Artificial Intelligence · Cross-listed from cs.CV
Kenta Watanabe, Atsuyuki Miyai, Mizuki Takenawa et al. (+2 more)
We present 360CityArena, a
benchmark for evaluating the urban exploration capabilities of
embodied agents within a photorealistic environment constructed from 360-degree
videos. Existing outdoor
benchmarks either lack sufficient photorealism or complexity, resulting in a considerable gap from real-world urban environments. 360CityArena is built on a realistic reconstruction of the Akihabara district in Tokyo, Japan, using 602 360-degree
video segments covering 85 streets, and consists of 175 meticulously human-crafted tasks. It encompasses three task categories: Environment Understanding, Path
Reasoning, and Spatial
Reasoning, covering fundamental abilities required for urban exploration, such as localization, landmark search, path planning, and relational spatial
reasoning, thereby enabling comprehensive evaluation in realistic urban scenes. Our evaluation using state-of-the-art LMM-based
agents shows that even the strongest model, Gemini 2.5 Flash, performs far below human level (human: 77.3% vs. Gemini 2.5 Flash: 17.1%), revealing substantial challenges that remain in city-scale
embodied navigation and
reasoning. 360CityArena provides a necessary and challenging testbed for photorealistic urban-district
navigation and spatial
reasoning.
Read the full abstract ▾
All authors Kenta Watanabe, Atsuyuki Miyai, Mizuki Takenawa, Kiyoharu Aizawa, Toshihiko Yamasaki
Artificial Intelligence
Three Generations of Healthcare IT: From the Digital Record to the Computable Care Process
Alexander Apartsin and Yehudit Aperstein
Objective. Healthcare IT is usually organized by the technologies it adopts. We instead organize it by the unit of information a system makes computable, and describe a computational layer whose object is patient-specific clinical intent. Approach. We give criteria for a computational layer, derive three (record, clinical state, and a proposed layer of intent), and formalize the Actionable Clinical Record (ACR) as the atomic object of the third layer. Discussion. The framework distinguishes prescribed, observed, and intended process; existing standards represent intent once it is structured but do not recover it from natural communication, the capability we localize. The ACR is complementary to FHIR workflow resources, guidelines, and process mining; a companion feasibility study illustrates tractability for one narrow subproblem. Conclusion. Computable clinical intent is a coherent research direction; the ACR, its readiness ladder, and an executable-correctness evaluation framework are reusable constructs for subsequent work to extend, evaluate, or falsify.
Read the full abstract ▾
Artificial Intelligence
Improving Generalization Robustness of Multimodal RLVR
Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng et al. (+11 more)
Reinforcement Learning with Verifiable Rewards (RLVR) makes
Multimodal Large
Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the
prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective. First, the binary verifier conflates format with content, so the reward signal cannot tell a wrong answer apart from a misformatted one. Second, the training distribution covers only a thin slice of the real-world
prompts that the model might meet at deployment, so policies that perform well on the training distribution can behave differently under unseen
prompts during test. Both failures call for a robust post-training method that helps the policy cover a broader distribution of semantically equivalent
prompts, and we identify two measures that help achieve this objective: separating format from semantics in the reward, and applying policy invariance across perturbed
prompts with equivalent semantics. We therefore propose
Prompt-Invariant RLVR (PIRL), consisting of a dynamic trinary reward and a consistency regularizer based on an
embedding-space adversary. Under stress testing, PIRL's average accuracy on
benchmarks drops by only $\le 1\%$, where GRPO drops ~3%. On dynamic evaluation, PIRL also achieves the smallest performance drop.
Read the full abstract ▾
All authors Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng, Chenrui Zhou, Lama Moukheiber, Yixing Ma, Bin Xu, Jiajun Song, Zhenglin Wan, Wangbo Zhao, Jiasheng Tang, Bohan Zhuang, Fan Wang, Yang You
Artificial Intelligence
Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs
Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim et al. (+1 more)
Omni-modal LLMs jointly process audio,
video, and text, but long
multimodal sequences incur substantial prefill and KV-cache costs. Existing omni-modal compression methods primarily focus on pre-LLM
token reduction, leaving modality-specific compression across the LLM boundary underexplored. We propose A-PACK, a two-stage framework that defers audio
pruning until query-conditioned
multimodal interactions emerge. Our analysis shows that audio exhibits higher task-relevant information density and representational diversity per
token than
video. We further find that local audio-visual dynamics provide a more effective cue for visual selection than
token-wise matching. We therefore preserve audio and compress
video with local dynamics before the LLM, then progressively prune low-relevance audio and visual
tokens and their KV-cache entries inside the LLM. Across four
benchmarks on Qwen2.5-Omni-7B/3B, A-PACK achieves the strongest average performance among the evaluated prior methods while reducing prefill FLOPs by up to 78% and improving decoding throughput by up to 2.21x.
