# Research Papers — 2026-04 · bundle page 225 of 233 > Full-text markdown of papers #11201–11250 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/225 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/224.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/226.md) ### YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches Authors: Mostapha Benhenda Published: 2026-04-01 Categories: cs.LG, q-fin.GN arXiv: https://arxiv.org/abs/2604.02378v2 Forecasting startup success is notoriously difficult, partly because meaningful outcomes, such as exits, large funding rounds, and sustained revenue growth, are rare and can take years to materialize. As a result, signals are sparse and evaluation cycles are slow. Y Combinator batches offer a unique mitigation: each batch comprises around 200 startups, funded simultaneously, with evaluation at Demo Day only three months later. We introduce YC Bench, a live benchmark for forecasting early outperformance within YC batches. Using the YC W26 batch as a case study (196 startups), we measure outperformance with a Pre-Demo Day Score, a KPI combining publicly available traction signals and web visibility. This short-term metric enables rapid evaluation of forecasting models. As a baseline, we take Google mentions prior to the YC W26 application deadline, a simple proxy for prior brand recognition, recovering 6 of 11 top performers at YC Demo Day (55% recall). YC Bench provides a live benchmark for studying startup success forecasting, with iteration cycles measured in months rather than years. Code and Data are available on GitHub: https://github.com/benstaf/ycbench --- ### CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe Authors: Tara Saba, Zhiyang Chen, Jikai Jason Li, Anne Ouyang, Xujie Si, Fan Long Published: 2026-04-01 Categories: cs.LG, cs.AI, cs.DC, cs.PF, cs.SE arXiv: https://arxiv.org/abs/2604.01489v2 High-performance GPU kernels are critical to modern machine learning systems, yet developing them remains a manual, expert-driven process. Recent work has explored using LLMs to automate kernel generation, but generated kernels still fall short of carefully tuned references on standardized benchmarks. We present CuTeGen, an agentic GPU kernel synthesis framework that treats kernel development as a structured generate-test-refine workflow over the CuTe abstraction layer. Two design choices distinguish CuTeGen from prior work: targeting CuTe rather than raw CUDA, which exposes performance-critical structures such as tiling and data movement while remaining stable enough for iterative refinement, and a delayed profiling schedule that withholds low-level performance feedback until the kernel's high-level structure has stabilized. On the 209 tasks of KernelBench Level-1 and Level-2, CuTeGen achieves an average speedup of 1.71$\times$ over PyTorch and outperforms the prior agentic baseline CudaForge (0.89$\times$) at comparable per-task generation cost. Code available at https://github.com/taratt/cutegen.git --- ### AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks Authors: Prince Zizhuang Wang, Shuli Jiang Published: 2026-04-01 Categories: cs.AI, cs.SI arXiv: https://arxiv.org/abs/2604.01487v2 With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are becoming a reality. This setting creates novel privacy challenges: agents must coordinate across domain boundaries, mediate between humans, and interact with other users' agents, all while protecting sensitive personal information. While prior work has evaluated multi-agent coordination and privacy preservation, the dynamics and privacy risks of human-centered agentic social networks remain unexplored. To this end, we introduce AgentSocialBench, the first benchmark to systematically evaluate privacy risk in this setting, comprising scenarios across seven categories spanning dyadic and multi-party interactions, grounded in realistic user profiles with hierarchical sensitivity labels and directed social graphs. Our experiments reveal that privacy in agentic social networks is fundamentally harder than in single-agent settings: (1) cross-domain and cross-user coordination creates persistent leakage pressure even when agents are explicitly instructed to protect information, (2) privacy instructions that teach agents how to abstract sensitive information paradoxically cause them to discuss it more (we call it abstraction paradox). These findings underscore that current LLM agents lack robust mechanisms for privacy preservation in human-centered agentic social networks, and that new approaches beyond prompt engineering are needed to make agent-mediated social coordination safe for real-world deployment. --- ### The topological gap at criticality: scaling exponent d + η, universality, and scope Authors: Matthew Loftus Published: 2026-04-01 Categories: cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2604.01484v1 The topological gap $Δ= TP_{H_1}^{real} - TP_{H_1}^{shuf}$ -- the excess $H_1$ total persistence of the majority-spin alpha complex over a density-matched null -- encodes critical correlations in spin models. We establish finite-size scaling: $Δ(L,T) = A L^{d+η} G_-(L|t/T_c|)$, with $G_-(x) \sim (1+x/x_0)^{-(1+β/ν)}$. For 2D Ising, $α= 2.249 \pm 0.038$, matching $d+η= 9/4$ to $0.03σ$; the $G_-$ exponent $γ= 1.089 \pm 0.077$ is consistent with $1+β/ν= 9/8$ ($ΔR^2 < 10^{-5}$). For 2D Potts $q=3$ with $L$ up to 1024, $α= 2.272 \pm 0.024$ ($0.2σ$ from $d+η= 2.267$), with two-term corrections to scaling ($R^2 = 0.9999$). The $G_-$ exponent $γ= 1.114$ (68% CI $(1.053, 1.173)$) matches $1+β/ν= 17/15$. Scope boundaries: the law fails for 2D Potts $q=4$ ($α= 2.347 \pm 0.017$, $9.3σ$ from $d+η= 5/2$) where logarithmic corrections prevent convergence, and for raw 3D Ising ($4σ$ from $d+η$), but density normalization $Δ/|M|^{1/2}$ recovers $α= 3.06 \pm 0.04$ ($0.6σ$). The framework fails for first-order, BKT, and percolation. The criterion: $α= d+η$ holds when corrections to scaling are algebraic ($ω> 0$) but fails when logarithmic ($ω\to 0$). --- ### Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving Authors: Devakh Rashie, Veda Rashi Published: 2026-04-01 Categories: cs.LO, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2604.01483v1 The rapid evolution of autonomous, agentic artificial intelligence within financial services has introduced an existential architectural crisis: large language models (LLMs) are probabilistic, non-deterministic systems operating in domains that demand absolute, mathematically verifiable compliance guarantees. Existing guardrail solutions -- including NVIDIA NeMo Guardrails and Guardrails AI -- rely on probabilistic classifiers and syntactic validators that are fundamentally inadequate for enforcing complex multi-variable regulatory constraints mandated by the SEC, FINRA, and OCC. This paper presents the Lean-Agent Protocol, a formal-verification-based AI guardrail platform that leverages the Aristotle neural-symbolic model developed by Harmonic AI to auto-formalize institutional policies into Lean 4 code. Every proposed agentic action is treated as a mathematical conjecture: execution is permitted if and only if the Lean 4 kernel proves that the action satisfies pre-compiled regulatory axioms. This architecture provides cryptographic-level compliance certainty at microsecond latency, directly satisfying SEC Rule 15c3-5, OCC Bulletin 2011-12, FINRA Rule 3110, and CFPB explainability mandates. A three-phase implementation roadmap from shadow verification through enterprise-scale deployment is provided. --- ### DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data Authors: Arshia Ilaty, Hossein Shirazi, Amir Rahmani, Hajar Homayouni Published: 2026-04-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.01481v1 The development of robust clinical decision support systems is frequently impeded by the scarcity of high-fidelity, privacy-preserving biomedical data. While Generative Large Language Models (LLMs) offer a promising avenue for synthetic data generation, they often struggle to capture the complex, non-linear dependencies and severe class imbalances inherent in Electronic Health Records (EHR), leading to statistically plausible but clinically invalid records. To bridge this gap, we introduce DISCO-TAB (DIScriminator-guided COntrol for TABular synthesis), a novel framework that orchestrates a fine-tuned LLM with a multi-objective discriminator system optimized via Reinforcement Learning. Unlike prior methods relying on scalar feedback, DISCO-TAB evaluates synthesis at four granularities, token, sentence, feature, and row, while integrating Automated Constraint Discovery and Inverse-Frequency Reward Shaping to autonomously preserve latent medical logic and resolve minority-class collapse. We rigorously validate our framework across diverse benchmarks, including high-dimensional, small-sample medical datasets (e.g., Heart Failure, Parkinson's). Our results demonstrate that hierarchical feedback yields state-of-the-art