Multiagent Systems
Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas
Yefei Zhang and Yuxuan Zhao
Spatial public goods models show that prescribed movement toward richer locations can generate spatial patterns. We ask how such patterns emerge when
agents learn where to move and how learning rates shape their consequences for collective welfare. Fixed populations of cooperators and defectors independently learn movement policies using tabular Q-learning and local observations. Cooperator learning generates clusters around resource peaks, while co-adaptation changes their strength and motion. At a fixed training budget, the largest welfare losses occur when cooperators learn at high rates and defectors at low rates. In part of this regime, learned policies also generate traveling bands supported by a shared directional preference. The conditions supporting travel change with further training, so these patterns reflect training history rather than an established asymptotic outcome. Across the tested learning-rate conditions with cooperator learning, mean collective welfare falls below random movement because increased crowding outweighs gains in resource benefit. Charging
agents for the crowding they impose on others during learning recovers much of the welfare loss in the tested conditions. These results connect learning rates to the emergence and welfare costs of spatial organization driven by individual rewards.
Read the full abstract ▾
Computer Vision
Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance
Amirhossein Zamani, Arianna Rampini and Bruno Roy
Recent motion generative models have demonstrated strong capabilities in synthesizing physically plausible character motion, but often overlook established animation principles used by professional animators to ground and design their animation work. Understanding and incorporating these principles into motion generative pipelines is essential for producing motions that serve not only physically grounded applications but also the needs of the character animation community. This enables the creation of characters that not only move in physically plausible ways but also feel alive, expressive, and engaging. To close this gap, we focus on the Exaggeration principle of animation and investigate how it can be incorporated into modern motion generative pipelines to produce more expressive character motions. To this end, we introduce a framework that operates at two stages of existing motion generative pipelines. The first stage introduces exaggeration during training, where we perform supervised fine-tuning of pre-trained text-to-motion models on our curated exaggeration
dataset. The second stage operates at inference time, where we: (i) introduce a mathematical formulation of exaggeration based on dynamic movement primitives (DMPs); and (ii) leverage this formulation as an exaggeration guidance signal to guide existing
diffusion and flow-matching text-to-motion generation models toward exaggerated motion without additional training. Through qualitative and quantitative evaluations against three strong motion generation models, we show that our methods generate more exaggerated and expressive motions while preserving neutral reference motion intent and physical plausibility.
Read the full abstract ▾
Artificial Intelligence
Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems
Saisab Sadhu, Aadit Sengupta, Vinay kumar Sankarapu et al. (+1 more)
Large
language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it is given. We test this directly across five models and 20 regulatory and platform-policy domains: delete, swap, or negate the governing rule while holding the case fixed, and check whether the verdict changes (OCS) or the model's internal representation of compliance shifts at all (ICS-delta). Neither moves much: models' verdicts are often invariant to substantial perturbations of the supplied rule, and the guard model, evaluated here under a custom-rule adaptation of its native taxonomy, is the least rule-sensitive and least accurate of the five, barely above chance (51%, versus 90-92% for general-purpose models). This reflects easy cases more than blanket neglect: on cases where deleting the rule changes a previously correct model prediction, models do track it closely. Neither better prompting nor direct intervention on the model's internal representations closes this gap. Accuracy alone does not establish that a compliance verdict is grounded in the supplied rule.
Read the full abstract ▾
All authors Saisab Sadhu, Aadit Sengupta, Vinay kumar Sankarapu, Pratinav Seth
Data Structures and Algorithms
The Geometry of Hierarchical Navigation: Accuracy and Query Cost for Point Process Input
Shankar Bhamidi, Souvik Dhara, Lars Schroeder et al. (+1 more)
Large-scale information
retrieval systems, including
retrieval-augmented generation (RAG) and recommendation engines, widely use multi-layered hierarchical data structures for ultra-fast approximate nearest-neighbor search in high-dimensional vector spaces. However, the
geometric conditions that ensure accurate and efficient greedy navigation remain poorly understood. In this work, we study the efficiency of greedy navigation on a hierarchy of proximity graphs constructed from \(n\) data points on the \(d\)-dimensional
torus~$\mathbb{T}^d$. We identify a deterministic coverage condition under which, given any query $q\in \mathbb{T}^d$, greedy search returns a point within $(1+\varepsilon)$-factor of the distance to the closest point. This coverage property holds with high probability when the data is distributed as a homogeneous Poisson process, a Hermitian determinantal process, or a bounded-density Cox process, as long as $d = o(\log n/\log \log n)$. Under the same assumptions, the expected number of greedy hops for a fixed query is \(O\!\left(\exp\!\left(\tfrac12 d\log d+O(d)\right)\log n\right)\), yielding logarithmic expected hop count in fixed dimension.
