liu, Bing-Yu Chen Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.18872v1 Robotic assembly in architectural construction faces a persistent bottleneck: existing planners are either highly specialized, requiring prohibitive retraining for every new geometric design, or operationally inefficient, treating structural sequencing and kinematic motion as disjoint processes. We present EUPHORIA, a unified framework that achieves universal few-shot adaptability and dynamic efficiency through a hybrid optimization strategy. To overcome the retraining bottleneck, we propose a Meta-Geometric Encoder based on Graph Hypernetworks: unlike standard contrastive learning, which performs only feature-level recognition, our hypernetwork dynamically generates policy parameters from a minimal support set, enabling parameter-level adaptation to complex topologies (e.g., domes, arches) without gradient-based retraining. For structural reasoning, we introduce a Physics-Informed Graph Transformer trained via Soft Actor-Critic (SAC), with a Physics-Bias Attention mechanism that modulates attention scores using contact forces from Discrete Element Model (DEM) simulations, guiding the planner toward structurally critical connections. We further ensure operational efficiency through Kinematics-Aware Sequencing, where the SAC objective penalizes high-energy transitions. Finally, we bridge the Sim2Real gap via Residual Stability Correction, a differentiable optimization layer that fine-tunes coarse assembly actions by minimizing a joint energy-stability cost prior to execution. Experiments show that EUPHORIA significantly reduces energy consumption over decoupled baselines and achieves state-of-the-art success rates on unseen, non-standard geometries with minimal few-shot examples, fusing meta-learning, physics-informed attention, and residual optimization into a cohesive, generalized planner. --- ### Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning Authors: Shireen Kudukkil Manchingal, Abhey Kalia, Fernanda Gonçalves, Shebin Rawther Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18871v1 When Large Language Models produce structured outputs such as travel plans, code solutions, or multi-step proofs, individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions. We propose a decomposed energy function that combines a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs. The quality scorer is a heterogeneous ensemble of low-rank adapters on a single frozen encoder (3% trainable parameters); the ensemble mean ranks candidates while the standard deviation quantifies epistemic uncertainty, driving a two-pass inference loop that triggers targeted regeneration or abstention. Across five benchmarks (GSM8K, MuSR, TravelPlanner, TACO, Knights & Knaves), our 149M-parameter verifier orchestrating a pool of 7-26B open generators outperforms single-shot Qwen-72B on every benchmark, matches Claude Sonnet 4.6 on MuSR (67.7% vs. 68.0%), and reduces constraint violations by 53% relative to Opus 4.6 on TravelPlanner (oracle 0.028, random 0.231). The two routes are complementary: structural verification wins when constraints are checkable (the verifier captures signal frontier models cannot self-detect), while pretraining-scale priors win where they are not (narrative inference, code semantics). A cross-dataset confounding analysis confirms genuine quality discrimination on four reasoning tasks and identifies a model-identity shortcut on code, mitigated via last-layer retraining. Scorers trained on difficult data transfer zero-shot: a MuSR-trained scorer achieves 93.9% on GSM8K without seeing a math problem. --- ### Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows Authors: Alex Massucco, Leonardo Del Grande, Marcello Carioni, Christoph Brune, Carola-Bibiane Schönlieb Published: 2026-05-15 Categories: cs.LG, math.AP, math.FA arXiv: https://arxiv.org/abs/2605.18870v1 In recent years, transformer architectures have revolutionized the field of language processing, opening the door to previously unforeseen possibilities. However, from a theoretical point of view, the mathematical models proposed in the literature often lack direct contact with the actual architectures and depend on strong simplifying assumptions. In this paper, we reduce this gap by modelling the data flow in multi-headed transformer architectures as time-dependent gradient flows for a suitable interaction energy capturing the design of the attention mechanism. The explicit dependence on time allows us to consider different weights for each head and for each layer, without imposing constraints on the initialization method. Moreover, we prove that, under a suitable integrability assumption on