Artificial Intelligence
Demystifying Agent Skills: Why They Work-Until They Don't
Zhiyuan Jiang, Fangrui Huang, Hanwen Xing et al. (+6 more)
Skills have emerged as a practical and effective approach for enhancing LLM
agents at inference time through structured packages of knowledge. However, existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: \emph{When do skills help, why do they work, and where do they fail?} Through controlled experiments across various
benchmarks,
agent harnesses and LLMs, we isolate the effects of representation, outcome annotation,
retrieval difficulty, and cross-framework robustness of skills. To further answer this question, we design a contrastive study that combines controlled quantitative experiments with paired trajectory analysis. We normalize 8,135 trial records from controlled experiments and retain 238 valid unique labels from 240 open-coded records. We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes: skills work when noisy trajectories become procedural anchors that stabilize execution. Skills improve over Workflow
Memory by 6.06 points in matched comparisons. Procedural anchoring accounts for 65.7% of skill cases, versus 4.5% for explicit knowledge injection, showing that skills stabilize action rather than inject missing facts.
Retrieval is a separate bottleneck: as pools grow from 5 to 100, actual-use precision falls from 29.6% to 3.3%. Confusable distractors impair offline identification, yet downstream success remains stable; exact ground-truth invocation is neither sufficient nor necessary. Skills fail under brittle assumptions, incompatible contexts, or insufficient adaptation. These findings move evaluation beyond aggregate success rates and guide reliable self-evolving
agents.
Read the full abstract ▾
All authors Zhiyuan Jiang, Fangrui Huang, Hanwen Xing, Xander Wu, Yipeng Gao, Rui Cao, Mengdi Wang, Shilong Liu, Yijiang Li
Artificial Intelligence
Agent-Orchestration in Autonomous Chip Design
Linyang Li
Recent developments in large
language models (LLMs) and tool-using
agents encourage people to explore the potential of using
agents in chip design. The core question is what kind of AI we really need in such a sophisticated industry. To this end, we bring the idea of modeling a chip-design superintelligence as an enormous AI-organization.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation
Yin Li, Ziyang Hu, Zhiyu Guo et al. (+7 more)
Existing
multimodal RAG methods often flatten structured documents into isolated text and image units, weakening the source organization and local text-image logic needed for faithful evidence selection and placement. We propose HAM-RAG, a Hierarchy-Aware
Multimodal RAG framework for structure-faithful interleaved generation. HAM-RAG uses document hierarchy as a grounding signal across
retrieval and generation, contextualizing textual and visual evidence and preserving source position and local text-image relations in the
prompt. We further introduce HAM-Bench, covering Wukong, Wiki, arXiv, and Recipe across game walkthroughs, web pages, scientific papers, and step-wise recipe documents. Across multiple backbones, HAM-RAG improves the main
multimodal average by 17.3% over the strongest non-hierarchical baseline. On Wukong, HAM-RAG improves Img-CBS by 24.2% over the strongest non-hierarchical baseline, demonstrating substantially better local text-image
alignment. The main experiments and ablation study together demonstrate that document hierarchy is a key grounding signal for faithful image selection, placement, and local text-image
alignment. These findings highlight the value of hierarchy-aware grounding for reliable
multimodal assistants that generate answers faithful to the source organization, procedural structure, and local text-image evidence of structured documents, such as technical manuals, maintenance guides, and industrial SOPs. The code is available at https://github.com/MCCodeAI/HAM-RAG.git.