Read the full abstract ▾
All authors Shankar Bhamidi, Souvik Dhara, Lars Schroeder, Clara Stegehuis
Computer Vision
Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
Xingwu Zhang, Duanyang Du, Huiling Zhu et al. (+5 more)
A single
multimodal large
language model (MLLM) struggles to excel simultaneously at detection, localization, description, and
reasoning in
multimodal industrial anomaly understanding (MM-IAU). We show that in-domain training does not close this gap. On MMAD, a widely adopted MM-IAU
benchmark, trained specialists reach at most 75.5% accuracy in defect localization, against 92.3% for human experts, and even detect anomalies less accurately than their untrained base model. Meanwhile, different MLLMs offer complementary strengths but share this weakness in fine-grained perception, so combining them alone cannot remove it. We therefore propose SiGMA, a spatially grounded multi-
agent framework that divides labor between heterogeneous MLLM
agents and a dedicated visual defect expert. A
multimodal searcher supplies industrial knowledge and normal references, the defect expert turns query-reference comparison into calibrated anomaly evidence, and a label-free reliability controller weighs each source by task-wise competence and query-level evidence quality. SiGMA reaches 85.2% average accuracy on MMAD, 4.0% above the strongest trained specialist and Gemini-2.5-Pro and within 1.5% of human experts. Even with three
agents of at most 9B parameters, it reaches 84.4%, and new MLLMs join without retraining.
Read the full abstract ▾
All authors Xingwu Zhang, Duanyang Du, Huiling Zhu, Jiayue Dai, Yixiao Liu, Guozhi Liu, Zhihan Zhang, Zijun Long
Computer Vision
BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion
Ozgur Kara, Yujia Chen, Daniel Watson et al. (+4 more)
Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static paradigm cannot adapt to different resource constraints at inference time, and yields suboptimal quality-cost tradeoff by devoting the same effort to both plain backgrounds and intricate details. We propose BudgetPix, an adaptive tokenization framework that dynamically allocates compute based on visual complexity and spatial layout, enabling flexible computational budgeting at inference time. BudgetPix comprises three key components: (1) an adaptive encoder that maps a fixed-size image to a variable-length
token sequence using an
entropy-guided quadtree alongside a multi-scale patch embedder; (2) a scale-aware decoder reconstructs fixed-resolution images from multi-scale
token sets; and (3) a flexible training and sampling schedule that enables pixel-space denoisers to operate across variable
token counts. BudgetPix seamlessly integrates with existing pixel-space
diffusion architectures, enabling a single checkpoint to be operated at a wide range of compute budgets. Evaluated on text-to-image generation, BudgetPix matches the fidelity of MiniT2I-L at $512^2$ and PixelDiT at $1024^2$ using just 25% of the original compute budget. In class-conditional generation using a MeanFlow backbone, BudgetPix requires merely 60% of the full compute budget to produce images with near-zero quality degradation, observing a marginal 0.8-point increase in FID. Comprehensive assessments by human and VLM judges confirm that BudgetPix establishes a significantly improved quality-efficiency tradeoff over prior budget-adaptive baselines. More details are available at our project page: https://karaozgur.com/BudgetPix
Read the full abstract ▾
All authors Ozgur Kara, Yujia Chen, Daniel Watson, David Forsyth, James Matthew Rehg, Wen-Sheng Chu, Du Tran
Artificial Intelligence
A Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space
Antal Jakovác and András Telcs
Learning and problem solving depend critically on the structure of internal representations. While many modern data-driven artificial systems achieve strong predictive performance, their learned representations often lack explicit structure for expressing abstraction, invariance, and task-relevant regularities. We propose a minimal structural framework in which representational operations relevant to problem solving, such as context formation, invariance recognition, representative selection, abstraction, and procedural reuse, are made explicit. The central notion is that of a context, formalized as a partition of a subset of an underlying state space, which fixes the distinctions, granularity, and form in which a problem can be posed. Within this setting, invariance recognition and representative selection are treated as fundamental representational operations. The framework is realized as a Knowledge Space composed of two coupled graph structures: a Concept Graph that hosts constructed and refined concepts, and a Procedure Graph that encodes typed operations over representations. Together, these structures provide a minimal cognitive-representational
algebra for operating on representations without assuming sophisticated inference, learning, control, perception, or motor mechanisms. Using simple illustrative examples and a finite weak-solver demonstration, we show that appropriate representational organization can simplify the form and scope of admissible regularities, even when problem solving is carried out by a fixed and limited solver. The contribution of the paper is structural rather than algorithmic: it identifies representational prerequisites for abstraction, invariance, and procedural reuse in problem solving, and states explicit success and failure conditions for the weak-solver setting.
Read the full abstract ▾
Computer Vision
From What to Which: Decoding Modifier Grounding in Frozen MLLMs
Barbara Toniella Corradini, Caterina Gallegati, Ludovica Genovese et al. (+1 more)
As
Multimodal Large
Language Models (MLLMs) can describe increasingly complex visual scenes,
token-level grounding becomes crucial. Yet, when an MLLM generates "the yellow banana on the left", established grounding approaches focus on what is in the image ("banana"), overlooking
tokens that help describe which instance is meant ("yellow", "left"). In this work, we ask whether frozen MLLM representations contain decodable grounding information about the referred instance across generated
tokens, extending to modifiers such as attributes, spatial expressions, and relational/action terms. To address this question, we introduce OTTER, a lightweight supervised probe over frozen MLLM representations that uses Optimal Transport (OT) to align generated
tokens with visual regions and produce compact grounding maps. Our results show that (i) instance-discriminative visual information can be decoded from modifier
tokens, with the clearest evidence for spatial terms, but (ii) is not confined to them, as contextualized object nouns also carry referential information; (iii) the recovered grounding remains informative under context perturbations, while selected regions remain relevant to generation; and (iv) the learned OT-based grounding extends beyond the controlled setting to free generation and cross-
dataset transfer.
