Artificial Intelligence · Cross-listed from cs.LG
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents
Bofan Chen, Boxuan Zhang, Fei Tang et al. (+7 more)
GUI
agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated widgets routinely invalidate plans fixed before execution. Recent
agent-skill frameworks encapsulate reusable procedural knowledge to mitigate this, yet existing skill designs are largely developed without targeting GUI execution dynamics and treat skills as static artifacts produced before deployment rather than living procedural knowledge that improves through it. We argue that what GUI
agents need is not better static skills, but skills that can be revised from execution feedback at deployment time, without additional training. We propose EvoSkill-GUI, a training-free framework in which each skill is a structured multi-file package containing
retrieval metadata, executable plans, backup localization, failure-recovery rules, accessibility utilities, and failure cases. EvoSkill-GUI operates through a \textbf{reflect-revise-reuse} loop: the executor performs instant in-rollout revisions, an isolated critic diagnoses failed trajectories under strict information isolation, and the executor edits specific skill files through a restricted tool interface. Across MobileWorld, AndroidWorld, and OSWorld, three mainstream GUI
benchmarks spanning mobile and desktop platforms, EvoSkill-GUI consistently improves multiple base models without any training, with maximum gains of $+16.2\%$, $+6.0\%$, and $+10.5\%$ respectively, and evolved skill libraries continue to benefit related tasks rather than being rebuilt from scratch. Our code is available at https://github.com/ZJU-REAL/EvoSkill-GUI.
Read the full abstract ▾
All authors Bofan Chen, Boxuan Zhang, Fei Tang, Zhengxi Lu, Yong Du, Tongbo Chen, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
Artificial Intelligence · Cross-listed from astro-ph.IM
Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models
Vanessa Lama, Sanjay Das, Emily Herron et al. (+5 more)
Domain-specialized
language models are widely used for scientific question answering, but stronger general-purpose systems raise a sharper question: when does domain-specific fine-tuning remain valuable for open-ended scientific
reasoning? We study this in astronomy with a curated QA
benchmark from publicly available 2017–2026 Olympiad-style materials. The free-response subset contains 300 questions, including 204 text-only and 96 image-linked examples. We compare open-weight and API-served general-purpose,
multimodal, and astronomy-specialized models using judge-based correctness and complementary reference metrics. Strong general-purpose models establish the highest correctness baseline in this testbed, while analyses of metric agreement, judge sensitivity,
benchmark composition, and modality reveal variation not captured by a single leaderboard. These results motivate treating domain specialization as a task- and deployment-dependent property and highlight the role of domain-specific evaluation in determining which models, capabilities, and evaluation criteria are appropriate for scientific workflows.
Read the full abstract ▾
All authors Vanessa Lama, Sanjay Das, Emily Herron, Yuan-Sen Ting, Tijmen de Haan, Junqi Yin, Tirthankar Ghosal, Feiyi Wang
Artificial Intelligence · Cross-listed from cs.IR
Scaling Articulated Rationales for MLLM-based Recommendation
Haoke Xiao, Yueyang Liu, Yuhui Zhang et al. (+17 more)
We presented SARA, an industrial framework that transforms sparse articulated user rationales into scalable recommendation signals. Its data engine curates questionnaire responses into SARA-HQ, providing explicit preference supervision for aligning SARA-7B through SFT and Quality-Refining DPO. This
alignment extends rationale generation from $86{,}564$ questionnaire-covered authors to the full $10$M-author space. SARA-Ranker translates the generated positive and negative rationales into features for user–author interaction modeling and negative-feedback history modeling, connecting articulated reasons to production ranking. Evaluation on unseen authors demonstrates that SARA-7B generates more specific, relevant, and grounded rationales than the evaluated general-purpose MLLMs. On top of a strong industrial ranking baseline with
multimodal features, separate online A/B tests show that positive-rationale integration increases watch time by $0.99\%$, while negative-rationale integration reduces Hate feedback by $8.16\%$. Daily refresh and more than $30$ days of production deployment further demonstrate the operational feasibility of the approach. These findings establish articulated rationales as a useful complement to behavioral and content signals, and demonstrate a practical role for MLLMs in scaling sparse human explanations into preference information that improves industrial recommendation.
Read the full abstract ▾
All authors Haoke Xiao, Yueyang Liu, Yuhui Zhang, Xiang Chen, Yufei Liu, Jia Xu, Yalong Guan, Xiaolan Zhu, Xiaoyu Zhang, Shijun Wang, Shuang Yang, Zijie Meng, Zejian Zhang, Ruochen Yang, Xiangyu Wu, Tingting Gao, Han Li, Lantao Hu, Cheng Luo, Kun Gai
Artificial Intelligence · Cross-listed from cs.LG
Lecture notes on Physics Informed Neural Networks, Neural Operators, and their applications
Alessandro Bombini
This is the set of lecture notes for the PhD course \href{https://www.unibz.it/en/faculties/engineering/phd-computer-science/study-course-offering/2025/36967}{Physics Informed Neural Network, held at the University of Bozen/Bolzano} in the academic year 2025/2026. The goal of the course was to introduce the concept of Physics Informed Deep Neural Networks (PINN) and Neural Operators (NOs), discuss their implementation from scratch in PyTorch and using advanced ad-hoc developed open-source libraries such as NVIDia PhysicsNeMo to address real-world problems in various fields (engineering, physics, petroleum reservoir). We discuss recent topics such as Mixture-of-Models,
Fourier Neural Operators, Physics-Informed Kolmogorov-Arnold Networks (PIKANs) and
Fourier Neural Operators.