the evolution of the weights, each element of the $ω$-limit set of the gradient flows is a stationary point of the interaction energy at a limiting weight distribution. Finally, we analyse the stability of the gradient flows considering perturbations of both the initial data and the weights. Specifically, on the one hand, we study the robustness of the proposed models with respect to noisy inputs, establishing a continuous dependence of the gradient flows on the initial data and uniqueness of the flows. On the other hand, we prove the $Γ$-convergence of the perturbed interaction energy to the unperturbed one, leading to the convergence of the corresponding gradient flows. We complement these theoretical results with numerical experiments that confirm the predicted energy-dissipation identity and clarify the asymptotic behavior of the dynamics in both the autonomous-like (Ornstein--Uhlenbeck) and the genuinely non-autonomous (oscillating-weights) regimes. --- ### MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization Authors: Jan Büssing, Moritz Schlager, Timo Heiß, Tom Zehle, Matthias Feurer Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2605.18869v1 Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need for automatic prompt optimization. Existing methods predominantly focus on performance alone, ignoring competing objectives such as inference cost or latency. At the same time, existing work on multi-objective prompt optimization relies on off-the-shelf NSGA-II, ignoring optimization efficiency. As a remedy, we introduce MO-CAPO, a novel multi-objective prompt optimization algorithm that jointly optimizes performance and inference cost while leveraging budget allocation for cost-efficient optimization. We further propose a deployment-oriented cost objective that captures the full computational profile of LLM inference. We evaluate our approach across four tasks and three LLMs and compare it to an NSGA-II-based multi-objective method and state-of-the-art single-objective prompt optimizers. Results show that MO-CAPO consistently identifies strong, robust, and diverse Pareto front approximations while maintaining cost-efficiency. It outperforms the NSGA-II baseline on 8 out of 12 cases in terms of the noisy R2 metric and achieves competitive performances often already at a considerably lower budget. The discovered solution sets span diverse performance-cost trade-offs that are omitted by single-objective optimizers, yet the top-performance candidates remain competitive with single-objective solutions. Additionally, we conduct the first evaluation of multi-objective machine learning experiments that considers generalization and robustness through noisy R2 and approximation gap, enabling a more realistic assessment of solution quality. MO-CAPO enables practitioners to select from an efficiently discovered set of multiple prompts offering different trade-offs between performance and cost. --- ### DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models Authors: Ye Sun, Xin Wang, Jiaming Zhang, Yifeng Gao, Yixu Wang, Yifan Ding, Qixian Zhang, Henghui Ding, Xingjun Ma, Yu-Gang Jiang Published: 2026-05-15 Categories: cs.CR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.18868v1 While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined objectives, tightly coupling each attack to a specific model or task, which restricts their scalability and flexibility in real-world scenarios. In this work, we present DarkLLM, a novel attack framework that trains an LLM to translate natural-language attack instructions into latent attack vectors, which are then decoded into visual adversarial perturbations. By leveraging natural-language instruction tuning, DarkLLM not only unifies targeted, untargeted, segmentation, and multi-model attacks within a single framework, but also achieves flexible and controllable adversarial generation, enabling each instruction to produce a perturbation that induces desired behaviors across heterogeneous models. Through extensive experiments across 4 tasks, 13 datasets, and 15 models, we demonstrate that DarkLLM with only 1B parameters can follow attacker instructions and generate highly effective attacks against CLIP, SAM, and frontier LLMs, revealing a systemic vulnerability in modern foundation models. --- ### EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample Authors: Guohao Chen, Shuaicheng Niu, Geng Li, Yunbei Zhang, Shilin Shan, Chunyan Miao, Jianfei Yang Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18867v1 Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation (BP), which incurs substantial memory overhead and makes them difficult to deploy on edge devices, quantized