Read the full abstract ▾
All authors Barbara Toniella Corradini, Caterina Gallegati, Ludovica Genovese, Vittorio Murino
Artificial Intelligence
Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
Zheng Huang, Sansheng Cao, Enpei Zhang et al. (+7 more)
Understanding large
language model (LLM)
reasoning requires looking beyond behavioral performance to examine how
reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional
brain networks, we investigate small-world connectivity as a structural signature of LLM
reasoning. We construct functional graphs from
attention-head activation similarities and find that a higher small-world index (SWI), capturing local clustering and short global paths, consistently correlates with better fluid
reasoning performance across models and training checkpoints. Since local clustering is central to small-world organization, we further examine how heads important for model performance connect within and across communities. We find that these heads tend to have a larger share of connection weight within their own communities (high core scores) and a more concentrated weight distribution across communities (low bridge scores). These observations motivate the hypothesis that high core and low bridge scores serve as structural indicators of head importance for
reasoning capability. We validate this hypothesis through
pruning, introducing Small-World Allocation (SWA), a hierarchical sparsity allocation method guided by these scores. Across six LLMs, SWA better preserves small-world organization and model performance than competing allocation strategies, reducing WikiText perplexity by up to 20%. Together, these findings identify small-world functional connectivity as a measurable signature of LLM
reasoning performance, offering a structural perspective that complements behavioral evaluation.
Read the full abstract ▾
All authors Zheng Huang, Sansheng Cao, Enpei Zhang, Weikang Qiu, Elynn Chen, Xiang Zhang, Yaoqing Yang, Rex Ying, Dawei Zhou, Yujun Yan
Artificial Intelligence
Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
Saurabh Mathur, Sahil Sidheekh, Bhavan Vasu et al. (+4 more)
Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic
reasoning, by expressing dependencies as weighted compositional rules. However, inducing them from data remains fundamentally hard, bottlenecked by the combinatorial explosion of symbolic search spaces. LLMs have recently emerged as powerful hypothesis generators, but when used in isolation, they lack the capacity to do systematic inductive
reasoning needed to reliably synthesize valid programs that fit complex relational distributions. We introduce grasp (Gradient-boosted Synthesis of Probabilistic logic programs), a neurosymbolic framework that casts relational structure learning as functional gradient boosting in which the weak learner is a first-order rule and the intractable inner search is delegated to an LLM proposal oracle. We evaluate grasp on four relational
benchmarks spanning molecular toxicity prediction (Tox21), mutagenesis, and citation matching (Cora), and show that it improves over purely symbolic, neural, and LLM-based baselines, while producing interpretable weighted rule ensembles. By replacing combinatorial search with gradient-guided LLM hypothesis generation, grasp retains boosting guarantees without sacrificing the transparency of symbolic outputs.
Read the full abstract ▾
All authors Saurabh Mathur, Sahil Sidheekh, Bhavan Vasu, Farbod Tavakkoli, Prasad Tadepalli, Kristian Kersting, Sriraam Natarajan
Information Retrieval
Compact and Efficient Indexes for Learned Sparse Retrieval
Franco Maria Nardini, Luca Rizzo, Cosimo Rulli et al. (+1 more)
This paper investigates how to substantially reduce the
memory footprint of learned sparse
retrieval indexes without sacrificing the efficiency of state-of-the-art
retrieval data structures. Building on SEISMIC, we revisit both levels of its design: the inverted index used to select candidates and the forward index used to score them. For the inverted index, we replace costly per-block summaries with medoids, namely existing documents elected as block representatives, collapsing the per-block metadata from a sparse vector to a single document identifier. For the forward index, we compress both components and values. We reorder the vocabulary to place co-occurring components closer together and encode the resulting $\Delta$-gaps with DOTPACKING8, a SIMD-friendly bit-packing scheme that fuses decompression with dot-product evaluation; values are quantized with compact per-component 4-bit codebooks fitted to each component's distribution. We further introduce JUMPDOT, a blocked dot-product kernel tailored for queries that contain only a few non-zero entries. Our forward-index compression is independent of SEISMIC and can be plugged into any system relying on forward-index-based scoring, as we demonstrate by integrating it into KANNOLO. A comprehensive evaluation on MS MARCO with three state-of-the-art learned sparse encoders shows that our solutions markedly improve the speed-space trade-off of learned sparse
retrieval: at equal accuracy, our indexes answer queries up to 5.3x faster than the best competitor while using about 3x less
memory, and in the most
memory-constrained regime, they remain up to 1.9x faster while using up to 3.9x less
memory.