Read the full abstract ▾
All authors Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim, Sungeun Hong
Artificial Intelligence
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Wenyao Cui, Huaping Zhang, Yongyi Huang et al. (+6 more)
Large
language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers are correct. Most existing “verification” signals are not diagnostic: answer matching observes only the outcome, LLM-as-judge provides subjective and non-verifiable critiques, and scalar rewards (e.g., PRMs/RMs) offer little insight into where a multi-step derivation fails.We propose SymDiag, a neuro-symbolic framework that reframes
reasoning verification as structured failure diagnosis. SymDiag translates natural-
language CoT into symbolic constraints and performs step-level satisfiability/entailment checks to (i) localize failing steps and (ii) produce verifiable diagnostic evidence, including counterexamples, inconsistency witnesses, and missing-premise indicators. A central challenge is that apparent “logic violations” can be caused either by genuine
reasoning defects or by neural-to-symbolic translation noise. SymDiag therefore incorporates a Self-Auditor that disentangles TranslationError from ReasoningError via dual symbolic encodings consistency checks, enabling robust diagnosis under partial observability. Across diverse mathematical, logical, scientific, and general
reasoning benchmarks, SymDiag improves detection of unfaithful
reasoning and provides substantially more effective feedback for multi-round
reasoning repair than outcome-only verification and LLM-based judging, offering a principled foundation for trustworthy and scalable
reasoning diagnosis.
Read the full abstract ▾
All authors Wenyao Cui, Huaping Zhang, Yongyi Huang, Qiuchi Li, Jian Xu, Cheng-Lin Liu, Chunxiao Gao, Juan Wang, Baohua Zhang
Artificial Intelligence · Cross-listed from cs.LG
Learning from Consensus and Disagreement: Unsupervised On-Policy Self-Distillation with Minority-Trajectory Contrast
Jiaxin Guo, Yanwei Yue, Xuanbo Fan et al. (+2 more)
On-policy self-
distillation improves
language-model
reasoning by querying a teacher on states actually visited by the student. Recent methods create a powerful information asymmetry by exposing the teacher to privileged context, yet they fundamentally rely on external supervision—such as gold solutions or verifiers—to construct this advantage. We introduce CoDA (Consensus and Disagreement
Alignment), a fully unsupervised framework that creates reliable privileged information entirely from the latent uncertainty structure of a model's own unlabeled rollouts. CoDA extracts two complementary signals. In the positive branch, answer-level consensus identifies a stable
reasoning mode, which conditions a frozen self-teacher to provide dense distributional guidance on fresh student trajectories. However, because agreement does not guarantee correctness, positive-only
distillation risks amplifying correlated errors into a false consensus. To break this harmful feedback loop, CoDA incorporates a negative branch that exploits disagreement: minority trajectories are treated as unstable alternatives and gently penalized via a reference-anchored, KTO-style calibration objective. This unpaired binary feedback provides robust regularization without requiring the strong assumption that the consensus is the absolute ground truth. Empirical evaluations on competition-level mathematical
benchmarks demonstrate that CoDA significantly improves
reasoning, outperforming self-generated baselines and effectively stabilizing training against erroneous consensus.
Read the full abstract ▾
All authors Jiaxin Guo, Yanwei Yue, Xuanbo Fan, Chunyu Yang, Yan Zhang
Artificial Intelligence · Cross-listed from cs.AR
Eco-SoC: A Sustainable VLSI Architecture for Energy-Proportional Artificial Intelligence
Jatin Chopra
In an era defined by escalating
climate change and the pervasive deployment of edge intelligence, the environmental cost of
semiconductor manufacturing and operation has reached a critical threshold. As Deep Learning (DL) accelerators dominate System-on-Chip (SoC) die area, achieving true sustainability requires a paradigm shift from static worst-case efficiency to dynamic energy-proportionality. This paper introduces Eco-SoC, a highly scalable VLSI architecture co-designed specifically for sustainable artificial intelligence. We propose a hardware-level Dynamic Precision-Scaling Logic (DPSL) framework that adaptively modulates bit-width precision based on real-time activation sparsity, successfully reducing switching activity by up to 42% on a commercial 7nm FinFET process node. Furthermore, we transcend traditional Power-Performance-Area (PPA) metrics by providing a comprehensive Life Cycle Assessment (LCA) using the Architectural Carbon footprint Tool (ACT). Our synthesis demonstrates that Eco-SoC offsets its increased
embodied carbon footprint (a marginal 4.8% area overhead) within 1.1 years of edge deployment. Finally, by introducing a thermal-aware power gating mechanism that mitigates localized hotspots, Eco-SoC doubles the projected Mean Time To Failure (MTTF) of the silicon, providing a tangible, scalable strategy for electronic waste (e-waste) mitigation in next-generation computing systems.
Read the full abstract ▾
Artificial Intelligence
Scale-to-Dialogue: Low-Burden Elicitation of Daily Premenstrual Symptom Ratings with Small Language Models
Yifan Wang
Prospective daily symptom tracking is central to premenstrual health assessment, but repeated ordinal forms impose substantial response burden. We formulate conversational administration as an ordinal label-recovery problem: the system actively elicits a small set of symptom clusters and maps each response to the original severity labels. We used 3,320 complete participant-days from the mcPHASES
dataset, covering cramps, mood swing, fatigue, sleep issues, stress, and bloating on a six-level scale. Six participants were reserved for development and 36 for a frozen evaluation comprising 360 participant-days and 2,160 item labels. A ModernBERT evidence gate detected whether a symptom was expressed, and Qwen2.5-1.5B-Instruct produced deterministic structured severity scores. Fixed six-item questioning achieved a quadratic weighted kappa of 0.976, whereas three joint symptom-cluster questions achieved 0.913, 97.45% agreement within one severity level, and 80.94% recall for moderate-or-higher symptoms while reducing questions by 50%. Open-first adaptive policies required 3.92-5.98 questions and produced lower agreement than the corresponding fixed policies. Participant-cluster bootstrap analysis estimated a kappa difference of -0.062 (95% CI -0.076 to -0.048) between the three-cluster and six-item strategies. Active cluster-level elicitation provides a direct, local-model route from natural conversation to reusable daily symptom labels.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Can We Optimize the Performance-Carbon Emission Break-Even Point?: The Quest for Greener LLMs
Sourav Das, Tanmay Joshi and Kripabandhu Ghosh
The carbon footprint of any deployed Large
Language Model (LLM) accumulates during inference, where repeated use of the model substantially exceeds the one-time cost of fine-tuning. Yet most efficiency interventions target either pre-training scale or post-hoc compression. We ask whether folding a calibrated, differentiable energy surrogate into the fine-tuning objective can produce inference behavior that gains task accuracy at zero or near-zero carbon cost, a break-even configuration. We propose a joint loss mechanism with a per-model carbon-emission parameter, a linear surrogate over parameter norm, FLOP proxy, and a
memory proxy, fit from on-hardware energy profiling. We fine-tune three architecturally distinct families: Gemma-2 2B, Llama-3.1 8B, and Qwen-2.5 14B, and evaluate inference F1 and CO$_2$ emissions on three MMLU subjects: abstract
algebra, philosophy, and formal logic. We discover from several outcomes that the carbon term behaves as either harmful interference or beneficial regularization depending on the task structure. We position calibrated carbon-aware fine-tuning as a lightweight, drop-in regularizer with a non-empty but model and task-dependent break-even region. This is an ongoing work, and we will release our codebase soon.