models, specialized accelerators, or black-box models. In this work, we study test-time model evolution under a strict two-forward budget, a setting that pushes adaptation toward highly efficient real-world deployment. We reveal three key obstacles in zeroth-order test-time optimization: susceptibility to shortcut solutions, uncontrolled weight drift, and ineffective update direction estimation. To overcome them, we propose EVA-0, a minimal zeroth-order adaptation framework that: 1) keeps the loss scale-invariant to prevent shortcut solutions; 2) devises an anchor-guided optimization strategy to alleviate weight drift; 3) uses sample-wise symmetric two-sided perturbation for update direction estimation and inference. EVA-0 requires no BP and performs both inference and adaptation within only two forward passes per sample. Results on ImageNet-C & ViT-Base show that EVA-0 outperforms both BP-based DeYO and BP-free FOA, while achieving a 14x speed-up over FOA. Code will be released. --- ### FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives Authors: Huaxi Huang, Meng Li, Zhengqing Gao, Xi Zhou, Xiaoshui Huang, Xiao Sun Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18866v2 Reconstructing continuous flow fields from sparse surface-mounted sensors is central to aerodynamic design, flow control, and digital-twin instrumentation. Existing neural methods for this task typically encode sensor readings into implicit latent codes with little spatial interpretability and limited formal guidance on how representational capacity should scale with observation count. Inspired by 3D Gaussian Splatting, we introduce FLUIDSPLAT, a sensor-conditioned model that predicts K anisotropic Gaussian primitives forming a partition-of-unity scaffold, a spatially explicit and interpretable intermediate representation of the flow. For an idealized Gaussian primitive estimator, we prove an $O(K^{-s/d})$ approximation rate for fields with Sobolev smoothness $s$; incorporating $N$ noisy observations yields a squared-risk decomposition with bias $O(K^{-2s/d})$ and variance $O(σ^{2}K/N)$.Balancing the two yields $K^{*}\!\sim\!(N/σ^{2})^{d/(2s+d)}$: primitive count cannot grow freely under sparse sensing, revealing a variance bottleneck that motivates complementing the scaffold with a state-conditioned residual decoder. Across four benchmarks spanning 2D and 3D, FLUIDSPLAT achieves 11-28% error reduction over several strong baselines on cylinder flow, AirfRANS, FlowBench LDC-3D, and PhySense-Car 3D benchmarks. --- ### From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation Authors: Yuxin Ren, Maxwell D Collins, Miao Hu, Huanrui Yang Published: 2026-05-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.18865v1 Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive substitution is often lossy, especially at larger scales. This paper revisits attention replacement through the lens of sparsity. Based on the observation of diverse sparsity patterns across transformer layers, we posit that pretrained transformers decompose the complex token dependency across tokens into various sequence-to-sequence mappings of diverse complexities, where some layer functionalities can be approximated and replaced with much simpler sequential modules without loss. We evaluate this premise using a plug-and-play layer-wise distillation framework to approximate and replace attention functionalities in pretrained vision transformer models. Controlled group-wise replacements under a fixed training budget reveal a clear pattern: substituting layers with sparser attention incurs substantially smaller accuracy drops than replacing denser ones. We further impose explicit attention sparsity on the pretrained ViT via AViT-style token retention and perform sparsity-guided distillation for sequential replacing models, where we see increasing teacher sparsity consistently reduces the student-teacher gap. The proposed method achieves efficient attention replacement for reduced parameter size and latency through the guidance of attention sparsity. --- ### SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs Authors: Chanuk Lee, Minki Kang, Sung Ju Hwang Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.18864v1 Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k, raising the question of whether RLVR genuinely enables large language models to acquire novel reasoning abilities or merely enhances the efficiency of sampling reasoning modes already present in the base model. Prior analyses largely support the latter view, attributing this limitation to structural properties of standard RLVR objectives that result in insufficient exploration pressure. In this work, we argue that a central