Read the full abstract ▾
All authors Franco Maria Nardini, Luca Rizzo, Cosimo Rulli, Rossano Venturini
Computer Vision
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Dahyun Chung, Siyoon Jin, Hyunwook Choi et al. (+5 more)
Egocentric world models predict first-person observations conditioned on an
agent's actions, but most focus on a single
agent. Real embodied settings often involve multiple
agents that act and interact within a shared environment. Existing multi-
agent world models rely on coarse actions like locomotion, camera control, or discrete commands, leaving fine-grained embodied interactions underexplored. We formulate multi-
agent egocentric world modeling as synchronized ego-stream generation for multiple
agents interacting through fine-grained actions in a shared world. This requires cross-view action consistency, shared-environment consistency, and consistent propagation of interaction-induced state updates. We propose Multi-
agent Egocentric World Model (ME-World), which jointly denoises multiple ego streams in a shared
token sequence, conditions each stream on all
agents' target-view poses, and grounds generation with shared environment
memory. We train and evaluate on real and synthetic multi-
agent data and introduce shared-world consistency metrics for environment, update, and identity consistency. Experiments show ME-World improves shared-world consistency, action control, identity preservation, and
video quality over existing methods.
Read the full abstract ▾
All authors Dahyun Chung, Siyoon Jin, Hyunwook Choi, Honggyu An, Junyoung Seo, Hyunsung Kim, Seung Wook Kim, Seungryong Kim
Artificial Intelligence · Cross-listed from hep-ph
Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery
Xun Chen, Weiyao Ke, Yu-Gang Ma et al. (+2 more)
Machine learning (ML) in high-energy nuclear physics (HENP) is entering a new stage in which physical knowledge is incorporated more directly into data analysis, simulation, and physics inference. This mini-review focuses on developments that have matured in the past several years. Whereas earlier applications emphasized event classification, pattern recognition, and surrogate models for selected observables, recent work has moved toward physics-integrated workflows: calibrated
Bayesian extraction of QCD matter properties, dense-matter equation-of-state inference from heavy-ion and
neutron-
star data, generative event modeling, neural unfolding of weak physical signals, differentiable inverse solvers, gauge-equivariant and
diffusion-based
lattice-field samplers, and neural reconstruction of model functions in holographic QCD. We survey recent applications of ML in heavy-ion collisions,
neutron-
star physics,
lattice QFT, and holographic or continuum QCD. The emphasis is not on ML architectures alone, but on how they enter concrete physics workflows, how physical constraints such as
symmetries, conservation laws, causality, thermodynamic stability, and
topology are imposed, and how uncertainty quantification and validation determine whether an AI-assisted result can support a reliable physics conclusion.
Read the full abstract ▾
All authors Xun Chen, Weiyao Ke, Yu-Gang Ma, Long-Gang Pang, Kai Zhou
Artificial Intelligence
One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
Seyedarmin Azizi, Erfan Baghaei Potraghloo and Massoud Pedram
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in
agent systems as guardrails: the component that reads a proposed tool call or incoming message and decides whether to allow it. We evaluate seven open-weight models in that role and report the two error directions separately: a fail-open error allows a prohibited action and is a vulnerability; a fail-closed error blocks a permitted one and is only a cost. On
prompt-injection, jailbreak and toxic-content screening, accuracy at the allow-or-block decision ranges from 36% to 72% against a chance level of 50%. A low error rate in one direction only reflects which answer a model defaults to: one allows nearly everything, another blocks nearly everything. On a synthetic suite of
agent tool calls, six lines of server log text that say nothing about the policy raise a gate's fail-open rate from 0% to 63% on a policy it otherwise decides correctly. Giving the permissive option a misleading name, with its definition and the judged text untouched, raises that rate to between 93% and 100% on the four models that place the label in their input. Every defense we tested is defeated, either by an attacker who targets its mechanism or by attacker-controlled text. Escalating the least confident decisions does not help either: a decision an attack has reversed is no less confident than the one it replaced. Parsing each policy field into a typed value does eliminate one attack, but it also makes the model unnecessary: a deterministic rule over those values reaches 100% accuracy on all six policies. These models can reduce how many cases reach a reviewer, but on this evidence they should not be the component that decides. Code is available at https://github.com/ArminAzizi98/option-channel-attack.