Read the full abstract ▾
All authors Yin Li, Ziyang Hu, Zhiyu Guo, Xiangyu Liu, Wenbin Li, Boo-Ho Yang, Rav Lawana, Ziyue Li, Wei Zeng, Fugee Tsung
Artificial Intelligence · Cross-listed from cs.RO
AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning
Zhiyue Zhao, Jingyi Wu, Hairuo Liu et al. (+5 more)
Dexterous manipulation is a fundamental capability for
embodied intelligence, but scaling it remains difficult because
robot demonstrations are expensive to collect and action spaces vary across embodiments. Policies trained on heterogeneous data can also entangle task-relevant visual cues with embodiment-specific appearance, limiting cross-embodiment generalization. We present AdvDex, a unified
Vision-
Language-Action framework for learning dexterous manipulation from human and
robot demonstrations. First, we introduce OmniShare, a large-scale
multimodal dataset of human manipulation demonstrations that provides high-quality kinematic supervision and tactile measurements while reducing reliance on
robot teleoperation. Second, we propose the Joint-Aligned Action Space (JAAS), a canonical action representation comprising an $\mathrm{SE}(3)$ wrist pose and 15 finger joints, thereby functionally aligning human hands, dexterous
robot hands, and parallel grippers. Finally, we use domain-
adversarial learning to reduce embodiment-specific information in the learned visual representation. Experiments on hand-action prediction and real-world dexterous manipulation show consistent improvements over baselines, effective zero-shot human-to-
robot skill transfer, generalization to unseen objects and environments, and data-efficient few-shot adaptation.
Read the full abstract ▾
All authors Zhiyue Zhao, Jingyi Wu, Hairuo Liu, Mingyu Liu, Liyang Li, Hengdi Zhang, Tong He, Zhengxue Cheng
Artificial Intelligence · Cross-listed from cs.CV
ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models
Xinye Li, Lingshuai Lin, Lei Wang et al. (+8 more)
Action-conditioned
video world models require low-latency causal generation and reliable responses to game-native controls. Although causal
distillation enables one- or few-step
video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressed latent chunks during causal training and autoregressive rollout. We introduce ForgeWM, a progressive framework that transforms a bidirectional action-conditioned
video generator into efficient few-step world models through domain adaptation, teacher-forced causal training, causal consistency
distillation, and on-policy distribution matching with a bidirectional teacher. The resulting budget-specialized students operate at steady-state denoising budgets of 1, 2, and 4 steps. ForgeWM further supports a dual-path deployment protocol combining latency-critical interaction with optional replay-time refinement, where the one-step student re-noises and refines its saved draft. On paired Minecraft trajectories, ForgeWM leads the evaluated systems in Imaging Quality, reference-aligned motion-profile agreement, action-sign accuracy, and mouse-control accuracy, while achieving the lowest reference LPIPS; the same four-stage recipe transfers to gamepad-controlled FPS gameplay. Replay-time refinement matches four-step reference quality while remaining roughly three times closer to the experienced trajectory than regeneration from noise. These results demonstrate ForgeWM's effectiveness for controllable few-step
video generation.
Read the full abstract ▾
All authors Xinye Li, Lingshuai Lin, Lei Wang, Liuzhou Zhang, Jialin Cui, Qingshan Li, Guanchu Wang, Qingbin Liu, Xi Chen, Jiang Bian, Wai Lam
Artificial Intelligence
Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders
Keito Kozaki, Keigo Sakurai, Ren Togo et al. (+2 more)
Transformer-based sequential recommenders with causal self-
attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for prediction remains unclear. We combine prediction-time diagnostics with norm-based analysis of the full
attention block. First, we show that SASRec-style models exhibit highly localized last-item reliance. We then find that, although self-
attention aggregates contextual information, residual addition sharply shifts the full-block representation toward same-position contributions, which we term residual dominance. To probe this interpretation, we use inference-time residual scaling as a controlled diagnostic intervention. Changing the residual strength induces a monotonic trade-off between structural mixing and last-item reliance, while reducing residual strength recovers a subset of final-position misses for which representations at non-final positions already rank the ground-truth item correctly. Our results provide a structural account linking extreme last-item reliance to residual dominance at inference time. The code is publicly available.