structural constraint arises from reverse-KL regularization, which stabilizes training but inherently anchors the policy to the reference distribution, thereby suppressing the emergence of alternative reasoning modes. However, we show that neither removing the KL term nor replacing it with forward-KL provides a satisfactory solution, as both disrupt the efficiency-coverage trade-off by either inducing reward hacking or allocating probability mass to off-target regions. To resolve this tension, we propose SAGE, a principled framework that enables controllable empirical support expansion by reshaping the reverse-KL anchor distribution itself through a guide function q(x,y), achieving consistent improvements in both pass@1 and pass@k across challenging mathematical reasoning benchmarks. Our code is available at https://github.com/tally0818/SAGE. --- ### Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables Authors: Hangyu Wu Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.18862v1 Cardiovascular disease remains the leading cause of death worldwide, and early detection of arrhythmias through continuous ECG monitoring on wearable devices can prevent life-threatening events. Federated Learning (FL) enables privacy-preserving collaborative training by keeping raw ECG data on device, yet standard FL incurs prohibitive communication overhead and standard deep learning models cannot fit on ultra-low-power microcontrollers. We propose Family-Grouped Hierarchical Federated Learning (Family-FL), a three-tier architecture that uses the family as a natural privacy boundary for intra-family aggregation before global synchronization. We further design a hardware-constrained Tiny CNN-LSTM architecture with only 669 parameters, INT8-quantized to occupy merely 4.65KB Flash and 2.95KB RAM, meeting the constraints of STC32G12K128-class microcontrollers. Experiments on the MIT-BIH Arrhythmia Database (mean of 5 independent runs with different seeds) demonstrate that Family-FL reduces communication volume by 76.7% compared to FedAvg while maintaining comparable accuracy. Family-FL-Tiny achieves 91.9 +/- 1.2% accuracy with macro-F1 of 0.483 +/- 0.031, reducing total communication to 0.31% of FedAvg. The model achieves reliable ventricular arrhythmia detection (per-class F1 = 0.80), the most clinically critical abnormality for home-based preliminary screening. These results demonstrate the technical feasibility of privacy-preserving federated learning on ultra-resource-constrained microcontrollers through simulation-based evaluation. We honestly discuss limitations: no hardware deployment, single-dataset validation (MIT-BIH, 47 subjects), reduced rare-class sensitivity, and absence of formal differential privacy guarantees. --- ### GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction Authors: Liangyi Huang, Zichen Liu, Fei Shao, Shang Ma, Mengshi Zhang, Zihao Chen, Yanfang Ye, Xusheng Xiao Published: 2026-05-15 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.16714v1 Security knowledge graphs can provide computable external memory for security agents, but constructing them from long-form cyber threat intelligence (CTI) remains difficult: LLMs often lack grounded security-domain knowledge, and end-to-end document-to-graph training is hard to supervise with cheap, stable rewards. We present GRID (Graph Representation of Intelligence Data), an end-to-end framework for security text knowledge graph construction. GRID first builds security-domain supervision from CTI articles by creating traceable article-graph alignments through graph extraction and knowledge-graph-conditioned text revision. It then turns document-to-graph learning into a scripted task bank combining four-option multi-select questions with triple-level regex matching targets, yielding more stable task-specific rewards than repeatedly scoring full graph outputs with an LLM judge. Using this supervision pipeline, we train two Qwen3-4B-Instruct-2507-based 4B extractors: a primary Task-bank Reward model and a secondary End2End Reward model with LLM-as-judge precision/recall rewards. On 249 CTI articles from GRID, CASIE, CTINexus, MalKG, and SecureNLP, the Task-bank Reward model with the ontology-guided GRID extraction pipeline reaches 84.62% source-averaged precision, 64.91% source-averaged recall, and 68.53% Avg F1, achieving the best source-averaged recall and near-top Avg F1 with lower token usage and deployment cost. The End2End Reward model reaches 76.91% precision, 53.85% recall, and 58.06% Avg F1. Further analyses show that task-bank rewards can be built once offline and reused across later post-training runs, outperforming online End2End LLM-as-judge reward and weaker