performance, achieving up to 38.2% improvement in downstream clinical classifier utility compared to GAN and Diffusion baselines, while ensuring exceptional statistical fidelity (JSD < 0.01) and robust resistance to membership inference attacks. This work establishes a new standard for generating trustworthy, utility-preserving synthetic tabular data for sensitive healthcare applications. --- ### A Self-Evolving Agentic Framework for Metasurface Inverse Design Authors: Yi Huang, Bowen Zheng, Yunxi Dong, Hong Tang, Huan Zhao, S. M. Rakibul Hasan Shawon, Hualiang Zhang Published: 2026-04-01 Categories: cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2604.01480v2 Metasurface inverse design can realize complex optical functionality, but turning a target optical response into executable optimization code still requires substantial expertise in computational electromagnetics and solver-specific software engineering. We present a self-evolving agentic framework that lowers this barrier by coupling a coding agent, explicit human-readable skill files, and a deterministic physics-based evaluator. Rather than updating model weights, it revises the skill files from solver-grounded feedback, while the base model and differentiable solver, which provides the physics simulation and gradients, stay fixed. On a multi-type benchmark, skill evolution raises same-type task success from 38\% to 74\%, the fraction of physical criteria met from 0.51 to 0.87, and reduces average attempts from 4.10 to 2.30. On two new-type families, success holds near ceiling on one (0.92 to 0.90) and rises from 0.20 to 0.90 on the other. Skill evolution offers a practical path toward autonomous and accessible inverse-design workflows. --- ### RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space Authors: Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu, Hanzhuo Huang, Zhengming Yu, Mengfei Li, Yuheng Liu, Zekai Gu, Zibo Zhao, Yuan Liu, Xin Li et al. Published: 2026-04-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.01479v3 Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for structural completeness. Conversely, diffusion-based generation provides rich geometric details but struggles with multi-view consistency. We present RecGen3D, a framework that combines these two paradigms into a cooperative system. To overcome inherent conflicts in coordinate spaces, 3D representations, and training objectives, we align both models within a shared canonical space. We employ decoupled cooperative learning, which maintains stable training while enabling seamless collaboration during inference. Specifically, the reconstruction module is adapted to provide canonical geometric anchors, while the diffusion generator leverages latent-augmented conditioning to refine and complete the geometric structure. Experimental results demonstrate that RecGen3D achieves superior fidelity and robustness, outperforming existing methods in creating complete and consistent 3D models from sparse observations. --- ### UniRecGen: Unifying Multi-View 3D Reconstruction and Generation Authors: Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu, Hanzhuo Huang, Zhengming Yu, Mengfei Li, Yuheng Liu, Zekai Gu, Zibo Zhao, Yuan Liu, Xin Li et al. Published: 2026-04-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.01479v2 Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for structural completeness. Conversely, diffusion-based generation provides rich geometric details but struggles with multi-view consistency. We present UniRecGen, a unified framework that integrates these two paradigms into a single cooperative system. To overcome inherent conflicts in coordinate spaces, 3D representations, and training objectives, we align both models within a shared canonical space. We employ disentangled cooperative learning, which maintains stable training while enabling seamless collaboration during inference. Specifically, the reconstruction module is adapted to provide canonical geometric anchors, while the diffusion generator leverages latent-augmented conditioning to refine and complete the geometric structure. Experimental results demonstrate that UniRecGen achieves superior fidelity and robustness, outperforming existing methods in creating complete and consistent 3D models from sparse observations. Code is available at https://github.com/zsh523/UniRecGen. --- ### Soft MPCritic: Amortized Model Predictive Value Iteration Authors: Thomas Banker, Nathan P. Lawrence, Ali Mesbah Published: 2026-04-01 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2604.01477v1 Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet combining them at scale remains computationally challenging. We propose soft MPCritic, an RL-MPC framework that learns in (soft) value space while using sample-based planning for both online control and value target generation. soft MPCritic instantiates MPC through model predictive path integral control (MPPI) and trains a terminal Q-function with fitted value iteration, aligning the learned value function with the planner and implicitly extending the effective planning horizon. We introduce an amortized warm-start strategy that recycles planned open-loop action sequences from online observations when computing batched MPPI-based value targets. This makes soft MPCritic computationally practical, while preserving solution quality. soft MPCritic plans in a scenario-based fashion with an ensemble of dynamic models trained for next-step prediction accuracy. Together, these ingredients enable soft MPCritic to learn effectively through robust, short-horizon planning on classic and complex control tasks. These results establish soft MPCritic as a practical and scalable blueprint for synthesizing MPC policies in settings where policy extraction and direct, long-horizon planning may fail. --- ### From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering Authors: Rui Wu, Ruixiang Tang Published: 2026-04-01 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.01476v3 Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation setting, where models can rewrite evaluator code to trivially pass tests without solving the task, as a controlled testbed. Across both studied models, we identify a reproducible three-phase rebound pattern: models first attempt to rewrite the evaluator but fail, as their rewrites embed test cases their own solutions cannot pass. They then temporarily retreat to legitimate solving. When legitimate reward remains scarce, they rebound into successful hacking with qualitatively different strategies. Using representation engineering, we extract concept directions for shortcut, deception, and evaluation awareness from domain-general contrastive pairs and find that the shortcut direction tracks hacking behavior most closely, making it an effective representational proxy for detection. Motivated by this finding, we propose Advantage Modification, which integrates shortcut concept scores into GRPO advantage computation to penalize hacking rollouts before policy updates. Because the penalty is internalized into the training signal rather than applied only at inference time, Advantage Modification provides more robust suppression of hacking compared with generation-time activation steering. --- ### When Reward Hacking Rebounds: Understanding and Mitigating It with Representation-Level Signals Authors: Rui Wu, Ruixiang Tang Published: 2026-04-01 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.01476v1 Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation setting, where models can rewrite evaluator code to trivially pass tests without solving the task, as a controlled testbed. Across both studied models, we identify a reproducible three-phase rebound pattern: models first attempt to rewrite the evaluator but fail, as their rewrites embed test cases their own solutions cannot pass. They then temporarily retreat to legitimate solving. When legitimate reward remains scarce, they rebound into successful hacking with qualitatively different strategies. Using representation engineering, we extract concept directions for shortcut, deception, and evaluation awareness from domain-general contrastive pairs and find that the shortcut direction tracks hacking behavior most closely, making it an effective representational proxy for detection. Motivated by this finding, we propose Advantage Modification, which integrates shortcut concept scores into GRPO advantage computation to penalize hacking rollouts before policy updates. Because the penalty is internalized into the training signal rather than applied only at inference time, Advantage Modification provides more robust suppression of hacking compared with generation-time activation steering. --- ### Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation Authors: Yunbei Zhang, Chengyi Cai, Feng Liu, Jihun Hamm Published: 2026-04-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.01474v1 Adapting closed-box service models (i.e., APIs) for target