Read the full abstract ▾
All authors Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama
Artificial Intelligence · Cross-listed from cs.CV
Content Based Video Narration of Gameplay with Vision Language Models
Mathew Varghese
Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based
video narration system that produces spoken, esports-style commentary for arbitrary gameplay recordings using a general-purpose
vision-
language model (VLM) and a text-to-
speech back end, with no game-specific instrumentation, no engine telemetry, and no task-specific training. Three mechanisms carry the system. Temporal mosaic packing arranges nine uniformly sampled frames into a single 3x3 image, letting an image-native VLM reason about motion while consuming one image payload per segment instead of nine. Context-conditioned prompting replays the K most recent narrations as assistant-role history, suppressing the repetition that dominates per-segment captioning of static scenes. Duration-conditioned generation and elastic
alignment constrain narration length in the
prompt, then time-scale or symmetrically pad the synthesized audio so each utterance fills its segment slot exactly, giving frame-accurate muxing without a forced aligner. The implementation supports either cloud TTS or a 6-bit quantized 4B-parameter on-device TTS model on Apple silicon, making the
speech stage fully local. We report a qualitative case study on real-time strategy footage, a cost model showing the mosaic reduces per-minute image payloads by 9x, and a candid account of observed failure modes - hallucinated game state, resolution loss from mosaicking, and prosody artifacts from time-scaling. We release the system as a reproducible baseline, with an evaluation protocol for the quantitative study a full version will report.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Yingying Fan, Penghui Du, Leyan Zhu et al. (+10 more)
Understanding tens-of-minutes
surgical videos requires long-horizon temporal
reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time. Existing approaches handle this poorly: a one-shot
vision-
language model (VLM) compresses the whole procedure to fit its context window and loses the detail a "before" or "after" question depends on, while
video agents that train the model where to look are data-hungry and transfer poorly to out-of-domain surgery. We build an
agent harness that separates
reasoning from perception and improves by evolving context rather than optimizing weights. A text-only orchestrator plans which evidence to gather and issues an auditable sequence of tool calls, while frozen
vision-
language sub-
agents execute each call over the pixels, viewing, cropping, inspecting frames, and retrieving external knowledge. We further propose a gradient-free, reward-gated Heuristic Skill
Distillation loop that mines the
agent's own low-scoring traces and keeps a candidate skill only when it raises a validation reward, yielding reusable
retrieval skills, notably directed re-look. Growing an external skill library rather than tuning weights, the loop adapts from only about 100 labeled examples, far fewer than supervised or reinforcement fine-tuning requires. To evaluate this
agent, we introduce MedClawBench, a de-leaked, doctor-grounded
benchmark of 1,123 questions over self-built long neurosurgery recordings and a held-out public lecture-
video test split. Across both
datasets and all four evaluation dimensions, our
agent consistently outperforms one-shot VLMs and general
video-
agent frameworks, with the largest gains on the long, out-of-domain neurosurgery
videos. Project page: https://fyycs.github.io/medclaw/.
Read the full abstract ▾
All authors Yingying Fan, Penghui Du, Leyan Zhu, Runze He, Zimeng Wu, Yuxuan Zhang, Liang Chen, Jiahao Xie, Jiangtang Wang, Shuai Shao, Anchao Yang, Yutong Bai, Yan Wang
Artificial Intelligence
Buy the Rumor, Sell the News: When Is News Priced In?
Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini et al. (+2 more)
Two old
market sayings hold that news is already priced in by the time it is published, and that the rumor is bought while the news is sold. Both are empirical claims about event time: they place the price move associated with a piece of news before and at publication rather than after it. Whether the claims hold, for which kinds of news, and by how much are basic questions about how fast
markets absorb public information. We test them on 4.57 million financial news articles covering roughly 3,000 US stocks (2023-2026). A large
language model teacher, distilled into a compact classifier through active learning, assigns each article one of 17 event tags and five attributes; articles are clustered into stories to separate first reports from follow-up coverage; and beta-adjusted abnormal returns are measured around the resulting 1.68 million stock-day events, with 364{,}405 neutral-sentiment events as a placebo group. Three results follow. First, the price move associated with news concentrates before and at publication: pooled across all signed events, the cumulative move in the news direction by the close of publication day is 2.8 times its value twenty days later, and for rumor-flagged events the directional return is concentrated around the rumor event, with little incremental return at the subsequent linked non-rumor event. Second, measured against the placebo of comparable stocks,
markets underreact to numbers and overreact to stories: quantified fundamental news (earnings, dividends, guidance, analyst actions) keeps drifting in the direction of the news for weeks, while soft story-driven news (launches, macro commentary, leadership) gives back its move. Third, news carries width as well as direction: neutral news raises publication-day
volatility. The study also produces a table of measured drift for each event tag, usable as a prior in news-conditioned
forecasting models.