alternatives such as Choice-only Reward and End2End SFT without RL. --- ### GeoWorld-VLM: Geometry from World Models for Vision-Language Models Authors: Renjie Gu, Kaichen Zhou, Yan Luo, Mengyu Wang Published: 2026-05-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16713v2 Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of this failure arises before language reasoning begins: the visual pathway may compress or discard critical 3D structural cues during feature extraction, so the language model receives image representations that are already insufficient for reliable spatial judgment. We introduce GeoWorld-VLM, a VLM-side distillation framework that transfers geometric structure from frozen camera-conditioned video world models into VLMs. GeoWorld-VLM fine-tunes only the image encoder and multimodal projector, aligning post-projector image features with intermediate world-model representations while leaving the main backbone frozen. Given images, a prompt, and a sampled camera trajectory, the world-model teacher converts static visual input into a synthetic multi-view spatial signal. Training combines spatial answer supervision, teacher-student feature alignment, and a preservation anchor to the original VLM. Since the language model remains frozen, GeoWorld-VLM preserves the original model's linguistic capabilities while attributing spatial improvements to the enhanced visual pathway. To evaluate the effectiveness and generality of the proposed method, we apply GeoWorld-VLM to two distinct VLM architectures and observe consistent improvements across both backbones. GeoWorld-VLM improves performance by approximately 4 percent on both the What'sUp and VSR benchmarks, suggesting that world-model-guided visual alignment generalizes across model structures and spatial reasoning datasets. --- ### Recall Isn't Enough: Bounding Commitments in Personalized Language Systems Authors: Rui Tang, Yichi Zhang, Xi Chen, Chen Dong, Youwei Yang, Yumeng Shen, Qiangqiang Liu Published: 2026-05-15 Categories: cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2605.16712v2 Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it turns noisy hints into hard constraints, drops rare witnesses, forgets downstream obligations, or answers despite infeasibility. We introduce Contract-Bounded Evidence Activation (CBEA) with Lexicographic Commitment Validation (LCV). CBEA activates a bounded evidence set using typed coverage, tail witnesses, and consequence debt; LCV validates structured commitments before prose and routes infeasible states to repair, abstention, or recontract. Across 360 fixtures and three generation backends, CBEA+LCV reaches zero failures within validator scope at 0.49-0.60 availability over attempted runs. Raw and long-context baselines with the same LCV gate reach zero only at 0.003-0.092. A shadow oracle diagnostic marks the limit: CBEA+LCV recalls 0.012 of uncompiled visible facts, while raw recalls 0.53. The result is a bounded operating point: explicit commitment control and 74-75% lower median input payload, not universal memory dominance. --- ### Isolating Nonlinear Independent Sources in fMRI with $β$-TCVAE Models Authors: Qiang Li, Shujian Yu, Jesus Malo, Jingyu Liu, Tülay Adali, Vince D. Calhoun Published: 2026-05-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.16708v1 Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in neuroimaging analysis. Traditional independent component analysis, widely used due to its ability to estimate interpretable functional brain networks, relies on a linear mixing assumption for latent sources, limiting its ability to capture the inherently nonlinear and complex organization of brain dynamics. More recently, deep representation learning methods have emerged as promising alternatives for modeling nonlinear latent structure. However, many of these approaches have been evaluated primarily on simulated datasets or natural image benchmarks, with comparatively limited validation on real-world neuroimaging data such as fMRI. In this work, we are motivated by the $β$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the $β$-VAE framework for learning latent representations without introducing additional hyperparameters during training. We adapt and modify this model to fMRI data for nonlinear source disentanglement, aiming to separate mixed spatial and temporal brain signals into interpretable components. We show that the $β$-TCVAE framework can recover meaningful nonlinear spatial components with biological relevance, including well-established intrinsic connectivity networks such as the default mode network. Furthermore, we evaluate the learned representations using functional network