tasks typically relies on reprogramming via Zeroth-Order Optimization (ZOO). However, this standard strategy is known for extensive, costly API calls and often suffers from slow, unstable optimization. Furthermore, we observe that this paradigm faces new challenges with modern APIs (e.g., GPT-4o). These models can be less sensitive to the input perturbations ZOO relies on, thereby hindering performance gains. To address these limitations, we propose an Alternative efficient Reprogramming approach for Service models (AReS). Instead of direct, continuous closed-box optimization, AReS initiates a single-pass interaction with the service API to prime an amenable local pre-trained encoder. This priming stage trains only a lightweight layer on top of the local encoder, making it highly receptive to the subsequent glass-box (white-box) reprogramming stage performed directly on the local model. Consequently, all subsequent adaptation and inference rely solely on this local proxy, eliminating all further API costs. Experiments demonstrate AReS's effectiveness where prior ZOO-based methods struggle: on GPT-4o, AReS achieves a +27.8% gain over the zero-shot baseline, a task where ZOO-based methods provide little to no improvement. Broadly, across ten diverse datasets, AReS outperforms state-of-the-art methods (+2.5% for VLMs, +15.6% for standard VMs) while reducing API calls by over 99.99%. AReS thus provides a robust and practical solution for adapting modern closed-box models. --- ### SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits Authors: Zikai Zhang, Rui Hu, Olivera Kotevska, Jiahao Xu Published: 2026-04-01 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.01473v3 Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious queries, which either introduce substantial latency or suffer from randomness in text generation. To overcome these limitations, we propose SelfGrader, a lightweight guardrail method that formulates jailbreak detection as a numerical grading problem using anchored token-level logits. Specifically, SelfGrader evaluates the safety of a user query within a compact set of numerical tokens (NTs) (e.g., 0-9) and interprets their logit distribution as an internal safety signal. To align these signals with the target safety rubric, SelfGrader constructs Probably Approximately Correct-guided ICL anchor examples and introduces a dual-perspective scoring rule that considers both the maliciousness and benignness of the query, yielding a stable and interpretable score that reflects harmfulness and reduces the false positive rate simultaneously. Extensive experiments across diverse jailbreak benchmarks, adaptive attacks, benign prompt benchmarks, multiple LLMs, and state-of-the-art guardrail baselines demonstrate that SelfGrader achieves strong robustness with low false positive rates, memory overhead, and latency. --- ### The Newton-Muon Optimizer Authors: Zhehang Du, Weijie Su Published: 2026-04-01 Categories: math.OC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.01472v1 The Muon optimizer has received considerable attention for its strong performance in training large language models, yet the design principle behind its matrix-gradient orthogonalization remains largely elusive. In this paper, we introduce a surrogate model that not only sheds new light on the design of Muon, but more importantly leads to a new optimizer. In the same spirit as the derivation of Newton's method, the surrogate approximates the loss as a quadratic function of the perturbation to a weight matrix $W$ using only three matrices: the gradient $G$, an output-space curvature matrix $H$, and the data matrix $Z$ that stacks the layer inputs. By minimizing this surrogate in one step and adopting a certain isotropic assumption on the weights, we obtain the closed-form update rule (up to momentum and weight decay) $W \leftarrow W - η\cdot \mathrm{msgn}(G(ZZ^\top)^{-1})$, where $η$ is the learning rate and $\mathrm{msgn}(X)=UV^\top$ if $X=USV^\top$ is a compact singular value decomposition. This new optimization method, which we refer to as Newton-Muon, shows that standard Muon can be interpreted as an implicit Newton-type method that neglects the right preconditioning induced by the input second moment. Empirically, on a reproduction of the earliest publicly released Modded-NanoGPT speedrun configuration using Muon for GPT-2 pretraining, Newton-Muon reaches the target validation loss in 6\% fewer iteration steps and reduces wall-clock training time by about 4\%. --- ### Oscillator-Based Associative Memory with Exponential Capacity: Theory, Algorithms, and Hardware Implementation Authors: Arie Ogranovich, Taosha Guo, Arvind R. Venkatakrishnan, Madelyn Shapiro, Francesco Bullo, Fabio Pasqualetti Published: 2026-04-01 Categories: cs.NE arXiv: https://arxiv.org/abs/2604.01469v1 Associative memory systems enable content-addressable storage and retrieval of patterns, a capability central to biological neural computation and artificial intelligence. Classical implementations such as Hopfield networks face fundamental limitations in memory capacity, scaling at most linearly with network size. We present an associative memory architecture based on Kuramoto oscillator networks with honeycomb topology in which memories are encoded as stable phase-locked configurations. The honeycomb network consists of multiple cycles that share nodes in a chain-like arrangement, creating a one-dimensional lattice of chained+loops. We prove that this architecture achieves exponential memory capacity: a network of $N$ oscillators can store $(2\lceil n_c/4 \rceil - 1)^m$ distinct patterns, where $m$ honeycomb cycles each contain $n_c$ oscillators. Moreover, we fully characterize all stable configurations and prove that each memory's basin of attraction maintains a guaranteed minimum size independent of network scale. Simulations using charge-density-wave (CDW) oscillators validate predicted phase-locking behavior, demonstrating practical realizability in neuromorphic hardware. --- ### A Dynamic Atlas of Persian Poetic Symbolism: Families, Fields, and the Historical Rewiring of Meaning Authors: Kourosh Shahnazari, Seyed Moein Ayyoubzadeh, Mohammadali Keshtparvar Published: 2026-04-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.01467v1 Persian poetry is often remembered through recurrent symbols before it is remembered through plot. Wine vessels, gardens, flames, sacred titles, bodily beauty, and courtly names return across centuries, yet computational work still tends to flatten this material into isolated words or broad document semantics. That misses a practical unit of organization in Persian poetics: related forms travel as families and gain force through recurring relations. Using a corpus of 129,451 poems, we consolidate recurrent forms into traceable families, separate imagistic material from sacred and courtly reference, and map their relations in a multi-layer graph. The symbolic core is relatively sparse, the referential component much denser, and the attachment zone between them selective rather than diffuse. Across 11 Hijri-century bins, some families remain widely distributed, especially Shab (Night), Ruz (Day), and Khaak (Earth). Wine vessels, garden space, flame, and lyric sound strengthen later, while prestige-coded and heroic-courtly vocabulary is weighted earlier. Century-specific graphs show change in arrangement as well as membership. Modularity rises, cross-scope linkage declines, courtly bridges weaken, and sacred bridges strengthen. Hub positions shift too: Kherqe (Sufi Robe) gains late prominence, Farkhondeh {Blessed} and Banafsheh (Violet) recede, and Saaghar (Wine Cup) stays central across the chronology. In this corpus, Persian symbolism appears less as a fixed repertory than as a long-lived system whose internal weights and connections change over time. --- ### Efficient Equivariant Transformer for Self-Driving Agent Modeling Authors: Scott Xu, Dian Chen, Kelvin Wong, Chris Zhang, Kion Fallah, Raquel Urtasun Published: 2026-04-01 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.01466v1 Accurately modeling agent behaviors is an important task in self-driving. It is also a task with many symmetries, such as equivariance to the order of agents and objects in the scene or equivariance to arbitrary roto-translations of the entire scene as a whole; i.e., SE(2)-equivariance. The transformer architecture is a ubiquitous tool for modeling these symmetries. While standard self-attention is inherently permutation equivariant, explicit pairwise relative positional encodings have been the standard for introducing SE(2)-equivariance. However, this approach introduces an additional cost that is quadratic in the number of agents, limiting its scalability to larger scenes and batch sizes. In this work, we propose DriveGATr, a novel transformer-based architecture for agent modeling that achieves SE(2)-equivariance without the computational cost of existing methods. Inspired by recent