Read the full abstract ▾
Artificial Intelligence
What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization
Narcis Marincat
Restricting what a module can read may improve what a system learns to compute. We test this in a preregistered confirmation with sixty four-
cell systems sharing a frozen
language-model backbone and communicating through learned continuous packets. Five conditions vary evidence masking, ownership markers, and replacement of foreign evidence with neutral filler (task-irrelevant text of the same
token length), across six initialization clusters, each with two data orders, on one fresh task world. With markers available in both regimes, masking improved accuracy on held-out two- and three-operation compositions by median paired differences of 0.846 and 0.859; all twelve pairs cleared the required margins, and the full preregistered behavioral criterion passed. The unmarked replication also passed. No marked global-visibility (G+) system passed the marker-following check, so the effect of usable role information remains unresolved. The filler condition yielded seven full generalizers, but its decomposition criteria were inconclusive. Packet interventions in all eighteen audited masked systems followed the predicted intermediate-value changes on eligible cases; these finite, success-conditioned audits do not establish mediation. The results confirm a large advantage of the tested masking regime, while leaving its finer attribution and generality open. Protocols, results, and checkpoints are public.
Read the full abstract ▾
Artificial Intelligence
Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
Oscar Mogollon Gutierrez, Fatemeh Ghasemi, Mohammadhossein Homaei et al. (+2 more)
City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the incoming stream as ground truth. We study what happens when it is not. We formalise stealthy false data injection for city-scale pedestrian sensing, where the map from latent flow to observation is far more rank deficient than in the power and water networks for which stealth has been characterised. Our twin estimates directed flows on the pedestrian street graph, assimilates counts through a learned graph-localised gain, and is trained against a flow conservation residual that couples metered and unmetered segments. Detection combines the innovation with that residual, and the alarm threshold is set by adaptive conformal calibration rather than by hand. To measure what the physics buys, we define the attack margin, the relative reduction in worst-case corruption of the estimated flow field, achieved against a white-box adversary that optimises directly through the twin. On six years of Melbourne data the margin reaches 0.54 against a single compromised device and falls to 0.19 when a third of the fleet is compromised, on a network where only 1.18 per cent of walkable segments are metered. Replacing the street graph by a distance graph collapses it to 0.09, which shows that the gain comes from the conservation law rather than from locality.
Read the full abstract ▾
All authors Oscar Mogollon Gutierrez, Fatemeh Ghasemi, Mohammadhossein Homaei, Andres Caro, Mar Avila
Artificial Intelligence
One Color Preprocessing Improves DSATUR
Adam Nouira and Lucas Isenmann
The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it despite producing colorings that typically use more colors than state-of-the-art coloring
algorithms. We propose SSLD (Semidefinite Spectral Learning with DSATUR), which improves DSATUR by preprocessing a first good color class before letting DSATUR complete coloring the rest of the given graph. We obtain this color class from a Semidefinite Programming (SDP), similar to an SDP used to compute the Lovász theta number. To the best of our knowledge, SSLD is the first approach to improve DSATUR by preprocessing through fixed color classes. We evaluate SSLD against DSATUR and against a naive 1-color-class preprocessing
algorithm on DIMACS instances, random graphs (Erdős–Rényi, Watts-Strogatz, Barabási–Albert), Frequency Assignment and Job Shop Scheduling instances. SSLD matches or beats DSATUR in almost every case across over 1600
benchmark instances, and out performs the naive GISD baseline, allows us to confirm the value brought by the SDP-guided choice of the first color class. This quality comes at a runtime cost of roughly 195 times slower that DSATUR, but demonstrating that SDP-guided preprocessing of a first color class is a direction for future improvements.
Read the full abstract ▾
Artificial Intelligence
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Sehee Kim, Yumin Choi, Minki Kang et al. (+1 more)
Large
language model (LLM) trading
agents can combine
market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment. This limits their ability to adapt how they gather evidence, invoke tools, verify signals, and manage risk under changing
market regimes. We introduce EvolveTrade, a self-evolving framework that treats the system
prompt of a tool-using trading
agent as a text-parameterized policy. After each update interval, a Policy
Agent revises this policy using accumulated decision traces and realized portfolio feedback, while keeping the backbone LLM fixed. The updated policy is then used for the next batch of trading decisions, enabling the
agent to refine its information-acquisition and portfolio-construction procedure over time. Experiments across multiple
market regimes and two LLM backbones show that EvolveTrade often improves Sharpe Ratio and Cumulative Return over fixed-policy LLM baselines, achieving the improved SR and CR in most evaluated settings. Behavioral analyses further show that self-evolved policies increase code-mediated analysis and activate regime-relevant computations; case-level policy-to-return attributions trace how policy-induced allocation changes contribute to realized return differences. These results suggest that adapting the reusable procedure governing tool use is a key direction for building more robust LLM trading
agents.