Read the full abstract ▾
Artificial Intelligence
FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models
Kaili Zheng, Kaiwen Wang, Xun Zhu et al. (+3 more)
Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of
Multimodal Large
Language Models (MLLMs) in this setting remain underexplored. Existing
benchmarks rely on action-specific annotation schemes and focus primarily on final assessment outputs, offering limited insight into how models assess exercise quality. We introduce FitAQA, a systematic
benchmark for evaluating MLLMs in fitness AQA, containing 2,219
videos and 5,512 QA instances across 30 bodyweight exercises. In collaboration with experts in sports science, we develop a unified form error taxonomy that defines 38 recurring form errors within six complementary quality dimensions:
alignment,
symmetry, stability, coordination, tempo, and completeness. This taxonomy provides a shared assessment framework across different exercises. FitAQA further formulates three evaluation tasks: perception for recognizing relevant visual evidence, judgement for combining that evidence with domain knowledge to assess execution correctness, and temporal grounding for localizing form errors over time. Extensive evaluation shows that current MLLMs still struggle to assess exercise quality comprehensively and localize form errors precisely. Controlled experiments further indicate that visual perception is a key bottleneck, as judgement performance improves substantially when ground-truth perceptual evidence is provided. The
dataset is available at https://huggingface.co/
datasets/Kelly0510/FitAQA.
Read the full abstract ▾
All authors Kaili Zheng, Kaiwen Wang, Xun Zhu, Qingyuan Yang, Chenyi Guo, Ji Wu
Artificial Intelligence · Cross-listed from cs.CV
TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases
Gia-Han Truong, Khang Nguyen Quoc and Luyl-Da Quach
To address this gap, we introduce TomaMMU, a large-scale Tomato leaf disease
MultiModal Understanding
dataset, alongside TomaBench, a
benchmark for evaluating VLMs on tomato disease understanding. TomaMMU comprises 28,808 high-quality images spanning 15 categories and 213,119 human-annotated visual question-answer pairs, generated through a three-stage pipeline comprising Data Collection, Human Annotation, and Question-Answer Generation. Building on this foundation, TomaBench organizes seven agricultural tasks into a hierarchical three-level taxonomy spanning Basic Perception, Pathology Understanding, and Expert Diagnosis, which together enable systematic evaluation from low-level visual recognition to high-level diagnostic
reasoning. The tasks assess visual symptom recognition, taxonomic relationships, and diagnostic
reasoning, offering a comprehensive view of how well models grasp plant pathology. Our results pronounced gaps in fine-grained recognition and factually grounded
reasoning with 14 state-of-the-art VLMs, consistently underperforming on both challenging MCQs and open-ended questions. These results suggest that current VLMs struggle to translate visual perception into reliable diagnostic knowledge, motivating the need for targeted domain adaptation. Simple fine-tuning on TomaMMU substantially narrows this gap, boosting accuracy on challenging MCQs to 96.09%, outperforming recent VLMs, and pointing toward promising directions for future work. All data and code is available in https://huggingface.co/
datasets/enalis/TomaMMU.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation
Yangyang Feng, Zhuoyan Feng and Junlan Chen
On-policy self-
distillation (OPSD) uses a privileged teacher to supervise a
reasoning model on prefixes sampled from its own rollouts. Yet each rollout also reveals how the student's response unfolds and whether it succeeds, student-specific hindsight that standard OPSD does not use to form the teacher. We introduce Privileged Adaptation from Student Trajectories (PAST), which treats each completed student trajectory as additional privileged information for the OPSD teacher while leaving the student's
distillation prefixes unchanged. PAST preserves the student's next-
token distribution on correct trajectories and uses failed trajectories to adapt the teacher toward verified success under student-proximity regularization. We characterize what such a trajectory-conditioned teacher can transfer to a prefix-only student. Forward-KL
distillation projects the teacher distributions to their conditional arithmetic mean given the prefix. This projection separates trajectory-specific variation that remains privileged from the mean policy shift available to the student. For correct trajectories, the unclipped population objective also has the frozen student as an ideal distributional fixed point. Across three mathematical
reasoning benchmarks, PAST improves the Avg@12 macro average over Vanilla OPSD by 5.6 percentage points. A $2\times2$ factorial study shows gains from both complete-trajectory access and teacher adaptation, while trajectory removal and shuffling confirm that the adapted teacher uses the matching hindsight context.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure
Víctor Gallego
Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim. We document this concretely in two GPU-kernel-optimization suites with held-out generalization gates: Metal-Sci (10 scientific-compute tasks) and Metal-ZK (12 zero-knowledge/cryptographic tasks), in which three frontier LLMs (Opus 4.7, Gemini 3.1 Pro, GPT-5.5) propose Metal kernels inside a $(1{+}1)$ evolutionary loop with rich feedback. Although no model is prompted to act adversarially, the promoted winners repeatedly fingerprint the evaluation configuration: they branch on the identity of runtime parameters, tune the measured branch maximally, and leave the unmeasured branch slow or silently wrong. Across the pooled suites, $16/53$ ($30\%$) of in-distribution wins fail to transfer to held-out configurations. We give a four-mode taxonomy of these failures, from configuration fingerprints to gate leakage. We distill design guidance for measurement under strategic optimization: held-out probes retain validity only on non-enumerable axes; gates must measure held-out performance, not just correctness; and a transfer rate is interpretable only with per-failure mechanism grades: ours decomposes into gamed, overfit, and benign. Code and research artifacts: https://github.com/vicgalle/kernel-fingerprinting