advances in geometric deep learning, DriveGATr encodes scene elements as multivectors in the 2D projective geometric algebra $\mathbb{R}^*_{2,0,1}$ and processes them with a stack of equivariant transformer blocks. Crucially, DriveGATr models geometric relationships using standard attention between multivectors, eliminating the need for costly explicit pairwise relative positional encodings. Experiments on the Waymo Open Motion Dataset demonstrate that DriveGATr is comparable to the state-of-the-art in traffic simulation and establishes a superior Pareto front for performance vs computational cost. --- ### Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis Authors: Keshav Shankar, Dan Ding, Wei Gao Published: 2026-04-01 Categories: cs.RO, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.01463v2 Physically Assistive Robots require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause substantial physical and cognitive fatigue for users with severe motor impairments. To solve this, we propose a low-burden, offline framework that translates unstructured natural language feedback directly into deterministic robotic control policies. To safely bridge the gap between ambiguous human speech and robotic code, our pipeline uses Large Language Models (LLMs) grounded in the Occupational Therapy Practice Framework. This clinical reasoning decodes subjective user reactions into explicit physical and psychological needs, which are then mapped into transparent decision trees. Before deployment, an automated "LLM-as-a-Judge" verifies the code's structural safety. We validated this system in a simulated meal preparation study with 10 adults with paralysis. Results show our natural language approach significantly reduces user workload compared to traditional baselines. Additionally, occupational therapists confirmed the generated policies are safe and accurately reflect user preferences. --- ### Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection Authors: Daniel Xie, Maxwell J. Jacobson, Adil Wazeer, Haiyan Wang, Xinghang Zhang, Yexiang Xue Published: 2026-04-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.01461v2 Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents and fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), which uses inter-document relationships to improve extraction accuracy in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. Our experiments demonstrate up to 98% precision in outlier detection across 6 scientific domains, reducing hallucinations and letting researchers focus on genuinely ambiguous cases. --- ### Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection Authors: Daniel Xie, Maxwell J. Jacobson, Adil Wazeer, Haiyan Wang, Xinghang Zhang, Yexiang Xue Published: 2026-04-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.01461v1 Reducing hallucinations in Large Language Models (LLMs) is essential for improving the accuracy of data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents but fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), a novel approach that uses the relationships between documents to improve extraction accuracy. Our application domain is in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. High-confidence results, supported by peer validation, are considered reliable. Our experiments demonstrate up to 98% precision in outlier detection across 6 domains of science, demonstrating that our design reduces hallucinations, enhances trust in automated systems, and allows researchers to focus on ambiguous cases, streamlining the data extraction workflows. --- ### Reinforcing Consistency in Video MLLMs with Structured Rewards Authors: Yihao Quan, Zeru Shi, Jinman Zhao, Ruixiang Tang Published: 2026-04-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.01460v2 Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal grounding: a model may fabricate object existence, assign incorrect attributes, or collapse repeated events while still producing a globally reasonable caption or answer. We study this failure mode through a compositional consistency audit that decomposes a caption into supporting factual and temporal claims, investigating whether a correct high-level prediction is actually backed by valid lower-level evidence. Our top-down audit reveals that even correct root relational claims often lack reliable attribute and existence support. This indicates that standard sentence-level supervision is a weak proxy for faithful video understanding. Furthermore, when turning to reinforcement learning (RL) for better alignment, standard sentence-level rewards often prove too coarse to accurately localize specific grounding failures. To address this, we replace generic sentence-level rewards with a structured reward built from factual and temporal units. Our training objective integrates three complementary components: (1) an instance-aware scene-graph reward for factual objects, attributes, and relations; (2) a temporal reward for event ordering and repetition; and (3) a video-grounded VQA reward for hierarchical self-verification. Across temporal, general video understanding, and hallucination-oriented benchmarks, this objective yields consistent gains on open-source backbones. These results suggest that structured reward shaping is a practical route to more faithful video understanding. --- ### Reinforcing Consistency in Video MLLMs with Structured Rewards Authors: Yihao Quan, Zeru Shi, Jinman Zhao, Ruixiang Tang Published: 2026-04-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.01460v1 Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal grounding: a model may fabricate object existence, assign incorrect attributes, or collapse repeated events while still producing a globally reasonable caption or answer. We study this failure mode through a compositional consistency audit that decomposes a caption into supporting factual and temporal claims, investigating whether a correct high-level prediction is actually backed by valid lower-level evidence. Our top-down audit reveals that even correct root relational claims often lack reliable attribute and existence support. This indicates that standard sentence-level supervision is a weak proxy for faithful video understanding. Furthermore, when turning to reinforcement learning (RL) for better alignment, standard sentence-level rewards often prove too coarse to accurately localize specific grounding failures. To address this, we replace generic sentence-level rewards with a structured reward built from factual and temporal units. Our training objective integrates three complementary components: (1) an instance-aware scene-graph reward for factual objects, attributes, and relations; (2) a temporal reward for event ordering and repetition; and (3) a video-grounded VQA reward for hierarchical self-verification. Across temporal, general video understanding, and hallucination-oriented benchmarks, this objective yields consistent gains on open-source backbones. These results suggest that structured reward shaping is a practical route to more faithful video understanding. --- ### Koopman Subspace Pruning in Reproducing Kernel Hilbert Spaces via Principal Vectors Authors: Dhruv Shah, Jorge Cortes Published: 2026-04-01 Categories: eess.SY, stat.ML arXiv: https://arxiv.org/abs/2604.01459v2 Data-driven approximations of the infinite-dimensional Koopman operator rely on finite-dimensional projections, where the predictive accuracy of the resulting models hinges heavily on the invariance of the chosen subspace. Subspace pruning systematically discards geometrically misaligned directions to enhance this invariance proximity, which formally corresponds to the largest principal angle between the subspace and its image under the operator. Yet, existing techniques are largely restricted to Euclidean settings. To bridge this gap, this paper presents an approach for computing principal angles and vectors to enable Koopman subspace pruning within a Reproducing Kernel Hilbert Space (RKHS) geometry. We first outline an exact computational routine, which is subsequently scaled for large datasets using randomized Nystrom approximations. Based on these foundations, we introduce the Kernel-SPV and Approximate Kernel-SPV algorithms for targeted subspace refinement via principal vectors. Simulation results validate our approach. --- ### Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Authors: Tianyi Zhao, Yinhan He, Wendy Zheng, Yujie Zhang, Chen Chen Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01457v3 Large language models are often not just wrong, but \emph{confidently wrong}: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather than signal uncertainty. Such verbalized overconfidence can mislead users and weaken confidence scores as a reliable uncertainty signal, yet its internal mechanisms remain poorly understood. We present a circuit-level mechanistic analysis of this inflated verbalized confidence in LLMs, organized around three axes: capturing