Read the full abstract ▾
Software Engineering
TestPrism: Rethinking Test Evaluation Beyond a Single Reference
Han Li, Lingxiang Hu, Jiacheng Huang et al. (+6 more)
Large
language model (LLM) coding
agents have advanced test generation across diverse programming tasks. However, the common practice of evaluating tests against a single reference solution overlooks alternative valid implementations and can overstate test quality. We introduce TestPrism, comprising 300 test tasks from 17 sources and 3000 candidate implementations, evenly split between valid and invalid solutions. Its primary metric, Joint Success Function, requires the generated tests to fail on the initial program state, accept every valid candidate, and reject every invalid candidate. Across fourteen baseline coding
agent configurations, Joint Success Function reaches only 28.00%, whereas single reference success reaches 59.67%. Our analysis reveals missed behaviors, unsupported assertions, and faulty test construction. To address these weaknesses, we introduce TestHelix, which combines heterogeneous synthesis of test and repair pairs with peer cross validation and recursive self improvement (RSI). Across two models, TestHelix improves Joint Success Function by 8.67 to 9.00 percentage points over the native harness comparators in the TestHelix evaluation
Read the full abstract ▾
All authors Han Li, Lingxiang Hu, Jiacheng Huang, Ziqian Jiang, Jingkai Luo, Wei Gao, Yunfan Tan, Zun Wang, Jiaheng Liu
Robotics
PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies
Yu Liu, Hetian Guo, Tianlv Huang et al. (+11 more)
Learning to predict how the world evolves can provide
vision-
language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future representation is modeled and how it conditions action generation. We introduce PLaW-VLA, which models task-relevant future states in a pretrained prediction-oriented representation space, reducing the need to predict control-irrelevant visual details. Built on a Mixture-of-
Transformers architecture, PLaW-VLA conditions action generation on observation history, current task semantics, and predicted future states through structured causal
attention. Experiments show a +11.8 percentage-point (pp) gain over reactive policies on RoboTwin Hard Horizon III and a +1.77 pp gain over reconstruction-oriented latent prediction on zero-shot LIBERO-Plus, supporting improved long-horizon control and generalization under distribution shift, respectively. By avoiding low-level visual reconstruction, PLaW-VLA lowers the burden of future prediction, enabling a lightweight latent world model with parallel future prediction and about 1/19 the inference latency of generative world-action modeling at comparable policy performance.
Read the full abstract ▾
All authors Yu Liu, Hetian Guo, Tianlv Huang, Ziyi Cai, Wudi Chen, Hantang Wang, Qiutong Liu, Yingzhi Peng, Wei Han, Peijun Tang, Jianan Wang, Zipei Fan, Zhiyuan Zha, Xuan Song
Computer Vision
Slot3R: Set-Associative Spatial Memory for Streaming 3D Reconstruction
Xiyuan Zhang, Yanming Yang, Kaiyuan Xu et al. (+2 more)
Streaming 3D reconstruction must preserve evidence from each frame while processing an expanding scene online. Spatial
memory is a natural fit because it organizes history by reconstructed 3D location. Yet Point3R uses spatial proximity both to associate a new observation with an existing
memory entry and to decide whether to fuse it, conflating co-location with state identity. Because pointers summarize image patches, nearby pointers may encode distinct surfaces, viewpoints, or visibility conditions; averaging them can destroy complementary evidence before later frames disambiguate it. We argue that location should determine address, not whether observations must merge. Slot3R realizes this principle as a training-free, set-associative retrofit that lets multiple states coexist at a shared address while keeping the pretrained Point3R backbone frozen. A bounded sparse readout further decouples persistent storage from per-frame decoder access. At 300-500 sampled frames, Slot3R reduces Point3R's point-cloud accuracy error (Acc) by 57.1%-63.1% on 7Scenes and 64.0%-72.0% on NeuralRGBD, lowers Sim(3)-aligned absolute trajectory error (ATE) on all three pose
benchmarks, and remains competitive on
video-depth estimation. It completes all evaluated settings from 600 to 1000 sampled frames at about 19 FPS under the same protocol, whereas Point3R and InfiniteVGGT run out of
memory at 800 frames and beyond.
Read the full abstract ▾
All authors Xiyuan Zhang, Yanming Yang, Kaiyuan Xu, Ruibo Li, Chi Zhang
Artificial Intelligence · Cross-listed from q-bio.GN
Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants
Pratik Dutta, Matthew B. Obusan, Max Chao et al. (+3 more)
Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet their functional interpretation remains a central open problem in genomic medicine. Large
language models prompted to interpret such variants routinely hallucinate transcription factor (TF) binding changes, fabricate experimental support, and assign biological significance to statistically negligible signals. We present ARGUS (Agentic Regulatory Genomics for an Uncertainty-aware Scientist), which strictly separates deterministic biological computation from LLM-mediated
reasoning. ARGUS wraps 458 DNABERT-based TF binding models in a hypothesis-directed investigation loop where a planner selects evidence sources based on current uncertainty, a verifier deterministically interprets each observation, and intermediate results change the investigation path. On variant rs6983267 at the 8q24 cancer risk locus, the same planner produces four divergent trajectories for four TFs. FOXA1 is rescued in 3 steps when real ADASTRA allele-specific binding data (15 experiments, FDR = 0.030) reveals a model false negative masked by saturation. KLF6 traverses 8 steps across ADASTRA, JASPAR motif analysis, and ENCODE cCRE regulatory annotation before abstaining due to mixed indirect evidence. RAD21 abstains in 8 steps after ADASTRA returns a coverage-qualified but nonsignificant allelic test (5 experiments, FDR = 0.65), and SP1, which shares FOXA1's saturated retained prediction, abstains because no direct experimental evidence exists at this locus. All observations come from real ADASTRA, JASPAR, and ENCODE cCRE queries; none are simulated. A comparison of fixed-priority and LLM-mediated planning shows that the LLM planner reaches identical verdicts with fewer tool calls by declining evidence that cannot resolve the claim under test.