Read the full abstract ▾
All authors Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini, Sid Ghatak, Arman Khaledian
Artificial Intelligence · Cross-listed from cs.IR
EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment
Haokai Ma, Aoqi Hu, Yueao Xing et al. (+5 more)
Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index
retrieval within the shared
token space. Recent attempts have introduced Multi-
Token Prediction (MTP) into this field, yet they primarily inherit its efficiency merit, leaving its potential as dense supervision unexplored. Unlocking this potential hinges on whether future behaviors qualify as informative supervision. Our analysis reveals that future behaviors carry a semantic echo of the current one far above that of random pairs, which nevertheless decays along horizons under intent transitions, making them informative yet order-dependent signals. Motivated by this, we propose EchoRec, which empowers MTP with cycle-consistent holistic preference
alignment across multi-horizon for generative recommendation. It comprises two synergistic modules. Horizon-aware Preference Generation (HPG) sequentially chains lightweight auxiliary branches upon the base recommender, where each branch conditions on its predecessor to respect preference
evolution. Verifiable Holistic-Preference
Alignment (VHA) further consolidates them into the holistic preference and echoes it back through cycle-consistent projectors to suppress spurious
alignment, with theoretical guarantees that exclude the rank-collapse form of spurious
alignment under an invertible transport, enabling the holistic preference to be retained in the decoding representation. All auxiliary components serve as disposable scaffolding discarded at inference, introducing negligible online serving overhead. Extensive experiments on three
datasets demonstrate the superiority of our EchoRec, together with its naturally acquired multi-item generation ability. Our code and
datasets will be available upon acceptance.
Read the full abstract ▾
All authors Haokai Ma, Aoqi Hu, Yueao Xing, Ruobing Xie, Yonghui Yang, Teng Tu, Lei Meng, Tat-Seng Chua
Artificial Intelligence
Simulation-Driven Vehicular Traffic Data Augmentation: Extending Sensor Coverage Through Virtual Sensing
Davide Andrea Guastella, Eladio Montero Porras, Evangelos Pournaras et al. (+1 more)
Urban traffic management relies on sensor networks whose spatial coverage is limited by deployment costs and
privacy regulations. Machine learning models trained on such sparse data cannot generalize to unmonitored locations and must be retrained whenever the sensor infrastructure changes. We propose a simulation-based methodology that addresses this problem by generating augmented traffic count
datasets in which each physical sensor is replaced by a virtual sensor placed at a surrogate location in the road network. Virtual sensors are selected by a graph-search heuristic that jointly maximises vehicle-flow continuity and traffic-metric similarity between the original and surrogate locations, while enforcing a minimum spatial displacement to ensure diversity of observed traffic conditions. We validate the method on two Belgian cities: Brussels, using a calibrated model, and Namur, using synthetic models. The augmented
datasets preserve the bimodal daily demand profile and the dynamics of traffic at the observed locations.
Read the full abstract ▾
All authors Davide Andrea Guastella, Eladio Montero Porras, Evangelos Pournaras, Gianluca Bontempi
Artificial Intelligence
Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy
Liwei Deng, Jing Jiang, Zhiwei Li et al. (+2 more)
Driven by the
attention economy, short-
video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting
videos that capture
attention within seconds. These systems inherently favor shallow-content
videos that are effective at attracting immediate
attention. However, growing evidence suggests that prolonged exposure to such content may negatively affect users' cognitive engagement and mental well-being, raising concerns about the long-term societal impact of the short-
video platform. To tackle this challenge, this paper introduces a new metric, the Content Depth Score (CDS), to quantify the content depth of short
videos. CDS measures the extent to which a
video is expected to stimulate higher-order cognitive processes, using a seven-level scale grounded in established theories of cognitive psychology and learning. As an initial step toward this
vision, we present SCOPE-Bench, the first
benchmark for content-depth evaluation in short-
video recommendation. Built upon a large-scale open-source short-
video dataset, SCOPE-Bench provides CDS annotations for 150K
videos, enabling systematic evaluation of RSs from a cognitive-content perspective. Leveraging SCOPE-Bench, we evaluate 13 representative RSs and reveal a consistent preference for shallow-content
videos. Moreover, we find that these
algorithms recommending cognitively deep content are only marginally better than random selection, highlighting a previously overlooked limitation of existing recommendation objectives. Our code and
datasets are available at https://liweidengdavid.github.io/SCOPE-Bench/.