verbalized confidence as a differentiable internal signal, identifying the circuits that causally inflate it, and leveraging these insights for targeted inference-time recalibration. Across two instruction-tuned LLMs on three datasets, we find that a compact set of MLP blocks and attention heads, concentrated in middle-to-late layers, consistently writes the confidence-inflation signal at the final token position. We further show that targeted inference-time interventions on these circuits substantially improve calibration. Together, our results suggest that verbalized overconfidence in LLMs is driven by identifiable internal circuits and can be mitigated through targeted intervention. --- ### Infeasibility Aware Large Language Models for Combinatorial Optimization Authors: Yakun Wang, Min Chen, Zeguan Wu, Junyu Liu, Sitao Zhang, Zhenwen Shao Published: 2026-04-01 Categories: cs.AI, cs.LG, quant-ph arXiv: https://arxiv.org/abs/2604.01455v1 Large language models (LLMs) are increasingly explored for NP-hard combinatorial optimization problems, but most existing methods emphasize feasible-instance solution generation and do not explicitly address infeasibility detection. We propose an infeasibility-aware framework that combines certifiable dataset construction, supervised fine-tuning, and LLM-assisted downstream search. For the minor-embedding problem, we introduce a new mathematical programming formulation together with provable zero-phase infeasibility screening, which enables scalable construction of training instances labeled either as feasible with structured certificates or as certifiably infeasible. Using training data generated through this exact optimization pipeline, we show that an 8B-parameter LLM can be fine-tuned to jointly perform solution generation and infeasibility detection. We further utilize LLM outputs as warm starts for downstream local search, providing a practical way to accelerate optimization even when the LLM outputs are imperfect. Experiments show that our fine-tuned model improves overall accuracy by up to 30\% over GPT-5.2; meanwhile LLM-guided warm starts provide up to $2\times$ speedup compared with starting from scratch in downstream local search. --- ### Nonlinear Methods for Analyzing Pose in Behavioral Research Authors: Carter Sale, Margaret C. Macpherson, Gaurav Patil, Kelly Miles, Rachel W. Kallen, Sebastian Wallot, Michael J. Richardson Published: 2026-04-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.01453v1 Advances in markerless pose estimation have made it possible to capture detailed human movement in naturalistic settings using standard video, enabling new forms of behavioral analysis at scale. However, the high dimensionality, noise, and temporal complexity of pose data raise significant challenges for extracting meaningful patterns of coordination and behavioral change. This paper presents a general-purpose analysis pipeline for human pose data, designed to support both linear and nonlinear characterizations of movement across diverse experimental contexts. The pipeline combines principled preprocessing, dimensionality reduction, and recurrence-based time series analysis to quantify the temporal structure of movement dynamics. To illustrate the pipeline's flexibility, we present three case studies spanning facial and full-body movement, 2D and 3D data, and individual versus multi-agent behavior. Together, these examples demonstrate how the same analytic workflow can be adapted to extract theoretically meaningful insights from complex pose time series. --- ### A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization Authors: Maxwell J. Jacobson, Daniel Xie, Jackson Shen, Adil Wazeer, Guang Lin, Xiao-Ying Yu, Haiyan Wang, Xinghang Zhang, Yexiang Xue Published: 2026-04-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.01452v2 Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery. --- ### A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization Authors: Maxwell J. Jacobson, Daniel Xie, Jackson Shen, Adil Wazeer, Haiyan Wang, Xinghang Zhang, Yexiang Xue Published: 2026-04-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.01452v1 Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery. --- ### When AI Gets it Wrong: Reliability and Risk in AI-Assisted Medication Decision Systems Authors: Khalid Adnan Alsayed Published: 2026-04-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.01449v3 Artificial intelligence (AI) systems are increasingly integrated into healthcare and pharmacy workflows, supporting tasks such as medication recommendations, dosage determination, and drug interaction detection. While these systems often demonstrate strong performance under standard evaluation metrics, their reliability in real-world decision-making remains insufficiently understood. In high-risk domains such as medication management, even a single incorrect recommendation can result in severe patient harm. This paper examines the reliability of AI-assisted medication systems by focusing on system failures and their potential clinical consequences. Rather than evaluating performance solely through aggregate metrics, this work shifts attention towards how errors occur and what happens when AI systems produce incorrect outputs. Through a series of controlled, simulated scenarios involving drug interactions and dosage decisions, we analyse different types of system failures, including missed interactions, incorrect risk flagging, and inappropriate dosage recommendations. The findings highlight that AI errors in medication-related contexts can lead to adverse drug reactions, ineffective treatment, or delayed care, particularly when systems are used without sufficient human oversight. Furthermore, the paper discusses the risks of over-reliance on AI recommendations and the challenges posed by limited transparency in decision-making processes. This work contributes a reliability-focused perspective on AI evaluation in healthcare, emphasising the importance of understanding failure behavior and real-world impact. It highlights the need to complement traditional performance metrics with risk-aware evaluation approaches, particularly in safety-critical domains such as pharmacy practice. --- ### Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars Authors: Derek Austin Published: 2026-04-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.01447v2 Recent 3D Gaussian splatting methods built atop SMPL achieve remarkable visual fidelity while continually increasing the complexity of the overall training architecture. We demonstrate that much of this complexity is unnecessary: by replacing SMPL with the Momentum Human Rig (MHR), estimated via SAM-3D-Body, a minimal pipeline with no learned deformations or pose-dependent corrections achieves the highest reported PSNR and competitive or superior LPIPS and SSIM on PeopleSnapshot and ZJU-MoCap. To disentangle pose estimation quality from body model representational capacity, we perform two controlled ablations: translating SAM-3D-Body meshes to SMPL-X, and translating the original dataset's SMPL poses into MHR both retrained under identical conditions. These ablations confirm that body model expressiveness has been a primary bottleneck in avatar reconstruction, with both mesh representational capacity and pose estimation quality contributing meaningfully to the full pipeline's gains. --- ### All Substitution Is Local Authors: Nidhish Shah, Shaurjya Mandal, Asfandyar Azhar Published: 2026-04-01 Categories: econ.TH, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2604.01443v1 When does consulting one information source raise the value of another, and when does it diminish it? We study this question for Bayesian decision-makers facing finite actions. The interaction decomposes into two opposing forces: a complement force, measuring how one source moves beliefs to where the other becomes more useful, and a substitute force, measuring how much the current decision is resolved. Their balance obeys a localization principle: substitution requires an observation to cross a decision boundary, though crossing alone does not guarantee it. Whenever posteriors remain inside the current decision region, the substitute force vanishes, and sources are guaranteed to complement each other, even when one source cannot, on its own, change the decision. The results hold for arbitrarily correlated sources and are formalized in Lean 4. Substitution is confined to the thin boundaries where decisions change. Everywhere else, information cooperates. Code and proofs: https://github.com/nidhishs/all-substitution-is-local. --- ### Generative Profiling for Soft Real-Time Systems and its Applications to Resource Allocation Authors: Georgiy A. Bondar, Abigail Eisenklam, Yifan Cai, Robert Gifford, Tushar Sial, Linh Thi Xuan Phan, Abhishek Halder Published: 2026-04-01 Categories: eess.SY, cs.LG, cs.OS, eess.SP, stat.ML arXiv: https://arxiv.org/abs/2604.01441v1 Modern real-time systems require accurate