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimization
Zexun Lin, Yuan Feng, Junlin Lv et al. (+2 more)
Speculative decoding accelerates large
language model inference by drafting multiple
tokens for parallel verification, with efficiency critically determined by the speculative length selected at each decoding round. Existing dynamic speculation methods select the speculation length by estimating how many
tokens will be accepted, which is reasonable for autoregressive drafters that generates
tokens sequentially. The recent wave of
diffusion-based drafters, however, generates candidate blocks in parallel at substantially lower drafting cost, shifting the key question from how many
tokens to generate to how many generated
tokens are worth verifying. We therefore reformulate dynamic speculative-length selection as expected-speedup optimization and derive a marginal criterion that extends the speculative sequence only when its acceptance gain outweighs the additional verification cost. Building on this criterion, we develop LibraSpec, a training-free and plug-and-play
algorithm that iteratively determines the speculative length using drafter confidence scores. Theoretically, we prove that LibraSpec monotonically converges toward the optimal speculative length. Experiments across six target models, three
diffusion-based speculative decoding methods, and math, coding, and chat
benchmarks show consistent improvements under both greedy and sampling settings, achieving a further $0.5\sim1.5\times$ improvement over baselines and up to $8.49\times$ speedup over autoregressive decoding.
Read the full abstract ▾
All authors Zexun Lin, Yuan Feng, Junlin Lv, Kevin S. Zhou, Xike Xie
Artificial Intelligence · Cross-listed from cs.CV
Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation
Jonathan Suprijadi, Raphael Stock, Moritz Langenberg et al. (+10 more)
Vision-
language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges. Modern foundation
vision encoders (VEs) can produce tens of thousands of
vision tokens per scan, making the visual sequence passed to the large
language model (LLM) a primary computational bottleneck.
Vision-to-
language projectors can compress this sequence to reduce computation, but may discard clinically relevant detail; conversely, effective compression can accommodate higher-resolution inputs while keeping the downstream
token count fixed. How this
vision-
token budget should be allocated across input field of view, spatial resolution, and
vision-to-
language projection therefore remains an open design question. We systematically evaluate four heterogeneous VEs (CNN- and ViT-based), five
token-reducing projectors at up to 64x compression alongside a non-reducing MLP projector baseline, and five instruction-tuned LLMs (1.7B–4B) on two large-scale CT report
datasets (CT-RATE and Merlin). At matched LLM
token budgets, anatomy-guided region of interest cropping is the most consistent strategy, improving clinical macro F1 in 19 of 20 settings by +3.7 points on average for the 3D ViT Primus encoder and +1.1 for the slice-based 2D ViT Curia encoder. Increasing input resolution further is strongly projector-dependent: the PerceiverResampler, paired with higher-resolution Curia features, yields the strongest configuration in the resolution study on both
datasets. Our best configurations achieve state-of-the-art clinical macro F1 on the test sets, reaching 49.5 on CT-RATE and 49.0 on Merlin. Code and models will be published upon publication.
Read the full abstract ▾
All authors Jonathan Suprijadi, Raphael Stock, Moritz Langenberg, David Zimmerer, Kim-Celine Kahl, Stefan Denner, Yannick Kirchhoff, Karol Gotkowski, Maximilian Rokuss, Jeremias Traub, Tassilo Wald, Constantin Ulrich, Klaus Maier-Hein
Artificial Intelligence
AI Evaluation Should Measure Verification Cost, Not Correctness Alone
Viviana Crescitelli, Generoso Immediato, Fabio Persia et al. (+1 more)
The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs. We argue that current evaluation metrics overlook a critical failure mode: Verification-Cost Errors (VCEs), defined as incorrect input-output pairs that a declared fraction of the verifier population fails to identify within the verification budget available in a given deployment context. Unlike standard notions of "
hallucination", VCEs are defined operationally, by the failure of correct identification within budget rather than by any property of the output itself. Plausibility and authoritative presentation are hypothesised contributors to that failure, not defining conditions. To capture this asymmetry, we introduce the notion of verification cost relative to a deployment budget as an operational dimension that current evaluation does not routinely capture. The quantity is presented as a conceptual instrument rather than a finalized metric. Evidence from code generation and multi-modal document understanding shows that high
benchmark accuracy can mask significant verification effort in practice. We therefore take the position that correctness alone is insufficient as a measure of reliability. AI evaluation should explicitly account for verification cost, reflecting whether errors can be detected under realistic resource constraints.