Read the full abstract ▾
All authors Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang
Artificial Intelligence
Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records
Torsten Olivi Tiltack, Yifei Dong, Kun Yu et al. (+5 more)
AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation, and correction history describe different states. We develop Publication Authority: an exact-state, non-transferable, single-use publication capability within PAC-2026 (Publication-Accountability Calculus), an AIJIM Protocol candidate. The evaluated specification version (SF-4) defines six non-compensating obligations: evidence, runs and artifacts, measurement disclosure, authorization, surface correspondence, and lifecycle continuity. Each yields a target-bound witness, localized counterexample, or localized unverifiability. Only a fresh, complete all-pass record derives a permit consumed by one atomic publication transition. Ten models explored 110,764 distinct safe reachable states; 76 unsafe configurations yielded the expected violation or observer countermodel. A surface passing its correspondence check cannot authorize publication unless admitted by the accepted record. SF-4 separates evidence horizon from verification time and rejects authentic but causally invalid authorization. An in-house, instance-blind study (G7-B) matched 183 scored expectations after shared integration. Three author-led native comparisons identify gaps in a constructed in-toto/OPA profile: measurement-state admission, proof-expiry evaluation, and required-run identity. Repairs restore parity on the tested cases. An exploratory extension constructs exact claim-edit regions under existing e-closure semantics: a minimum retained core qualifies every permitted selection. For the full hypothesis universe (U=H), a quadratic frontier computes all strongest-core sizes. Enumeration and native controls distinguish reusable statistical qualification from the fresh publication authority each candidate requires. Results yield transferable protection rules; independent conformance and field evaluation remain open.
Read the full abstract ▾
All authors Torsten Olivi Tiltack, Yifei Dong, Kun Yu, Xu Wang, Wei Liu, Jianlong Zhou, Ren Ping Liu, Fang Chen
Artificial Intelligence · Cross-listed from cs.MA
Agentic Societies Need a Social Harness
Tapan Chugh, Vidushi Singh, Krish Jain et al. (+2 more)
An agentic society is a collection of AI
agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectives may only partially align. We show experimentally that in agentic societies even honest, competent
agents often fail to reach satisfactory outcomes with existing harnesses and messaging primitives, and that faulty or malicious
agents can stall collaboration, influence outcomes, and pursue other harmful goals by exploiting vulnerabilities in communication (“
speech”). We argue that agentic societies need a social harness for inter-
agent interactions, in addition to each
agent's personal harness, which manages its private context and communication with its principal. We propose a layered architecture for social harnesses which (i) prevents classes of failures outright, (ii) enables
agents to detect invalid messages at runtime, and (iii) supports post-facto investigation and consequences, and highlight directions for future research to realize these capabilities.
Read the full abstract ▾
All authors Tapan Chugh, Vidushi Singh, Krish Jain, Arvind Krishnamurthy, Ratul Mahajan
Artificial Intelligence
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Shuhan Xue, Jianyuan Zhong, Ziyuan Nan et al. (+10 more)
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific
agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness
evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Harness
evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the
benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: http://science-buddy.io
Read the full abstract ▾
All authors Shuhan Xue, Jianyuan Zhong, Ziyuan Nan, Wenbin Li, Zhaochen Yu, Jinchao Ding, Qiang Gao, Pengyu Zhan, Yuntong Zhang, Tian Cheng, Zhenfei Yin, Yingcheng Wu, Ling Yang
Artificial Intelligence · Cross-listed from cs.CV
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Chuhao Chen, Peter Wonka, Chaoyang Wang et al. (+4 more)
Interactive control for
video generation is moving from coarse
prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet existing controllable methods either require the full control schedule before generation starts, or use pixel-space signals that dictate object positions rather than physical dynamics. To address these limitations, we propose PhysStream, an autoregressive model for physics-grounded image-to-
video synthesis that incorporates structured scene
memory—positional maps and object tracking maps derived online from previously generated frames—and supports fine-grained motion control via sparse velocity-increment signals that encode physical quantities, letting the model learn the underlying dynamics. We train our model in two stages: a bidirectional model is first finetuned with motion-control conditioning, then a causal autoregressive model is trained with additional structured scene
memory, further improving physical consistency. PhysStream enables interactive, mid-generation control over multi-object tabletop rigid-body scenes—a capability not supported by prior methods—reducing motion distribution distance (FVMD) by 33% and trajectory error by 12% over the strongest baselines on synthetic
benchmarks, and is preferred by human evaluators in over 85% of in-the-wild comparisons. Please check our website for more details: https://czzzzh.github.io/PhysStream