characterization of task timing behavior to ensure predictable performance, particularly on complex hardware architectures. Existing methods, such as worst-case execution time analysis, often fail to capture the fine-grained timing behaviors of a task under varying resource contexts (e.g., an allocation of cache, memory bandwidth, and CPU frequency), which is necessary to achieve efficient resource utilization. In this paper, we introduce a novel generative profiling approach that synthesizes context-dependent, fine-grained timing profiles for real-time tasks, including those for unmeasured resource allocations. Our approach leverages a nonparametric, conditional multi-marginal Schrödinger Bridge (MSB) formulation to generate accurate execution profiles for unseen resource contexts, with maximum likelihood guarantees. We demonstrate the efficiency and effectiveness of our approach through real-world benchmarks, and showcase its practical utility in a representative case study of adaptive multicore resource allocation for real-time systems. --- ### Know Your Streams: On the Conceptualization, Characterization, and Generation of Intentional Event Streams Authors: Andrea Maldonado, Christian Imenkamp, Hendrik Reiter, Thomas Seidl, Wilhelm Hasselbring, Martin Werner, Agnes Koschmider Published: 2026-04-01 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2604.01440v1 The shift toward IoT-enabled, sensor-driven systems has transformed how operational data is generated, favoring continuous, real-time event streams (ES) over static event logs. This evolution presents new challenges for Streaming Process Mining (SPM), which must cope with out-of-order events, concurrent activities, incomplete cases, and concept drifts. Yet, the evaluation of SPM algorithms remains rooted in outdated practices, relying on static logs or artificially streamified data that fail to reflect the complexities of real-world streams. To address this gap, we first perform a comprehensive review of data stream literature to identify stream characteristics currently not reflected in the SPM community. Next, we use this information to extend the conceptual foundation for ES. Finally, we propose Stream of Intent, a prototype generator to produce ES with specific features. Our evaluation shows excellence in producing reproducible, intentional ES for targeted benchmarking and adaptive algorithm development in SPM. --- ### ClawSafety: "Safe" LLMs, Unsafe Agents Authors: Bowen Wei, Yunbei Zhang, Jinhao Pan, Kai Mei, Xiao Wang, Jihun Hamm, Ziwei Zhu, Yingqiang Ge Published: 2026-04-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.01438v2 Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond conventional text-level jailbreaks, yet existing safety evaluations fall short: most test models in isolated chat settings, rely on synthetic environments, and do not account for how the agent framework itself shapes safety outcomes. We introduce CLAWSAFETY, a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type) and grounded in realistic, high-privilege professional workspaces spanning software engineering, finance, healthcare, law, and DevOps. Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages. We evaluate five frontier LLMs as agent backbones, running 2,520 sandboxed trials across all configurations. Attack success rates (ASR) range from 40\% to 75\% across models and vary sharply by injection vector, with skill instructions (highest trust) consistently more dangerous than email or web content. Action-trace analysis reveals that the strongest model maintains hard boundaries against credential forwarding and destructive actions, while weaker models permit both. Cross-scaffold experiments on three agent frameworks further demonstrate that safety is not determined by the backbone model alone but depends on the full deployment stack, calling for safety evaluation that treats model and framework as joint variables. Code and data will be available at: https://weibowen555.github.io/ClawSafety/. --- ### Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering Authors: Jingyue Li, André Storhaug Published: 2026-04-01 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.01437v1 With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black boxes, making it difficult to justify the superiority of Agentic AI approaches over baselines. Furthermore, missing information in the evaluation design description frequently renders the reproduction of results infeasible. To synthesize current evaluation practices for Agentic AI in SE, this study analyzes 18 papers on the topic, published or accepted by ICSE 2026, ICSE 2025, FSE 2025, ASE 2025, and ISSTA 2025. The analysis identifies prevailing approaches and their limitations in evaluating Agentic AI for SE, both in current research and potential future studies. To address these shortcomings, this position paper proposes a set of guidelines and recommendations designed to empower reproducible, explainable, and effective evaluations of Agentic AI in software engineering. In particular, we recommend that Agentic AI researchers make their Thought-Action-Result (TAR) trajectories and LLM interaction data, or summarized versions of these artifacts, publicly accessible. Doing so will enable subsequent studies to more effectively analyze the strengths and weaknesses of different Agentic AI approaches. To demonstrate the feasibility of such comparisons, we present a proof-of-concept case study that illustrates how TAR trajectories can support systematic analysis across approaches. --- ### Leveraging the Value of Information in POMDP Planning Authors: Zakariya Laouar, Qi Heng Ho, Zachary Sunberg Published: 2026-04-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.01434v1 Partially observable Markov decision processes (POMDPs) offer a principled formalism for planning under state and transition uncertainty. Despite advances made towards solving large POMDPs, obtaining performant policies under limited planning time remains a major challenge due to the curse of dimensionality and the curse of history. For many POMDP problems, the value of information (VOI) - the expected performance gain from reasoning about observations - varies over the belief space. We introduce a dynamic programming framework that exploits this structure by conditionally processing observations based on the value of information at each belief. Building on this framework, we propose Value of Information Monte Carlo planning (VOIMCP), a Monte Carlo Tree Search algorithm that allocates computational effort more efficiently by selectively disregarding observation information when the VOI is low, avoiding unnecessary branching of observations. We provide theoretical guarantees on the near-optimality of our VOI reasoning framework and derive non-asymptotic convergence bounds for VOIMCP. Simulation evaluations demonstrate that VOIMCP outperforms baselines on several POMDP benchmarks. --- ### Semantically Annotated Multimodal Dataset for RF Interpretation and Prediction Authors: Steve Blandino, Jelena Senic, Raied Caromi, Samuel Berweger, Anuraag Bodi, Camillo Gentile, Nada Golmie Published: 2026-04-01 Categories: cs.ET, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2604.01433v1 Current limitations in wireless modeling and radio frequency (RF)-based AI are primarily driven by a lack of high-quality, measurement-based datasets that connect RF signals to their physical environments. RF heatmaps, the typical form of such data, are high-dimensional and complex but lack the geometric and semantic context needed for interpretation, constraining the development of supervised machine learning models. To address this bottleneck, we propose a new class of multimodal datasets that combines RF measurements with auxiliary modalities like high-resolution cameras and lidar to bridge the gap between RF signals and their physical causes. The proposed data collection will span diverse indoor and outdoor environments, featuring both static and dynamic scenarios, including human activities ranging from walking to subtle gestures. By achieving precise spatial and temporal co-registration and creating digital replicas for voxel-level annotation, this dataset will enable transformative AI research. Key tasks include the forward problem of predicting RF heatmaps from visual data to revolutionize wireless system design, and the inverse problem of inferring scene semantics from RF signals, creating a new form of RF-based perception. --- ### Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation Authors: Hexuan Wang, Jingyu Zhang, Benjamin Van Durme, Daniel Khashabi Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01432v4 Citation granularity -- whether to cite individual sentences, paragraphs, or documents -- is a critical design choice in attributed generation. While fine-grained citations are commonly preferred for precise human verification, their impact on model performance remains under-explored. We analyze four model scales (8B-120B) and demonstrate that enforcing fine-grained (sentence-level) citations forfeits gains of 2-97% (median 40%) relative to the best-performing granularity, and up to 338% on individual tasks. Strikingly, setting citation granularity to its optimal value (based on attribution quality) unlocks these substantial gains while leaving overall answer correctness essentially unchanged (between -2.3% and +4.4%). We observe a consistent pattern where attribution quality peaks at intermediate (paragraph-level) granularities: finer citations appear to sever the semantic dependencies needed to ground a claim, while excessively coarse citations introduce distracting noise. Importantly, this performance gap varies with scale: when a claim rests on a small or moderate amount of evidence, it disproportionately penalizes larger models by disrupting the multi-sentence information synthesis at which they excel. Fine-grained citation rests on the premise that a sentence is a sufficient unit of evidence on its own. Our results indicate that it often is not, and that this is a property of the model rather than of the citation standard. Standards fixed for human verifiability may therefore paradoxically degrade the very attribution they aim to ensure; effective attribution requires matching granularity to the model's semantic scope rather than fixing it by convention. --- ### Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation Authors: Hexuan Wang, Jingyu Zhang, Benjamin Van Durme, Daniel Khashabi Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01432v2 Citation granularity - whether to cite individual sentences, paragraphs, or documents - is a critical design choice in attributed generation. While fine-grained citations are often preferred for precise human verification, their impact on model performance remains under-explored. We analyze four model scales (8B-120B) and demonstrate that enforcing fine-grained citations degrades attribution quality by 16-276% compared to the best-performing granularity. We observe a consistent performance pattern where attribution quality peaks at intermediate granularities (paragraph-level). Our analysis suggests that fine-grained (sentence-level) citations disrupt necessary semantic dependencies for attributing evidence to answer claims, while excessively coarse citations (multi-paragraph) introduce distracting noise. Importantly, the magnitude of this performance gap varies non-monotonically with model scale: fine-grained constraints disproportionately penalize larger models, suggesting that atomic citation units disrupt the multi-sentence information synthesis at which these models excel. Strikingly, citation-optimal granularity leads to substantial gains in attribution quality while preserving or even improving answer correctness. Overall, our findings demonstrate that optimizing solely for human verification via fine-grained citation disregards model constraints, compromising both attribution faithfulness and generation reliability. Instead, effective attribution requires aligning citation granularity with the model's natural semantic scope. --- ### Improving Latent Generalization Using Test-time Compute Authors: Arslan Chaudhry, Sridhar Thiagarajan, Andrew Lampinen Published: 2026-04-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.01430v1 Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary strengths, in-weights learning frequently struggles to facilitate deductive reasoning over the internalized knowledge. We characterize this limitation as a deficit in latent generalization, of which the reversal curse is one example. Conversely, in-context learning demonstrates highly robust latent generalization capabilities. To improve latent generalization from in-weights knowledge, prior approaches rely on train-time data augmentation, yet these techniques are task-specific, scale poorly, and fail to generalize to out-of-distribution knowledge. To overcome these shortcomings, this work studies how models can be taught to use test-time compute, or 'thinking', specifically to improve latent generalization. We use Reinforcement Learning (RL) from correctness feedback to train models to produce long chains-of-thought (CoTs) to improve latent generalization. Our experiments show that this thinking approach not only resolves many instances of latent generalization failures on in-distribution knowledge but also, unlike augmentation baselines, generalizes to new knowledge for which no RL was performed. Nevertheless, on pure reversal tasks, we find that thinking does not unlock direct knowledge inversion, but the generate-and-verify ability of thinking models enables them to get well above chance performance. The brittleness of factual self-verification means thinking models still remain well below the performance of in-context learning for this task. Overall, our results establish test-time thinking as a flexible and promising direction for improving the latent generalization of LMs. --- ### The power of context: Random Forest classification of near synonyms. A case study in Modern Hindi Authors: Jacek Bąkowski Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01425v1 Synonymy is a widespread yet puzzling linguistic phenomenon. Absolute synonyms theoretically should not exist, as they do not expand language's expressive potential. However, it was suggested that even if synonyms denote the same concept, they may reflect different perspectives or carry distinct cultural associations, claims that have rarely been tested quantitatively. In Hindi, prolonged contact with Persian produced many Perso-Arabic loanwords coexisting with their Sanskrit counterpart, forming numerous synonym pairs. This study investigates whether centuries after these borrowings appeared in the Subcontinent their origin can still be distinguished using distributional data alone and regardless of their semantic content. A Random Forest trained on word embeddings of Hindi synonyms successfully classified words by Sanskrit or Perso-Arabic origin, even when they were semantically unrelated, suggesting that usage patterns preserve traces of etymology. These findings provide quantitative evidence that context encodes etymological signals and that synonymy may reflect subtle but systematic distinctions linked to origin. They support the idea that synonymous words can offer different perspectives and that etymologically related words may form distinct conceptual subspaces, creating a new type of semantic frame shaped by historical origin. Overall, the results highlight the power of context in capturing nuanced distinctions beyond traditional semantic similarity. --- ### EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation Authors: Abhishek Saroha, Huajian Zeng, Xingxing Zuo, Daniel Cremers, Xi Wang Published: 2026-04-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.01421v1 Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the lack of explicit physical reasoning in existing generative models. We present EgoFlow, a flow-matching framework that synthesizes realistic and physically plausible trajectories conditioned on multimodal egocentric observations. EgoFlow employs a hybrid Mamba-Transformer-Perceiver architecture to jointly model temporal dynamics, scene geometry, and semantic intent, while a gradient-guided inference process enforces differentiable physical constraints such as collision avoidance and motion smoothness. This combination yields coherent and controllable motion generation without post-hoc filtering or additional supervision. Experiments on real-world datasets HD-EPIC, EgoExo4D, and HOT3D show that EgoFlow outperforms diffusion-based and transformer baselines in accuracy, generalization, and physical realism, reducing collision rates by up to 79%, and strong generalization to unseen scenes. Our results highlight the promise of flow-based generative modeling for scalable and physically grounded egocentric motion understanding. --- ### Cost-Efficient Estimation of General Abilities Across Benchmarks Authors: Michael Krumdick, Adam Wiemerslage, Seth Ebner, Charles Lovering, Chris Tanner Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01418v2 Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM performance is often sufficiently explained by a small set of latent factors, or abilities. This suggests the potential for more efficient and principled benchmarking, but it remains difficult to compare the quality of different methods. Motivated by predictive validity, we argue that the quality of a benchmarking framework should be grounded in how efficiently it enables the prediction of model performance on unseen tasks. To analyze this objective, we collect the "Wide-scale Item Level Dataset" (WILD), a dataset of item-model response pairs, comprising evaluations of 65 models on 109,564 unique items spanning 163 tasks drawn from 27 datasets. This dataset enables the first analysis of how different techniques can predict a model's performance on a