Read the full abstract ▾
All authors Viviana Crescitelli, Generoso Immediato, Fabio Persia, Stefania Costantini
Artificial Intelligence
PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function Calling
Dongjie Xu, Julius, Hanchi Dong et al. (+6 more)
Reliable evaluation of tool routing is critical as Large
Language Models increasingly operate as autonomous
agents. Current
benchmarks face three structural limitations: data distributions that follow a power law leave rare scenarios underrepresented; the absence of
adversarial hard negatives obscures performance differences across models; and annotation pipelines depend on LLM judgments that have not been validated through execution. In this paper, we introduce PluginEval, a
benchmark constructed through a two-stage framework that systematically mitigates these limitations. First, we formulate tool routing as a sequence of three decisions and separate generation from verification. LLMs propose candidate calls, while deterministic validation and real API execution provide reliable quality signals. Second, we decompose each plugin by capability, intent, and boundary to identify trigger and exclusion scenarios. We then generate queries at different difficulty levels to fill coverage gaps, including
adversarial negatives targeting three failure modes, and return them to the first stage for annotation. This process creates a closed loop that iterates until coverage converges. For evaluation, we move beyond aggregate accuracy. An LLM judge anchored to gold annotations classifies failures as missed calls, spurious calls, or parameter errors, producing a detailed error profile for each model. We evaluate five model families, including proprietary models and models with open weights, analyze their performance across difficulty levels and error categories, and validate the judge through agreement with human annotations.
Read the full abstract ▾
All authors Dongjie Xu, Julius, Hanchi Dong, Minghua Tang, Yuxuan Sun, Ziwei Nie, Zicheng Liu, Dujun Qing, Jiajie Xu
Artificial Intelligence
EnergyBridge: Benchmarking Household Energy Management, User Participation, and Grid Flexibility
Xudong Wu, Zeqing Wu, Jiarui Zhang et al. (+8 more)
Residential virtual power plants (VPPs) can provide grid flexibility by shifting household demand, but physical flexibility becomes dependable capacity only when residents authorize a plan and the promised response is delivered. Existing
benchmarks evaluate control but omit event-specific authorization. We present EnergyBridge, a
benchmark and
agent framework connecting capacity reporting, household authorization, and physical execution. It combines region-specific EnergyPlus environments for Tianjin and Berlin with an LLM-based User Participation Simulator. Against 584 persona- and event-matched human role-play judgments, the LLM-based User Participation Simulator preserves method ordering with a 5.3-point mean absolute acceptance error. Across conventional controllers and
agent baselines, EnergyBridge achieves the highest simulated authorization, lowest event-window energy, and the most reliable capacity commitment in both regions. We release human data and codes for reproducible human-centered grid-flexibility research: https://github.com/Agentic-Intelligence-Lab/EnergyBridge.
Read the full abstract ▾
All authors Xudong Wu, Zeqing Wu, Jiarui Zhang, Xuhao Fan, Ziang Ding, Yuming Zhuang, Mingqi Yuan, Yilun Du, Hongjie Jia, Yunfei Mu, Jiayu Chen
Artificial Intelligence
A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration
Wei Wang, Yaosen Chen, Han Yang et al. (+5 more)
The state
evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error. Forcing all sources into one black box makes mechanism attribution and constraint preservation unauditable; forcing every mechanism into one equation family discards mature domain solvers. We propose SD-GWM, a Structural Dynamics Graph World Model as an executable structural contract: nodes declare self-dynamics S, edges declare neighbor graph-coupled dynamics N—both fixed-form mechanism assets (rules, ODEs, solvers) calibrating only authorized parameters. An optional bounded residual R concentrates learnability, while a global projection maps states to feasibility, enforcing constraints without guaranteeing accuracy gains. On eight pre-registered research questions, SD-GWM delivers (i) heterogeneous integration: rules and solvers plug in natively; (ii) semantic fidelity: disabling R preserves source semantics bit-for-bit, with four theory properties under explicit proof/empirical boundaries; (iii) auditable governance: stepwise traces enable counterfactual fault localization (top-1 = 1.0) without post-hoc approximations. On a semi-synthetic flood testbed and USGS streamflow, SD-GWM reduces constraint violations to floating-point tolerance in analytical tests and to zero in semi-synthetic and real-data cases. Persistence matches SD-GWM in calm periods, but during a 254-day extreme-flood shift persistence and all neural baselines collapse (90-min RMSE 892-3007 cfs) while SD-GWM holds at 108 cfs (8-28x gain). The bounded residual cuts RMSE ~50% only under backbone bias. We position SD-GWM not as a universally superior forecaster, but as a verifiable substrate for auditable, constraint-safe spatiotemporal mining.