Read the full abstract ▾
All authors Chuhao Chen, Peter Wonka, Chaoyang Wang, Chen Wang, Qiao Feng, Sergey Tulyakov, Lingjie Liu
Artificial Intelligence · Cross-listed from cs.CL
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
Ali Şenol
Large
language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a
prompt-only framework that makes answer commitment conditional on an explicit assessment of the information required to answer a question. We evaluate three CoSQ variants under seventeen conditions on the 817-item TruthfulQA multiple-choice validation set using eleven open-weight and hosted model families. In the final balanced-option protocol, Grounded-CoSQ at {\tau}=0.90 reduces the mean unconditional wrong-commitment rate from 13.1% under chain-of-thought prompting to 8.9%, a 32.1% relative reduction, while increasing answered accuracy from 86.9% to 89.7% and answering 87.6% of questions. Both improvements hold for all eleven models and at every evaluated threshold. Critical-CoSQ and Adaptive-CoSQ provide neighboring operating points with 88.6% and 86.5% coverage, respectively, while remaining more reliable than the baseline. A secondary Natural Questions Short-Answer evaluation provides convergent open-form evidence. These findings show that self-assessment can support explicit, tunable answer-or-abstain decisions when an unsupported commitment is more costly than referral or review.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
Thanapat Trachu, Samuele Cornell, William Chen et al. (+1 more)
Neural audio codecs are a key component in
speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computational costs. Dynamic frame rate codecs mitigate this by reducing the effective frame rate using a compression step to merge multiple frames together. However, most prior methods either operate on single-codebook codecs or apply a single compression step before multi-layer quantization. This forces all quantization layers to share the same
segmentation boundaries, despite the residual
embeddings at different quantization layers exhibiting different rates of change over time. We propose LACE (Layer-Adaptive Codec Encoding), a dynamic frame rate codec that applies an independent compression step at each quantization layer, enabling layer-specific
segmentation boundaries. To use LACE
tokens in downstream text-to-
speech (TTS), we further introduce union
alignment and boundary anchor mechanisms to make durations consistent across layers while preserving compression benefits. Experiments on LibriTTS show that LACE offers a better rate-quality tradeoff than prior dynamic frame rate methods on the reconstruction task and improves TTS inference efficiency while maintaining competitive synthesis quality. Our code is released as part of the ESPnet3 codec recipe.
Read the full abstract ▾
All authors Thanapat Trachu, Samuele Cornell, William Chen, Shinji Watanabe
Artificial Intelligence · Cross-listed from cs.LG
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
Vicky Feliren, A. Taufiq Asyhari and Muhamad Risqi U. Saputra
Uncertainty estimation for
Vision-
Language-
Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling
agents to make safer
navigation decisions. As one of the most advanced uncertainty estimation frameworks, conformal prediction (CP) offers a promising approach for uncertainty estimation in VLN. However, given that VLN
agent requires a sequence of steps, standard calibration in conformal prediction fails to provide coverage guarantee it promises over a dependent, variable-length VLN episode. To this end, we propose Episode-Normalized Conformal Prediction (ENCP), which rescales a nonconformity score by the policy's residual confidence and calibrates one maximum score per episode. Under exchangeable calibration and test episodes, this construction covers the ground truth at every step with probability at least $1 - \alpha$, while allowing dependence among steps within an episode. Across four VLN policies and three nonconformity scores on R2R and REVERIE
dataset, ENCP meets all reported empirical step-coverage targets on the seen-to-unseen evaluation. These results demonstrate that ENCP can provide model-agnostic uncertainty estimates, which might be useful for determining when a VLN
agent should defer to a more capable predictor, including human assistance.
Read the full abstract ▾
Artificial Intelligence
Verifiable Social Reasoning for LLM Assistants
Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush et al. (+6 more)
LLM assistants are widely used for daily social advice, yet evaluating their social
reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others' intentions, typically lack verifiable ground truth. To address these challenges, we introduce Fuse, a multi-
agent simulation framework for studying user-mediated social
reasoning. In Fuse, a target
agent with a hidden motive interacts with other
agents including one representing the user, who then consults the evaluated assistant to infer the target's motive, providing verifiable ground truth by construction. Simulation faithfulness is validated through a human study with 24k annotations. We apply Fuse to 12 LLMs and demonstrate its analytical utility by systematically isolating key factors, showing that (i) user mediation compounds the inherent difficulty of social
reasoning; (ii) LLMs exhibit systematic sensitivity to biased user framing; (iii) models can require more details than humans need to reach a correct prediction; and (iv) longer conversations do not always improve performance despite providing opportunities for clarifying questions. We open-source Fuse and a
dataset with 21k examples.