Read the full abstract ▾
All authors Pratik Dutta, Matthew B. Obusan, Max Chao, Rekha Sathian, Nimisha Papineni, Ramana V. Davuluri
Robotics
Toward Lunar Legged Robots: Field Deployment Lessons at LUNA
Adrian Fuhrer, Joseph Church, Oliver Fischer et al. (+6 more)
Legged
robots are promising candidates for future lunar surface missions because they can traverse steep, loose, and obstacle-rich terrain that challenges conventional wheeled rovers. However, readiness for lunar deployment is limited by uncertainties in foot-regolith interaction, dust generation, illumination-driven perception degradation, and operational constraints. This paper reports lessons from the 2025 LUNA analogue campaign, where ANYmal-D and Magnecko traversed loose regolith simulant and crater-like terrain and collected long-horizon navigation and visual-inertial data under challenging lighting. We show that quadrupedal
robots can traverse regolith simulant, but performance is affected by sinkage and slip, dust-generating contacts, and perception failures caused by overexposure, shadows, and low-texture regions. These results motivate tighter integration of regolith-aware locomotion policies, illumination-robust perception, repeatable analogue testing, and mission-level operational validation for future lunar legged
robots.
Read the full abstract ▾
All authors Adrian Fuhrer, Joseph Church, Oliver Fischer, William Talbot, Nicolas Faesch, Yannic Hofmann, Hendrik Kolvenbach, Yusuke Tanaka, Marco Hutter
Computation and Language
HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments
Haolin Yang, Jipeng Zhang, Zhiqiang Qian et al. (+4 more)
Text-to-SQL models are commonly trained to map questions directly to static queries, whereas real-world database
agents operate through stateful, multi-turn interaction with live databases – inspecting schemas, executing probe queries, diagnosing errors, and revising hypotheses. This creates a critical train-deploy mismatch, as the execution harness that mediates this interaction is introduced only at inference time. To bridge this gap, we propose HarnessSQL, a harness-native post-training framework that preserves the full interaction structure throughout both supervised fine-tuning and reinforcement learning. HarnessSQL builds isolated, executable database environments paired with hidden execution oracles, rolls out teachers directly inside the target SQL harness, and retains only verified trajectories for full-sequence SFT, followed by execution-reward RL. Across Spider 2.0-SQLite, HarnessSQL dramatically boosts the execution accuracy of compact models, raising Qwen3-8B from 15.5% to 45.2% and Qwen3-14B from 22.2% to 54.8%, while transferring effectively to out-of-distribution interactive
benchmarks such as BIRD-Interact and LiveSQLBench. Our findings demonstrate that training database
agents directly within their execution harness is essential for mastering complex, long-horizon database workflows.
Read the full abstract ▾
All authors Haolin Yang, Jipeng Zhang, Zhiqiang Qian, Jian Xie, Shuaishuai Gong, Yike Guo, Sirui Han
Robotics
Walking on Roofs: Exploring the Potential of Walking Robots for Construction Work on Roofs
Bjoern-Felix Dettmar and Arne Roennau
This paper investigates the feasibility of deploying quadruped walking
robots for the automation of work in roof environments. While quadrupeds have demonstrated versatility across various domains, their large-scale deployment remains limited, partly due to lack of application-specific designs. Roof environments represent a novel and unexplored use case, combining high safety risks for human workers with repetitive, strenuous tasks that could benefit from robotic assistance. A dedicated test rig of a roof's surface was designed to evaluate the baseline performance of a commercial quadruped, the Unitree Go2, in this new environment. Experiments revealed that standard ball feet are inherently inadequate for locomotion on sloped roofs: slippage increased quadratically with incline angle, get-up and lie-down sequences were only possible on small inclines, and critical failures already occurred regularly on moderate inclines of 25{\deg}. This work provides the first systematic assessment of quadruped locomotion in roof environments, highlighting both the potential and the current limitations of this application and establishes a baseline for future research. Effective solutions will require a combination of task-oriented foot designs, advanced contact mechanics and environment-specific control strategies, such as reinforcement learning for roof-adapted gaits.
Read the full abstract ▾
Information Theory
Event-Native Immersive Communication for 6G: From Multimodal Streams to Event Beliefs
Yiyang Zhu, Li Wei and Chau Yuen
The development of
multimodal sensing capabilities is crucial for realizing immersive communications and enabling rich, natural remote interactions in future sixth-generation~(6G) communications. However, transmitting high-dimensional sensory streams places substantial pressure on wireless resources and leaves a fundamental question unresolved: what information about the underlying physical process should be preserved across wireless delivery? To address this issue, we establish an event-native immersive-communication framework in which a service-relevant physical event defines the communication object, while event beliefs represent the information available to transceiver
agents before and after wireless delivery. Based on this event-native framework, we further propose event-belief deficiency (EBD) to evaluate quality of experience (QoE) in immersive communications, which differs from the conventional normalized mean-squared error (NMSE), as NMSE can be insensitive to physically distinct procedures whose stream distortions lie in a similar range. For Gaussian event beliefs with mode-separable delivery over Rayleigh fading, we derive the log-det EBD, its induced received signal-to-noise ratio (SNR) threshold, the exact outage probability, and the required transmit SNR. Simulation results with a physics-driven source show that stream NMSE can remain nearly unchanged across physically distinct event procedures, whereas log-det EBD reliably reflects their event-level uncertainty. Relative to a mean-squared-error (MSE)-oriented interface, event-native delivery reduces normalized log-det EBD by up to $63.6\%$ and lowers the required average received SNR by $3.47$~dB under the evaluated outage constraint, substantiating the effectiveness of the proposed framework.