Read the full abstract ▾
All authors Wei Wang, Yaosen Chen, Han Yang, Yuegen Liu, Mingli Luo, Xinxin Jiao, Xuming Wen, Ming Liu
Artificial Intelligence · Cross-listed from cs.LG
RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation
Dongjie Xu, Kai Qian, Julius et al. (+6 more)
Long-context LLM inference is bottlenecked by KV cache
memory, yet distributing a limited cache budget across layers remains challenging. Existing methods rely on proxies such as layer depth,
attention statistics, or representation change. These proxies do not measure how perturbations at each layer propagate to the output and may therefore cause sensitive layers to be underallocated while tolerant layers are overallocated. To address this issue, we propose RippleKV, which allocates cache across layers by estimating how perturbations to each layer's value cache affect the final predictive distribution. RippleKV independently injects norm-adaptive perturbations into each layer's value cache and measures the induced KL divergence at the model output over a small calibration set. Averaging these responses yields a sensitivity profile specific to the model that need not vary monotonically with depth. RippleKV then converts the sensitivity profile into layer budget multipliers by normalizing the sensitivity scores and applying an exponential mapping. A ratio parameter controls the allocation disparity between sensitive and tolerant layers, while a final normalization preserves the KV cache budget. Experiments on LongBench demonstrate that RippleKV achieves the highest average performance among the evaluated KV cache compression methods under matched cache budgets.
Read the full abstract ▾
All authors Dongjie Xu, Kai Qian, Julius, Weijie Shi, Yuxuan Sun, Minghua Tang, Fenglei Jin, Hanchi Dong, Jiajie Xu
Artificial Intelligence
Branch2Skill: Efficient Skill Evolution Through Reasoning Trees
Yanwei Ren, Haotian Zhang, Likang Xiao et al. (+5 more)
Skill
evolution improves
agent skills through feedback over time, with failed trajectories often providing informative signals by revealing incomplete or misleading behaviors. However, existing methods mainly rely on single trajectories, where early
reasoning errors can propagate through subsequent steps and weaken the feedback available for skill refinement. Consequently, improving skills requires repeated cycles of rollout, diagnosis, and update, incurring substantial
token costs. To address this challenge, we introduce Branch2Skill, an efficient framework that transforms a single
reasoning tree into dense supervision for skill
evolution. For each task or problem, Branch2Skill performs Monte Carlo tree search under a fixed budget to obtain diverse
reasoning trajectories, then compares an elite path with sibling alternatives sharing the same prefixes to extract step-wise evidence about which
reasoning patterns to retain, revise, or avoid. Finally, Branch2Skill distills multi-step evidence into reusable updates, allowing one
reasoning tree to provide supervision across multiple
reasoning steps and reducing the need for repeated rollout-update cycles. Across six
benchmarks covering
reasoning and agentic tasks, Branch2Skill consistently improves task performance while enhancing skill
evolution efficiency. For example, with GPT 5.5 as the target model, Branch2Skill uses 73.2% fewer
tokens than SkillOpt, while achieving superior performance. These results demonstrate that
reasoning trees can support not only more effective trajectory search, but also richer supervision for more efficient skill improvement. Code will be published.
Read the full abstract ▾
All authors Yanwei Ren, Haotian Zhang, Likang Xiao, Jiaxing Huang, Jiayan Qiu, Baosheng Yu, Quan Chen, Liu Liu
Artificial Intelligence · Cross-listed from cs.CV
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
Jinbo Yan, Limeng Qiao, Jie Qin et al. (+3 more)
Semantic
vision encoders have become a central visual interface for
multimodal understanding and semantic conditioning in image generation. However, their final
tokens discard fine-grained visual details, leading to poor pixel reconstruction and limiting their use in reconstruction-sensitive tasks such as image generation and editing. In this work, we ask whether understanding, generation, and editing can be modeled in a single visual representation space built from a pretrained semantic ViT. We show that the frozen
Transformer blocks of a semantic ViT are not intrinsically unable to preserve visual details. Instead, the original patch parameterization drives the representation toward semantic abstraction, making fine-grained information difficult to recover from the final
tokens. Based on this observation, we introduce Patch Reparameterization, which preserves the original semantic pathway while adding a reconstruction-aware patch
embedding that provides fine-grained visual information to the same frozen ViT blocks. The resulting unified representation preserves
multimodal understanding while enabling high-fidelity image reconstruction and a favorable reconstruction–generation trade-off. We further scale this representation into UniSpace, an 8B Mixture-of-
Transformer-Experts model that performs understanding, generation, and editing in the same visual space without a separate VAE pathway. System-level evaluations demonstrate practical text-to-image generation and instruction-based image editing, showing that a reparameterized pretrained ViT can serve as a unified visual interface for scalable
multimodal modeling.
Read the full abstract ▾
All authors Jinbo Yan, Limeng Qiao, Jie Qin, Junyan He, Feize Wu, Guanglu Wan
Artificial Intelligence
The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task
Marc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo et al. (+1 more)
How much an AI coding
agent costs to run can depend more on the
agent scaffolding that drives it than on the interface through which it reaches its tools. We set out to measure the cost of tool use over the Model Context Protocol (MCP) against tool use over an ordinary command-line interface (CLI), a difference on which published estimates disagree by more than an order of magnitude while resting on practitioner reports that cannot be reproduced. We ran one fixed software task – six operations against a private online git repository – across seven
agent scaffoldings and five
language models, and we verified completion by inspecting the repository state rather than trusting the
agent's self-report. The dominant effect was the scaffolding. Two of the seven ship no MCP support at all; they completed every run using only the CLI, which shows that MCP is unnecessary for this class of work, and they were 5.0x to 28x cheaper than the five scaffoldings that do support MCP, comparing CLI runs alone with no MCP server attached anywhere. The effect was largest for a small 27-billion-parameter model running locally, whose cost varied 139x across scaffoldings while it completed the task under all of them. The comparison we set out to make proved unstable: thirteen strictly paired MCP-to-CLI ratios span 0.43x to 29x, with outliers on both sides. The two interfaces separate on the cost of failure, where 12.9 per cent of the money spent on MCP runs bought no completed work against 2.2 per cent on CLI runs, but not on its frequency: failures were equally common in both, in the original runs and in their repetitions alike.