Read the full abstract ▾
All authors Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush, Itay Laish, Ariel Goldstein, Marian Croak, Avinatan Hassidim, Yossi Matias, Amir Feder
Artificial Intelligence
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
Xingxuan Zhang, Gang Ren, Hao Yuan et al. (+57 more)
We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic
datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current
dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature
attention encodes direct causal relationships, enabling accurate causal skeleton recovery.
Read the full abstract ▾
All authors Xingxuan Zhang, Gang Ren, Hao Yuan, Hao Zou, Hongze Tan, Hui Wang, Jianhao Song, Jiansheng Li, Jiayao Zhang, Jinghan Zhang, Kaifang Li, Lang Mo, Li Mao, Mingchao Hao, Nuo Xu, Rui Ding, Ruiji Zhang, Shuyang Li, Siyu Mei, Tianyang Zhang, Weiyang Mu, Yancheng Dong, Yongxian Wei, Yuan Xue, Yuanrui Wang, Yue He, Zijia Yang, Ziyun Li, Dongzhe Li, Fuqiang Wang, Jiandong Liu, Jiawei Chen, Jiaxin Du, Kaijie Cheng, Kehan Li, Lei Sun, Linjun Zhou, Ningbo Dai, Qi Wang, Renzhe Xu, Shaoxing Du, Shumeng Yang, Wang Lu, Wenjing Chu, Xiannan Huang, Xiaoyu Lin, Xing Ai, Xinyan Han, Xuanyue Li, Xuanyue Su, Xukun Zhang, Yan Lu, Yaxin Zhang, Yi Qin, Yifei Huang, Yihan Xu, Yongle Lv, Yuanyuan Jiang, Yushan Han, Peng Cui
Artificial Intelligence · Cross-listed from cs.CV
Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
Jiayi Zhou, David W. Johnston and Brinnae Bent
Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthermore, most classification-oriented explainability tools are ill-suited to detection tasks involving imagery of social organisms or those with colonial life histories, as they ignore multiple detections within a scene and produce single-instance outputs that blur evidence across individuals. These methods also generate low-resolution, often biologically irrelevant visuals, limiting their utility for debugging, targeted data augmentation, and refined data collection. We proposed Det-LIME, a detector-aware, multi-instance adaptation of Local Interpretable Model-Agnostic Explanations (LIME) that produced instance-specific, box-aligned explanations by combining per-detection weighting, a proximity kernel that emphasizes regions near each box, and Intersection-over-Union-based matching to track the same instance across perturbations. We evaluated Det-LIME on aerial drone imagery for harbor seal detection, with an additional seabird case study to assess generality, and compared it with vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient-based attribution methods. Using the Attribution Ratio and Max Saliency Hit Rate metrics, we showed that Det-LIME consistently improved multi-instance attribution. In practice, these higher-resolution, instance-aware explanations provide insight into model outputs and support post-processing, debugging, and actionable improvements in modeling and data collection or augmentation.
Read the full abstract ▾
Artificial Intelligence
JustFit: Just-in-Time State Management for Local LLM Serving
Yuhua Chen
Local
agents need
memory for model execution and working history. We present JustFit, an MLX runtime that coordinates their overlapping allocations: KVExec executes and checkpoints four-bit KV with bounded workspace, PhaseSwap loads phase-dependent components, and StateTrans preserves history across execution modes. With Qwen3.8-27B MXFP4 on a 24 GiB M4 Pro MacBook, JustFit reaches 327,680 retained positions across two requests, 10.67 times the evaluated baseline's 30,720-position single-request record. One request completes the full 262,144-position native window at median 5.986
tokens/s. Each shape completes 16,384 outputs per request in three fresh processes: B1 uses one cold build and two prefix extensions; B2 uses three ordered prefix extensions (Section 4). Image encoding can proceed while preserving a live 196,608-input text request. A controlled, repetitive 32K+6K workload reaches median 18.284
tokens/s at 15,626 MiB; a separate AIME 2026 evaluation scores 29/30. Coordinating execution and state lifetimes makes longer histories feasible on personal hardware.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
Haichen Hu, Yuheng Zhang and David Simchi-Levi
Large
language model (LLM)
distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can also transfer the teacher's systematic bias and errors. This challenge is particularly pronounced under
covariate shift, when the teacher's reliability on target questions is uncertain and target-domain reward feedback is unavailable. We propose Coupled Calibration and Learning (CCL), an LLM
distillation algorithm that couples teacher calibration with student updates through
token-level branching, using reward feedback only on source questions. Each iteration calibrates the teacher using source feedback and then uses the calibrated teacher to train the student on target questions. The updated student, in turn, informs subsequent calibration. In an autoregressive policy framework, we prove that the output student's expected average Kullback-Leibler divergence to the oracle student converges to zero at a