large, diverse collection of unseen tasks under different budget constraints. We demonstrate that combining a modified multidimensional item response theory (IRT) model with adaptive item selection driven by optimal experimental design can predict performance on 112 held-out benchmark tasks with a mean absolute error (MAE) of less than 7%, and can do so after observing only 16 items. We further demonstrate that incorporating cost-aware discount factors into our selection criteria can reduce the total tokens needed to reach 7% MAE from 141,000 tokens to only 22,000, an 85% reduction in evaluation cost. --- ### Cost-Efficient Estimation of General Abilities Across Benchmarks Authors: Michael Krumdick, Adam Wiemerslage, Seth Ebner, Charles Lovering, Chris Tanner Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01418v1 Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM performance is often sufficiently explained by a small set of latent factors, or abilities. This suggests the potential for more efficient and principled benchmarking, but it remains difficult to compare the quality of different methods. Motivated by predictive validity, we argue that the quality of a benchmarking framework should be grounded in how efficiently it enables the prediction of model performance on unseen tasks. To analyze this objective, we collect the "Wide-scale Item Level Dataset" (WILD), a dataset of item-model response pairs, comprising evaluations of 65 models on 109,564 unique items spanning 163 tasks drawn from 27 datasets. This dataset enables the first analysis of how different techniques can predict a model's performance on a large, diverse collection of unseen tasks under different budget constraints. We demonstrate that combining a modified multidimensional item response theory (IRT) model with adaptive item selection driven by optimal experimental design can predict performance on 112 held-out benchmark tasks with a mean absolute error (MAE) of less than 7%, and can do so after observing only 16 items. We further demonstrate that incorporating cost-aware discount factors into our selection criteria can reduce the total tokens needed to reach 7% MAE from 141,000 tokens to only 22,000, an 85% reduction in evaluation cost. --- ### ReFormeR: Learning and Applying Explicit Query Reformulation Patterns Authors: Amin Bigdeli, Mert Incesu, Negar Arabzadeh, Charles L. A. Clarke, Ebrahim Bagheri Published: 2026-04-01 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2604.01417v1 We present ReFormeR, a pattern-guided approach for query reformulation. Instead of prompting a language model to generate reformulations of a query directly, ReFormeR first elicits short reformulation patterns from pairs of initial queries and empirically stronger reformulations, consolidates them into a compact library of transferable reformulation patterns, and then selects an appropriate reformulation pattern for a new query given its retrieval context. The selected pattern constrains query reformulation to controlled operations such as sense disambiguation, vocabulary grounding, or discriminative facet addition, to name a few. As such, our proposed approach makes the reformulation policy explicit through these reformulation patterns, guiding the LLM towards targeted and effective query reformulations. Our extensive experiments on TREC DL 2019, DL 2020, and DL Hard show consistent improvements over classical feedback methods and recent LLM-based query reformulation and expansion approaches. --- ### Adaptive Stopping for Multi-Turn LLM Reasoning Authors: Xiaofan Zhou, Huy Nguyen, Bo Yu, Chenxi Liu, Lu Cheng Published: 2026-04-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.01413v3 Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by iteratively retrieving information, reasoning, or acting, but introduce a key challenge: \textbf{When should the model stop?} Existing approaches rely on heuristic stopping rules or fixed turn budgets and provide no formal guarantees that the final prediction still contains the correct answer. This limitation is particularly problematic in high-stakes domains such as finance and healthcare, where unnecessary turns increase cost and latency, while stopping too early risks incorrect decisions. Conformal prediction (CP) provides formal coverage guarantees, but existing LLM-CP methods only apply to a single model output and cannot handle multi-turn pipelines with adaptive stopping. To address this gap, we propose Multi-Turn Language Models with Conformal Prediction (MiCP), the first CP framework for multi-turn reasoning. MiCP allocates different error budgets across turns, enabling the model to stop early while maintaining an overall coverage guarantee. We demonstrate MiCP on adaptive RAG and ReAct, where it achieves the target coverage on both single-hop and multi-hop question answering benchmarks while reducing the number of turns, inference cost, and prediction set size. We further introduce a new metric that jointly evaluates coverage validity and answering efficiency. --- ### Adaptive Stopping for Multi-Turn LLM Reasoning Authors: Xiaofan Zhou, Huy Nguyen, Bo Yu, Chenxi Liu, Lu Cheng Published: 2026-04-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.01413v2 Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by iteratively retrieving information, reasoning, or acting, but introduce a key challenge: \textbf{When should the model stop?} Existing approaches rely on heuristic stopping rules or fixed turn budgets and provide no formal guarantees that the final prediction still contains the correct answer. This limitation is particularly problematic in high-stakes domains such as finance and healthcare, where unnecessary turns increase cost and latency, while stopping too early risks incorrect decisions. Conformal prediction (CP) provides formal coverage guarantees, but existing LLM-CP methods only apply to a single model output and cannot handle multi-turn pipelines with adaptive stopping. To address this gap, we propose Multi-Turn Language Models with Conformal Prediction (MiCP), the first CP framework for multi-turn reasoning. MiCP allocates different error budgets across turns, enabling the model to stop early while maintaining an overall coverage guarantee. We demonstrate MiCP on adaptive RAG and ReAct, where it achieves the target coverage on both single-hop and multi-hop question answering benchmarks while reducing the number of turns, inference cost, and prediction set size. We further introduce a new metric that jointly evaluates coverage validity and answering efficiency. --- ### Test-Time Scaling Makes Overtraining Compute-Optimal Authors: Nicholas Roberts, Sungjun Cho, Zhiqi Gao, Tzu-Heng Huang, Albert Wu, Gabriel Orlanski, Avi Trost, Kelly Buchanan, Aws Albarghouthi, Frederic Sala Published: 2026-04-01 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2604.01411v1 Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling laws, such as Chinchilla, do not address. We present Train-to-Test ($T^2$) scaling laws that jointly optimize model size, training tokens, and number of inference samples under fixed end-to-end budgets. $T^2$ modernizes pretraining scaling laws with pass@$k$ modeling used for test-time scaling, then jointly optimizes pretraining and test-time decisions. Forecasts from $T^2$ are robust over distinct modeling approaches: measuring joint scaling effect on the task loss and modeling impact on task accuracy. Across eight downstream tasks, we find that when accounting for inference cost, optimal pretraining decisions shift radically into the overtraining regime, well-outside of the range of standard pretraining scaling suites. We validate our results by pretraining heavily overtrained models in the optimal region that $T^2$ scaling forecasts, confirming their substantially stronger performance compared to pretraining scaling alone. Finally, as frontier LLMs are post-trained, we show that our findings survive the post-training stage, making $T^2$ scaling meaningful in modern deployments. --- ### Assessing Pause Thresholds for empirical Translation Process Research Authors: Devi Sri Bandaru, Michael Carl, Xinyue Ren Published: 2026-04-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.01410v2 Text production (and translations) proceeds in the form of stretches of typing, interrupted by keystroke pauses. It is often assumed that fast typing reflects unchallenged/automated translation production while long(er) typing pauses are indicative of translation problems, hurdles or difficulties. Building on a long discussion concerning the determination of pause thresholds that separate automated from presumably reflective translation processes (O'Brien, 2006; Alves and Vale, 2009; Timarova et al., 2011; Dragsted and Carl, 2013; Lacruz et al., 2014; Kumpulainen, 2015; Heilmann and Neumann 2016), this paper compares five approaches for computing these pause thresholds, and suggest and evaluate a novel method for computing Production Unit Breaks. ---