Read the full abstract ▾
Software Engineering
Cadence: Strategic Guidance for Coding Agents
Minxing Wang, He Ye, Earl T. Barr et al. (+1 more)
Runtime monitors are increasingly used to improve the reliability of LLM-based coding
agents by inspecting execution trajectories and delivering corrective guidance upon detecting misbehavior. However, their effectiveness remains limited by static guidance triggering schemes. Existing monitors rely either on fixed inspection intervals, missing timely guidance during severe misbehaviors while incurring unnecessary overhead during healthy execution, or on rigid heuristic rules, failing to detect complex
reasoning errors. To address these limitations, we propose Cadence, a dynamic monitoring framework that adaptively schedules inspections and delivers guidance according to the
agent's real-time execution health. Cadence consists of two core modules: a two-tier intervention module and an inspection scheduler. The intervention module delivers advisory-level guidance for normal executions and minor lapses, while providing replacement-level guidance for severe misbehaviors. Driven by the intervention level, the scheduler adjusts the inspection frequency by tightening supervision after replacement-level guidance and relaxing it after advisory-level guidance. Evaluated on 300 SWE-bench Lite tasks across two distinct
agents, mini-swe-
agent and Moatless, Cadence achieves the highest resolve rate among all evaluated monitors. Specifically, Cadence outperforms vanilla
agents by 25.33% (+76 resolved tasks) on mini-swe-
agent and 15.67% (+47 resolved tasks) on Moatless, while maintaining competitive
token efficiency compared to state-of-the-art baselines.
Read the full abstract ▾
All authors Minxing Wang, He Ye, Earl T. Barr, Yintong Huo
Computer Vision
DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception
Jinghua Hou, Zhe Liu and Hengshuang Zhao
Multimodal large
language models have made remarkable progress in bridging
vision and
language, facilitating various perception tasks essential for human-machine interaction, robotics, and autonomous driving. However, existing MLLM-based perception methods predominantly rely on text-based coordinate representation, which suffers from excessive
token overhead, or fixed-range quantization, which suffers from range and precision constraints, especially for 3D domains with unbounded spatial range and high localization accuracy requirements. To address these challenges, we propose a dynamic vector decoding method named DVD, which unifies the representation of 2D and 3D perception tasks. Specifically, we first transform diverse perceptual representation (i.e., 2D bounding boxes, 2D masks, and 3D bounding boxes) into 1D vector sequences, which are then mapped to compact discrete
tokens in the high-dimensional space. Then, a lightweight de-tokenizer enables seamless integration with MLLMs by decoding output
tokens back to original 2D and 3D perceptual representations. Extensive experiments on 2D and 3D perception
benchmarks including RefCOCO series, SUN-RGBD, KITTI, Hypersim, nuScenes demonstrate that DVD achieves superior performance in 2D and 3D tasks and reduces significantly the
token overhead and inference latency. DVD provides an efficient and general framework for integrating perception capabilities into MLLMs, overcoming the inherent limitations of existing methods.
Read the full abstract ▾
Machine Learning
AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift
Xinhua Miao, Bowei Yang and Zhengong Cai
Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral content, product launches, and user behavior degrade offline-trained models rapidly. Naive online learning recovers accuracy but incurs prohibitive per-step compute cost. We propose AdaptLSTM, an adaptive online framework that detects drift via validation-calibrated thresholds and applies selective, targeted updates. On the Alibaba Machine Trace, AdaptLSTM recovers 54% of Naive Online's improvement at 20% cost ($2.7\times$ efficiency, $p=0.002$ over 10 seeds). On the more volatile Container Trace, it achieves 96% at 20% cost ($4.8\times$ efficiency, $+75\%$ MAE reduction over Static). Unlike classical drift detectors (ADWIN, DDM, Page-Hinkley) which fail to trigger on regression-scale error streams, AdaptLSTM fires 42 times over 301 steps and outperforms matched-budget baselines. Wall-clock profiling shows $1.33\times$ throughput gain and 45% update-time reduction. The framework is model-agnostic: identical Pareto patterns hold for LSTM, GRU, and
Transformer backbones.
Read the full abstract ▾
Computer Vision
Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings
Youngtaek Oh, Qiyu Wu, Hiromi Wakaki et al. (+2 more)
Omnimodal
embeddings naturally involve both shared representations and modality-specific features across heterogeneous inputs. However, existing omnimodal
embedding methods often rely on a single shared parameter space over mixed-modality data, limiting structural separation between universal and modality-specific representations. To address this, we propose Syn-Omni, a unified framework for structured omnimodal adaptation with modality specialization and controlled cross-modal collaboration. Specifically, we introduce Orthogonal Modality-Expert LoRA (OME-LoRA), which decomposes adaptation into a shared LoRA path for universal semantics and modality-expert LoRA paths for modality-aware specialization. Furthermore, Progressive Synergy Routing (PSR) enables experts to first establish modality-specific priors, then gradually interact with other modality-experts for cross-modal synergy. Evaluated across 81 diverse tasks spanning image,
video, audio, and audiovisual modalities, Syn-Omni consistently outperforms omnimodal baselines, demonstrating the effectiveness of structured specialization and cross-modal progressive collaboration.