polynomial rate in the number of iterations. The oracle maximizes the true reference-regularized target reward within the student class, which need not represent the unrestricted optimal policy. Our analysis quantifies the progress of projected student gradient updates while controlling the error in teacher calibration. We further establish a separation from regularized direct matching: its error relative to the oracle student can remain bounded away from zero even when the teacher achieves higher regularized target reward than every student policy. These results demonstrate that LLM
distillation can overcome persistent teacher bias and recover the optimal student through coupled calibration and learning, without target-domain reward feedback.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
Decomposition Buys Integrity, Not Yield
Rong He
Multi-
agent systems split a task across a tree of
agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We ask what the split does to how much of what the leaves discover reaches the root. Model a decomposition as a tree in which an
agent handed $b$ items keeps any one with probability $r(b)$. If $r(b)=1/b$, every tree delivers exactly one finding, for every task size and every shape; we verify this to $2.4 \times 10^{-15}$ on 20,000 random irregular trees. If $r(b)=Cb^{-\delta}$, a depth-$k$ tree over $N$ findings yields $C^k N^{1-\delta}$: task size and architecture separate, and architecture contributes only $C \le 1$ per level, so flat is optimal for yield and no arrangement of
agents escapes the exponent $\delta$. On 600 production deep-research traces $\delta = 0.34$ [0.30, 0.38], by three identifications that do not share a failure mode. At a hop where item boundaries come from the tool rather than a text heuristic, and where $b=1$ occurs 550 times, $C = 0.571$ [0.527, 0.615] is observed rather than extrapolated, over 16,082 hops. A tier also costs
alignment: on 1,012 annotated multi-
agent traces one brief in sixteen goes off-target, giving $\mu = 0.939$ and a per-tier penalty $C\mu = 0.536$. Depth is bought on two other axes. The root context is the only state that persists and the only one that cannot cheaply forget, and depth cuts its exposure from $N$ items to $N^{1/k}$. Depth is also cheaper: production flat
agents bill as $N^{1.39}$, not the $N^2$ an append-only context predicts, and at equal spend two tiers overtake flat at 403 findings. Across every parameter we measured the model says 0.7% to 11.3% of production sessions are worth delegating, against 7.8% that do. A hazard model on 743,819 production tool calls finds that delegation does not respond to a filling context and is instead an opening move.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from quant-ph
Evaluating Verified Autonomy in Quantum Engineering
Naixu Guo, Changhao Li, Siyu Cheng et al. (+6 more)
Reliable
quantum engineering is essential for turning
quantum phenomena into practical technologies. As
quantum platforms grow in scale and complexity, their characterization and operation require increasing human effort and coordination. Scientific artificial intelligence
agents, which can plan experiments, operate instruments, and analyze observations, offer a promising route towards autonomous
quantum engineering. Yet whether current
agents can perform reliably in this setting has not been systematically established. To fill this gap, we developed
Quantum-Harbor, a virtual laboratory that provides a controlled execution environment for
agents to interact with
quantum systems. This design enables direct verification of both the actions taken and the conclusions drawn. Building on this framework, we introduce QIQCBench, a
benchmark of $49$ expert-authored tasks spanning multiple layers including calibration and control, error correction and compilation, sensing and networking. Across $17$ frontier agentic systems, QIQCBench reveals wide variation in verified performance. These results expose a substantial gap between demonstrating capability and achieving reliable operation, and establish
Quantum-Harbor as a foundation for measuring progress towards verified autonomy in
quantum engineering.
Read the full abstract ▾
All authors Naixu Guo, Changhao Li, Siyu Cheng, Qicheng Tang, Binzhao Luo, Bikun Li, Yuxuan Du, Shihao Ru, Jiaqi Cai
Artificial Intelligence · Cross-listed from cs.HC
CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem
Jiayue Melissa Shi, Ethan Nguyen, Drishti Goel et al. (+7 more)
Family caregivers of people living with dementia shoulder emotional and practical responsibilities, yet their own wellbeing often remains peripheral to dementia care. We built CareMirror, an envisioned caregiver wellbeing ecosystem with interconnected caregiver- and clinician-facing interfaces for longitudinal reflection, personalized support, and caregiver-controlled sharing with clinical care. We conducted semi-structured interviews with 14 caregivers, using CareMirror as a design probe to examine how they perceived this ecosystem and what expectations, concerns, and boundaries emerged around clinical connection. Caregivers valued
attention to their wellbeing, longitudinal awareness, context-sensitive support, and clinical visibility when it could lead to meaningful follow-up. However, repeated reflection could become burdensome or emotionally difficult, automatic clinical sharing could inhibit candid disclosure, and participants wanted control over what information entered clinical care. They also expected AI to support reflection and communication without replacing caregiver voice or clinician judgment. We contribute design considerations for proactive, clinically connected caregiver wellbeing support.