Agents frequently ignored the interface they were assigned, so comparisons that do not verify actual behaviour measure an unknown mixture. The harness, the task, the verification and the complete
dataset are released as open source.
Read the full abstract ▾
All authors Marc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo, Juanan Pereira
Artificial Intelligence · Cross-listed from cs.LG
LegoLM: Structured Weight Sharing for Large Language Models
Joseph Bingham
We present \LegoLM{}, a structured weight-sharing compression framework for large
language models grounded in a systematic study of why global weight sharing fails and how to fix it. We identify two distinct failure modes. Distributional mismatch: for vector blocks of dimension d <= 2,
transformer layers with heterogeneous weight scales impose a scale-mismatch penalty that grows linearly with d and cannot be resolved by increasing K, producing perplexity in the millions.Outlier dominance: for scalar blocks, a fraction ~1/K of weights lies beyond the outermost Lloyd-Max decision threshold and cannot be represented by any centroid; their misrepresentation accumulates across layers, causing catastrophic quality loss. \LegoLM{} resolves both failure modes via three data-free adaptations: 1 scalar-block encoding to eliminate the $d$-linear mismatch component, 2 percentile-selective replacement that identifies and preserves outlier weights verbatim, and 3 boundary-layer protection for the first and last
transformer blocks. Across GPT-2 small (124M) and Mistral-7B, \LegoLM{} achieves +0.03% PPL degradation at 4.41X compression on Mistral-7B - outperforming PTQ-8bit in both quality and compression ratio - and -0.02% at 2.67X. Downstream evaluation on LAMBADA and HellaSwag confirms that \LegoLM{} at K=64, p=99% preserves accuracy within noise at 5.12 X compression, exceeding PTQ-8bit's compression ratio while matching its accuracy. We further discover that outlier dominance grows with model scale: full replacement at K=128 degrades GPT-2 small by only +23% but catastrophically degrades Mistral-7B by +1,134,279%, while selective replacement at p=99% rescues both models to under +15%. A controlled ablation confirms that selective replacement is the dominant mechanism: adding it to per-layer K-means also yields near-lossless quality, matching \LegoLM{} within 0.02%.
Read the full abstract ▾
Artificial Intelligence
SkillReason: Reasoning-Enhanced Agent Skill Retrieval for Implicit User Requests
Donghong Jiang, Endian Lin, Luoping Cui et al. (+6 more)
Large
language model
agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the appropriate skill from a large- scale library remains challenging because realistic user re- quests are often concise and underspecified, stating only the task goal while leaving the required capabilities and execu- tion steps implicit. Existing
benchmarks provide limited cov- erage of such requests. To address this gap, we introduce SkillReason-Bench, a large-scale cross-domain
benchmark containing 3,729 queries and a
retrieval corpus of 61,228 skills spanning nine domains. We further propose SkillRea- son, a two-stage framework that uses chain-of-thought rea- soning as training-time supervision for skill
retrieval. In Stage I, capability
reasoning traces generated by a stronger teacher provide explicit supervision through contrastive learning, re- trieval distribution
alignment, and
language modeling, en- couraging the retriever to internalize capability
reasoning in its query representation. In Stage II, a
retrieval-guided GRPO objective encourages the model to explore
reasoning trajecto- ries better suited to its own capabilities and more effective for
retrieval. At inference, SkillReason directly encodes the orig- inal query without autoregressive CoT generation, preserv- ing efficient query-only
retrieval. Extensive experiments on SkillReason-Bench, SkillRet, and SRA-Bench show that Skill- Reason achieves state-of-the-art performance across all three
benchmarks, demonstrating that
reasoning-enhanced training better bridges the semantic gap between high-level task goals and skill capabilities.
Read the full abstract ▾
All authors Donghong Jiang, Endian Lin, Luoping Cui, Hanqing Liu, Mingjie Liu, Fan Yang, Hong Wang, Zhao Yang, Chuang Zhu
Artificial Intelligence
Smart Compaction: Predicting Compaction Utility from Lakehouse Table Metadata
Jannic Cutura and Subash Prakash
Open lakehouse table formats accumulate small data files over time, which degrades query performance. Deciding when compaction is worthwhile remains threshold-driven, but which metadata features actually determine compaction utility is not well understood. We present an open simulation framework that generates 2,376 Apache Iceberg tables spanning three orders of magnitude in file size, extracts 17 metadata features from manifest files without reading data, and trains XGBoost to predict the continuous file-reduction ratio (R2 = 0.998, RMSE= 0.013). The binary compaction decision turns out to be trivially separable by a single partition-level threshold max_files_per_partition> 4, requiring no learned model. Cross-schema validation on 96 TPC-H tables confirms generalisation without retraining (R2 = 0.976). A query
benchmark reveals that compaction benefits metadata-heavy queries but can slow full-scan aggregations by reducing task parallelism. All code and data are publicly available.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
Yuqian Zhang, Yao Shi, Kexin Huang et al. (+7 more)
Zero-shot text-to-
speech (TTS) now supports interactive assistants, personalized media, and accessibility tools. All TTS systems require faithful linguistic rendering, consistent speaker identity, and low-latency response. Yet compact streaming systems must preserve sufficient acoustic detail in a predictable low-rate latent sequence, while iterative
diffusion sampling and classifier-free guidance multiply inference cost at every autoregressive step. To strike a balance between high-fidelity synthesis and low-latency inference, we present CuteTTS, a compact continuous-autoregressive TTS system. It combines semantically aligned causal VAE latents with patch-level autoregression, explicit speaker conditioning, and a bidirectional flow-matching head. We further introduce guidance-step
distillation, which absorbs classifier-free guidance and multiple solver steps into a single interval-conditioned student. Evaluations on LibriSpeech and Seed-TTS-Eval demonstrate competitive intelligibility and speaker similarity in zero-shot voice cloning, while
distillation lowers first-audio latency by 23.3% and real-time factor by 40.8% relative to the base model with comparable objective and subjective quality. These results provide a practical path toward continuous-autoregressive TTS that reconciles high-fidelity generation with the latency demands of real-time interaction.