Read the full abstract ▾
All authors Youngtaek Oh, Qiyu Wu, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji
Logic in Computer Science
Universal Construction and Exact Self-Reproduction in Ternary McCulloch-Pitts Networks
Charles C. Norton
A fixed network of McCulloch-Pitts threshold units with weights in {-1,0,1} can hold other threshold networks in its state and run them: the state is a ring of banks of records, each record a unit of a stored network, and each step evaluates one record. We use such a network to carry out von Neumann's universal construction and self-reproduction exactly. As a cellular automaton keeps its rule, the fixed network keeps its weights, and what reproduces is a stored network. A constructor of 143 records reads the description of a network from its tape, builds that network in the next bank, copies the description onto the next tape and hands control to what it built; started on its own description, it rebuilds itself, weights included, in every generation. The scheme scales to a universal computer. A SUBLEQ computer of 17,598 ternary units, stored as 36,080 records and running a program of 27 instructions, builds any network that fits a bank and reproduces itself in the same way, at every word width from eight bits on; run directly, it emits the serialization of its own weights,
memory and tape. Integer pre-activations give every orbit a margin of 1/2, and replicating each unit r times multiplies it by r. That suffices against noise of any size on the pre-activations, but against von Neumann's output flips only below a threshold inversely proportional to the fan-in. These results are proved in Rocq.
Read the full abstract ▾
Sound
How Much Audio Is Left In An Embedding? An Inversion Audit Of Audio Encoders
Marios Glytsos and Brian McFee
Pretrained audio encoders are reused for downstream tasks that are often unknown when the encoder is trained, so their usefulness depends partly on which signal properties survive the pretext objective. We study this retained information through paired source reconstruction. Using a shared Stable Audio Open latent
diffusion decoder, we reconstruct five-second, 44.1-kHz stereo music from frozen representations produced by supervised classifiers (VGGish, ConvNeXt), an audio-text contrastive model (CLAP), and a waveform-reconstruction model (EnCodec). These objectives impose different pressures to preserve source detail, while their exposed interfaces vary substantially in temporal and spectral resolution. Evaluating on the Million Song
Dataset (MSD), we find clear differences in reconstructability across encoder families, while within encoder comparisons show improved recovery when finer temporal or spectral structure is exposed. Even compressed task oriented
embeddings support reconstructions that preserve measurable source specificity and high level musical content.
Read the full abstract ▾
Robotics
Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods
Eran Iceland, Alexander Tuisov, Oren Gal et al. (+2 more)
We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rather than introducing a new planner, we construct a unified
benchmark in which representative classical and learning-based methods face the same environments, motion constraints, information assumptions, and evaluation metrics. The test environment consists of planar domains populated with rotating sprinkler-like hazards that generate time-varying forbidden regions via sweeping angular sectors. Our results show a clear regime shift. In deterministic environments, classical planners achieve near-perfect success and higher-quality paths, though sometimes at the cost of substantial planning or replanning time. Under
stochastic obstacle dynamics, however, online search becomes strongly budget-sensitive: low budgets lead to frequent failure, while high budgets improve success at the cost of latency and longer trajectories. PPO-based policies, trained under the same scenario distribution, consistently outperform in latency, success rate, and path quality in these
stochastic regimes. Overall, the results indicate that uncertainty in obstacle
evolution, more than partial observability, is the dominant factor determining which planning paradigm is practically effective for the problem at hand.
Read the full abstract ▾
All authors Eran Iceland, Alexander Tuisov, Oren Gal, Ariel Barel, Alfred M. Bruckstein
Computation and Language
EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams
Heeseung Kim
Wearable augmented reality (AR) assistants are moving toward continuous real-world interaction, where they perceive the user's activity through first-person
video and audio and provide timely spoken guidance without being explicitly asked. While proactive
video assistants, spoken dialog systems, and egocentric task understanding have each advanced rapidly, existing systems do not address the joint problem of deciding when to speak and what to say from continuous first-person streams. We introduce EgoVoice, a framework for training and evaluating proactive egocentric spoken assistants. From HoloAssist
video recordings of real human instructors, we construct clean audio streams through source separation and
speech resynthesis, and convert each
video session into a format where the model must decide at each moment whether to remain silent or provide spoken guidance. We fine-tune an omni-modal LLM with our data, and further improve its proactive intervention behavior with direct preference optimization. Experiments across closed and open-source models show that existing systems rarely produce well-timed, meaningful proactive interventions, while EgoVoice yields clear improvements in intervention timing, content relevance, and human preference over the zero-shot backbone.
Read the full abstract ▾