Read the full abstract ▾
All authors Jiayue Melissa Shi, Ethan Nguyen, Drishti Goel, Upasana Natarajan, Shashwat Srivatsa, Daniel S. Brown, Violeta J. Rodríguez, Dong Whi Yoo, Ravi Karkar, Koustuv Saha
Artificial Intelligence · Cross-listed from cs.LG
Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
Liang-Ching Tao and Pi-Chung Wang
Many learned sequential decision systems map the current state directly to an action. That shortcut becomes brittle when candidate actions are numerous, geometrically structured, and rebuilt with the state. One-to-many mobile charging makes this setting concrete: with N=250 sensors, the initial state induces about 1,125 candidate charging-stop actions; each chosen stop simultaneously serves its in-range sensors, and the action universe changes as sensors die. LP-BTS is a learning-guided planning architecture: a graph proposal policy concentrates a small candidate support, a learned value critic evaluates leaves, and edge-budgeted PUCT compares short simulated futures before committing an action. Because the policy scores this set without a fixed output head, a single frozen checkpoint covers every evaluated setting, spanning action universes from 736 to 2,813 stops. Matched ablations reveal complementary effects: uniform sampling costs 8.8 survival percentage points, while, with targeted support fixed, PUCT jointly retains 1.4 points (about 3.5 of 250 sensors) and direct policy selection travels 23% farther. On a prospectively specified, sealed 30-scenario confirmatory bank evaluated once, LP-BTS attains the highest observed survival (0.4545) and alive-AUC (0.8031). Its estimated survival advantage over the strongest domain-engineered comparator is +0.0066 (95% CI [-0.0037, +0.0184]), an unresolved difference, while it exceeds a deadline heuristic and two source-derived direct-policy reconstructions on every paired scenario. Both learned rows are trained, source-derived reconstructions of variants reported by Gong et al. In this setting, the results provide controlled evidence about learning-guided planning in a large, dynamic action space.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion
Mais Mohammed, Sharifa Mohammed, Hanan Awadh et al. (+3 more)
Real-time multi-object tracking systems remain highly vulnerable to full and long-term occlusion, where targets temporarily or completely disappear from the camera's field of view. Conventional trackers may terminate trajectories prematurely, resulting in identity loss and reduced situational awareness in applications such as defense and surveillance. This work proposes an occlusion-robust target tracking framework that maintains target identity and trajectory continuity through the integration of YOLOv11n object detection, Kalman Filter motion prediction, and occlusion-aware appearance-based re-identification. The framework consists of three stages: object detection, position estimation during occlusion, and identity recovery after target reappearance. Six Re-Identification (Re-ID) architectures were evaluated within the same tracking framework under identical conditions, with the Occlusion-Aware Mask Network (OAMN) achieving the best overall performance and therefore selected for the final pipeline. The framework was benchmarked against OccluTrack on the public OVIS
dataset, achieving relative improvements of 18.1 percent in Multiple Object Tracking Accuracy (MOTA) and 25.1 percent in Identity F1 Score (IDF1), while reducing identity switches by 12.8 percent. On a custom military
dataset simulating surveillance and battlefield-like environments with long-term occlusion, the framework achieved a MOTA of 0.734 and an IDF1 of 0.729, corresponding to relative improvements of 14.2 percent and 5.8 percent over OccluTrack. The system demonstrated strong tracking continuity, robust identity preservation, and reliable trajectory estimation under challenging occlusion conditions, highlighting its effectiveness for defense-related surveillance applications requiring continuous target tracking during visibility loss.
Read the full abstract ▾
All authors Mais Mohammed, Sharifa Mohammed, Hanan Awadh, Haneen Bamaas, Raghad Bawazeer, Elham Alghamdi
Artificial Intelligence · Cross-listed from cs.SE
Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead
Fengshuo Liu, Ying Liu, Ruize Sun et al. (+2 more)
Small differences on coding-
agent leaderboards are often read as an ordering of systems. We audit whether the published verdicts support this reading, using 254 SWE-bench submissions across four splits without running models. On Verified, the leading two entries each resolve 396 of 500 instances. The top ten share 285 successes and 51 failures, leaving 164 instances that distinguish their outcomes. Frontier solution sets have median nesting 0.935 against a score-implied baseline of 0.774, indicating strongly shared successes. Scores also depend on the evaluated model-scaffold pair: observed within-model scaffold ranges reach 29.8 percentage points, compared with the 8.8-point spread of the top thirty. Six of nine
cell-mean interaction tests remain significant after Holm correction, although this observational design does not identify causal scaffold effects. Exact paired McNemar tests separate none of the 29 adjacent Verified top-thirty pairs at alpha=0.05, while the larger Test split separates 14 of 23. A stated leader-based rule yields three descriptive tiers, or two after Holm correction; non-rejection does not establish equivalence. We release the partition and a five-step audit protocol that profiles shared outcomes, tests paired differences, reports grouping sensitivity, and estimates the instance budget needed for resolution. The results motivate reporting comparison-set-specific resolution and model-scaffold provenance instead of interpreting small aggregate gaps as established rank differences.