connectivity, showing that the latent structure captures coherent and interpretable brain organization patterns. This study provides a pilot investigation that bridges nonlinear representation learning and fMRI analysis. --- ### On-Device Interpretable Tsetlin Machine-Based Intrusion Detection for Secure IoMT Authors: Rahul Jaiswal, Per-Arne Andersen, Linga Reddy Cenkeramaddi, Lei Jiao, Ole-Christoffer Granmo Published: 2026-05-15 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.16707v2 The rapid evolution of digital health technologies is redefining healthcare services worldwide. The integration of wireless communication and Internet-enabled medical devices within Internet of Medical Things (IoMT) networks enables continuous, real-time patient monitoring. However, this increased connectivity raises cybersecurity and patient safety risks due to increasingly sophisticated cyberattacks. This paper proposes a novel on-device, interpretable Tsetlin Machine (TM)-based Intrusion Detection System (IDS) to identify various phases of cyberattacks in IoMT environments. The TM is a rule-driven and transparent machine learning (ML) approach that represents attack patterns using propositional logic. Extensive evaluations on the MedSec-25 dataset, encompassing various phases of realistic cyberattacks, show that the proposed model outperforms ML models, attaining an F1-score (macro) of 97.83%. Moreover, the proposed model offers explicit explanations of its decisions to enhance transparency using feature-level contributions, class-wise vote scores, and clause activation heatmaps. Edge deployment (Raspberry Pi) further supports real-time on-device inference and intrusion detection. The combination of interpretability and high performance makes the proposed model well-suited for IoMT healthcare, where trust, reliability, safety, and timely decision-making are critical. --- ### Convex Dataset Valuation for Post-Training Authors: Siqi Zeng, Christopher Jung, Rui Li, Zhe Kang, Ming Li, Nima Noorshams, Zhigang Wang, Fuchun Peng, Han Zhao, Xue Feng Published: 2026-05-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16704v1 Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers face constraints on compute, labeling, and licensing costs that preclude using all available data, necessitating principled dataset-level selection. These constraints are increasingly shaped by dataset marketplaces, where data acquisition is governed by budgets and negotiation. We study dataset valuation as a subset selection problem during LLM post-training. Our goal is to identify and weight auxiliary datasets so as to maximize target task performance given constrained budgets. We first show that commonly used gradient alignment scores provide a reasonable yet incomplete valuation signal, as they ignore redundancy among datasets. To address this, we propose a scalable convex dataset-level valuation method based on kernel mean matching (KMM) in gradient space, which jointly accounts for alignment with the target task and redundancy across auxiliary datasets. Through extensive experiments across diverse post-training settings and tasks, we show that our approach consistently outperforms existing valuation baselines, achieving stronger performance with low computational overhead. Our results position dataset valuation as a practical decision tool for post-training data selection in market-constrained large language model settings. The code is available at https://github.com/uiuctml/convex_data_valuation. --- ### Your SaaS Is an Insurance Product: A Modeling Framework Authors: Caio Gomes Published: 2026-05-15 Categories: cs.LG, q-fin.RM, stat.ML arXiv: https://arxiv.org/abs/2605.16699v1 Capped-usage SaaS products -- LLM subscriptions such as Claude Code and ChatGPT, cloud platforms such as Vercel and Cloudflare Workers, corporate benefit platforms, identity-verification services with liability transfer -- share a structural signature with insurance products: a fixed premium decoupled from realized consumption, stochastic per-user demand with heavy-tailed severity, a non-fungible cap that resets on a fixed schedule, and a portfolio-level exposure that requires reserve adequacy under tail risk. We argue that this is not an analogy. It is the same operational problem actuarial science has been tooled for decades to address, restated with new dependent variables (tokens, bandwidth bytes, function-invocations, gym check-ins) in place of medical claims. This paper proposes a modeling framework for capped-usage SaaS pricing built from frequency-severity decomposition, premium calculation principles, and Monte Carlo reserve adequacy. We map the framework to publicly observable subscription