Read the full abstract ▾
All authors Yuqian Zhang, Yao Shi, Kexin Huang, Botian Jiang, Zhe Xu, Yiwei Zhao, Min Liang, Shuang Chen, Xipeng Qiu, Yu-Gang Jiang
Artificial Intelligence · Cross-listed from cs.CL
Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach
Tong Bao, Yi Zhao, Heng Zhang et al. (+1 more)
Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large
language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recognition and classification by LLMs. However, when too many candidate entity types are provided in the
prompt, LLMs struggle to accurately recognize and label entities in scientific texts, where entity types are more complex than in general domains. To address this challenge, we propose TdSciNER, a type-driven approach that effectively leverages entity type information to enhance SciNER performance. In TdSciNER, we first design an entity type filter model to identify the most likely entity types present in a given sentence. Subsequently, we introduce an auxiliary multi-class entity typing task within a multi-task learning framework alongside SciNER to obtain richer contextual representations. Then, we develop a novel demonstration selection strategy based on sentence similarity and entity type diversity to activate the in-context learning capabilities of LLMs, thereby improving entity recognition accuracy across diverse scientific domains. Experiments on three
datasets demonstrate that our method achieves performance comparable to fully supervised models. Further analysis validates that each entity type-driven component in TdSciNER contributes to the improvement of SciNER performance. This work provides valuable insights for future advancements in SciNER and broader information extraction tasks in scientific text mining.
Read the full abstract ▾
All authors Tong Bao, Yi Zhao, Heng Zhang, Chengzhi Zhang
Artificial Intelligence
Can Open-Weight Models Compete on Financial Text Comprehension?
Jan Spörer
Open-weight
language models from Chinese AI labs caught up on
benchmarks relative to proprietary frontier models in recent months. Yet their reliability on real-world financial tasks remains largely untested. We updated the Financial Touchstone
benchmark, which now has 2,967 question context-answer triplets across 495 international annual reports. We also apply a new set of models on the
benchmark, expanding coverage from eleven to twenty models across ten providers, including recent open-weight models such as GLM 4.7, GLM 5, Kimi K2.6, and DeepSeek V3.2, as well as Alibaba's proprietary flagship Qwen3-Max. Anthropic's Claude Opus 4.6 achieves the highest accuracy (88.4%), while Google's Gemini 2.5 Pro maintains the lowest
hallucination rate (0.08%). Notably, the open-weight Kimi K2.6 ranks third in accuracy, and the non-
reasoning models GLM 5 and Mistral 3 rank fourth and fifth, challenging the assumption that
reasoning architectures or proprietary weights are a prerequisite for strong financial comprehension. Information
retrieval remains the primary bottleneck, accounting for 48.9% of all failures. We also document a new finding: geopolitical content filters in Chinese models refuse legitimate financial questions (0.08% of attempts), sometimes without clear reason, and the refusal behavior depends on the access route as much as on the model. The complete
dataset and evaluation framework are publicly available.
Read the full abstract ▾
Artificial Intelligence
A QUBO-Inspired Computational Framework for Airport Landside Bottleneck Diagnosis and Dynamic Dispatch Optimization
Wuming Lei, Xiaobin Li, Mingyan Sun et al. (+3 more)
Airport landside traffic centers connect terminal arrivals with taxis, ride-hailing vehicles, private cars, buses, metro services, parking facilities, and terminal-area roadways. Peak arrivals can create coupled congestion across passenger queues, vehicle queues, pickup berths, storage areas, and access roads. This study proposes a QUBO-inspired computational framework for bottleneck diagnosis and dynamic dispatch in this setting. Shanghai Pudong International Airport and Hangzhou Xiaoshan International Airport serve as case airports. A five-minute state model links passenger arrivals, vehicle supply, pickup berth service, vehicle storage, and road capacity. Bottleneck diagnosis uses service intensity, road demand saturation, bottleneck frequency, queue severity, shadow-price leverage, and a composite congestion severity index. Two dispatch schemes are tested under consistent demand inputs: finite-action model predictive control and quadratic-unconstrained-binary-optimization-inspired simulated annealing. In the strong-peak baseline scenario, the QUBO-inspired method reduces the final passenger queue from 3445 to 2477 passengers at Shanghai Pudong and from 2053 to 1482 passengers at Hangzhou Xiaoshan. Case results indicate different dominant bottlenecks. Shanghai Pudong is more affected by road saturation, whereas Hangzhou Xiaoshan is more affected by pickup berth service. Robustness tests under demand, supply, service, road-capacity, modal-share, and random-noise perturbations show retained queue-reduction benefits under the tested uncertainty levels.
Read the full abstract ▾
All authors Wuming Lei, Xiaobin Li, Mingyan Sun, Jianing Long, Yulin Tong, Yanbin Gao