Read the full abstract ▾
All authors Fengshuo Liu, Ying Liu, Ruize Sun, Lie Luo, Siyuan Guo
Artificial Intelligence
FlashVector: Agent for Hierarchical Model Serving Stack Optimization
Qi Wu, Lohan Lemire, Kai Meng et al. (+8 more)
Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hierarchy: GPU kernels, the ML framework computation graph, the model server, and on-demand feature processing – each demanding specialized domain expertise. Such cross-layer expertise is inherently difficult to acquire, and does not scale with a workload that continuously grows and evolves, leaving significant cost efficiency gains unrealized. While recent AI
agents have demonstrated human expert level efficiency in standalone GPU kernel optimization, automated tuning and optimization for the rest of the serving stack remain largely unexplored. We present FlashVector, an agentic system that optimizes performance across all layers of the model serving stack. The key contribution is an extensible framework to generalize the single kernel optimization
agent paradigm to heterogeneous technical stacks, and to deliver performance improvements holistically. After deployment in Unity's Vector advertising platform, FlashVector achieved up to 2x throughput increase and up to 1.98x latency speedup on model server, and up to 1.6x throughput increase on feature store. These optimizations were discovered not only at the GPU kernel and computation graph levels, but also across the other components of the model serving stack, such as the model server (NVIDIA Triton's C++ codebase) and the on-demand feature transformation service (Python codebase), demonstrating the extensibility of the framework to more complex system architectures.
Read the full abstract ▾
All authors Qi Wu, Lohan Lemire, Kai Meng, Zhongmou Cai, Raphael Bargues, Petr Zhitnikov, Zeyuan Cao, Yao Wang, Shujun Bian, Wei Chen, Sean Sheng
Artificial Intelligence · Cross-listed from cs.CL
Where Should a Document Live: Context, Representations, or Parameters?
Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias et al. (+1 more)
To answer questions outside of their pre-training data, large
language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive
benchmarks. We show that in the oracle setting, Cartridges (KV) are the most accurate injection method at nearly every storage budget, outperforming parametric methods by 10 points. Compaction (KV) matches Cartridges only at low compression rates, lagging behind the parametric methods by 10 points at rates higher than $50\times$. In the more realistic multi-document
retrieval scenario, Cartridges are the only method that matches in-context learning (ICL), leading the parametric methods by 29 points and Compaction by 15 points. Nonetheless, Cartridges are also the only method, besides full fine-tuning and large MLP adapters, that suffers from catastrophic forgetting, i.e., a 6% performance degradation on control
benchmarks, with 13% in coding.
Read the full abstract ▾
All authors Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias, Adrià de Gispert
Artificial Intelligence
Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling
Xiaoyang Liu
Large
language model (LLM)
agents exhibit strong
language-generation and problem-solving capabilities, yet suffer from three structural limitations: personality drift, non-evolutionary reflection, and the absence of a self-other boundary. Existing generative-
agent simulations rely on static
memory and fixed
prompts, maintaining neither behavioral inertia nor endogenous self-
evolution. We propose the Self-Emergence
Agent Architecture (SEAA), which integrates three components: (i) a Hidden Markov Model (HMM) that encodes long-term behavioral and cognitive inertia as an editable state-transition
matrix; (ii) a Reflexion-style verbal metacognition loop whose output updates the HMM parameters themselves, rather than merely being stored as text; and (iii) a multi-
agent social environment in which initially identical
agents continuously compare their behavior with others'. The three components form a closed loop: social action $\to$ feedback $\to$ self-reflection $\to$ inertia update $\to$ differentiated action. We state three falsifiable hypotheses and provide a reproducible experimental protocol with operational metrics. A
language-model-free prototype shows the loop spontaneously breaks
symmetry: initially identical
agents consolidate distinct, stable personalities whereas matched controls do not. Experiments with a hosted LLM surface these differences as distinct first-person self-narratives, and a five-
agent deliberation spontaneously develops social structure—a consensus hub and a unanimously rejected outlier—absent in the control. Following an epistemologically agnostic stance inspired by Zhuangzi, SEAA studies only observable behavioral emergence and makes no claim about subjective qualia. This work contributes a unified framework, a concrete architecture with pseudocode, mechanistic evidence, and a microscope-style sandbox for studying artificial-self emergence.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs
Toqeer Ehsan, Nico Penttilä, Richard Schmidt et al. (+2 more)
This paper describes our submission to the SHROOM-
Visions shared task on detecting and classifying hallucinated character spans in
vision-
language model outputs across four
languages. We employ several fine-tuned
vision-
language models as independent annotators and combine their span predictions through character-level majority voting, and additionally explore activation probes. The approach ranks first in three of four
languages and places on the podium in every
language and metric. Our analysis indicates that disagreement among diverse models tracks disagreement among human annotators.
Read the full abstract ▾
All authors Toqeer Ehsan, Nico Penttilä, Richard Schmidt, Arash Hajikhani, Victoria Palacin