tiers in two domains (LLM services and cloud platforms), ground it in canonical health-insurance economics (Arrow 1963; Pauly 1968; Manning et al. 1987; Brot-Goldberg et al. 2017), and demonstrate divergence from traditional unit economics through a worked example. The contribution is operational rather than theoretical: not a new theorem, but vocabulary and tools currently absent from cs.LG/stat.ML practice. --- ### Face inpainting with Identity Preserving Latent Diffusion Models Authors: João Santos, Carlos Santiago, Manuel Marques Published: 2026-05-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16696v1 Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output remains a fundamental challenge. Identity consistency is crucial for downstream applications such as face recognition, digital forensics, and human-computer interaction, where even subtle identity distortions can significantly degrade performance or trust. Although diffusion-based generative models have recently achieved remarkable progress in image inpainting, they often struggle to faithfully retain individual-specific facial characteristics. On the other hand, existing identity-aware methods typically rely on costly fine-tuning, auxiliary supervision, or exhibit limited robustness to diverse occlusions, poses, and facial variations. To address these limitations, we propose ID-ControlNet, an identity-preserving face inpainting framework built upon latent diffusion models. Based on ControlNet architecture, our approach conditions the diffusion process on facial identity embeddings extracted from a pretrained face recognition network. This design enables reconstruction of occluded facial regions while maintaining global facial coherence and identity fidelity. Furthermore, we introduce an identity consistency and triplet loss training strategy that explicitly enforces alignment between the generated face and the target identity representation. Extensive experiments on CelebA-HQ, FFHQ, and on a new E-Mask dataset demonstrate that ID-ControlNet significantly improves identity preservation over standard diffusion-based inpainting methods, achieving performance comparable to SOTA identity-aware approaches. --- ### EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control Authors: Thomas Evers, Cristian Meo, Wendelin Bohmer, Justin Dauwels, Yaniv Oren Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.16692v5 We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is a planner that aims to find an action sequence that maximizes the estimated return. The return is estimated using a learned model and value networks, each of which can introduce error. EfficientTDMPC introduces three contributions that improve performance by aiming to reduce this error. First, we introduce a multi-horizon planning objective that evaluates the value at different rollout depths and averages them. Second, to our knowledge we are the first to train a value-equivalent dynamics ensemble. Our improved objective then averages over rollouts from multiple dynamics heads. Third, we add pessimistic reanalyze for tasks that can terminate early. Applying our contributions to a recent baseline (BMPC) yields EfficientTDMPC, which to our knowledge is the new state of the art in sample efficiency on HumanoidBench and the DeepMind Control Suite, reaching BMPC's final aggregated performance using 57\% fewer environment steps. --- ### EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control Authors: Thomas Evers, Cristian Meo, Wendelin Bohmer, Justin Dauwels, Yaniv Oren Published: 2026-05-15 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.16692v2 We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is a planner that aims to find an action sequence that maximizes the estimated return. The return is estimated using a learned model and value networks, each of which can introduce error. EfficientTDMPC proposes to reduce this error in two ways. First, it introduces an ensemble of dynamics models and averages the return estimates across those models and across different rollout depths. Second, it adds the option to apply an uncertainty penalty to the planner objective, yielding a planner that avoids actions with uncertain return estimates. It then adds practical improvements which increase buffer data freshness and reduce compute. Lastly, we find that our contributions enable EfficientTDMPC to benefit more from a higher update-to-data (UTD) ratio, further improving sample efficiency. To the best of our knowledge, in the low data regime of each benchmark, EfficientTDMPC achieves state-of-the-art (SOTA) in terms of sample efficiency on HumanoidBench-Hard and DMC hard, while matching SOTA on DMC easy. ---