Read the full abstract ▾
All authors Liwei Deng, Jing Jiang, Zhiwei Li, Yang Wang, Guodong Long
Artificial Intelligence
Nanbeige4.2-3B on Apple Silicon: Fixing Deployment Bugs and Decreasing Looped Transformer Memory Overhead
John T. Halloran
Nanbeige4.2-3B is a 3B-parameter agentic model built around a Looped
Transformer (LT) that reuses one stack of layers for a second forward pass, adding effective depth without additional parameters. Evaluated on Apple Silicon (MPS), we identify five independent bugs which prevent the released checkpoint from running via Hugging Face
transformers out of the box (including a silently-zeroed RoPE buffer and calls to removed
transformers cache APIs). Furthermore, we show that fixing these bugs is still not sufficient for agentic tasks, due to the LT's layer-reuse strategy (which effectively doubles peak
attention memory) used to achieve parameter efficiency. We thus introduce a chunked-prefill strategy which alleviates the incurred
memory-capacity penalty, extending allowable context width by $2.7 \times$ on 32~GiB shared
memory. However, even with the reduced
memory overhead, we show that patches are required to render Nanbeige4.2-3B usable; resolving both system
prompt and MPS-native
memory bugs finally allows reliable evaluation on standard MCP and tool-calling
benchmarks. On a subset of MCPMark, the debugged model completes up to 30% of real agentic tasks (up from the original's 0%), while, on BFCL, it is near-perfect at single tool calls (yet fails the majority of multi-tool tests). We release the patched checkpoint, system
prompt optimizer, and evaluation harnesses at https://github.com/johnhalloran321/Nanbeige4.2-3B-mps-fix.
Read the full abstract ▾
Artificial Intelligence
Implementing Computational Law in Wolfram Language for the Governance of Artificial Intelligence
James K. Wiles
How do we govern AI systems whose
reasoning we cannot fully inspect? Governance does not require understanding a system's
reasoning. It requires stating what the system is obliged, permitted, and forbidden to do, and checking whether it complied. I present an implementation of Reified Input/Output Logic, the formalism behind the DAPRECO knowledge base, in Wolfram
Language: the core I/O axioms, obligations, permissions, constitutive norms, reified eventualities, and temporal operators. I then test whether GPT-4 can translate English legal statements into the formalism, and report the failures: hallucinated functions, omitted temporal scope, deviation from the formalism, and (in the worst cases) code that runs, reads plausibly, but silently encodes the wrong norm. A case study, an AI guard dog operating under a computational contract, shows how formalized rules can extend from a contract directly into the operational code of an
embodied agent, producing symbolic, auditable justifications for its behaviour. I argue that computational law can be used as a governance tool and that a desirable goal would be to formalize the law that can and ought to be programmatically executable.
Read the full abstract ▾
Artificial Intelligence
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement
Tianyu Fan and Chao Huang
Scaling
agent capability has largely focused on improving the model, yet an interactive
agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model can accomplish and the trajectories from which it learns. This coupling motivates model-harness co-
evolution for recursive self-improvement: build harnesses for a fixed model, update the model from verified sibling trajectories, and rebuild the harnesses as model capabilities change. Realizing this loop requires a controlled way to evolve harnesses while preserving intervention identity and effect. We present HELIX, a source-traceable substrate for harness
evolution. HELIX decomposes
agent systems into typed ports, reusable atoms, recipes, product shells, and runtime policies. It makes interventions explicit and auditable while retaining trajectories, test outcomes, and provenance. Harness
evolution thus serves two linked roles: improving fixed-model execution and producing matched successes, regressions, near misses, and alternative solutions as data for subsequent model improvement. We evaluate HELIX in one
evolution round on code repair. A 65-candidate portfolio discovers a fixed harness that improves task coverage by 4.0% over Pi, while the full portfolio exposes up to 58.0% more verified coverage through complementary sibling behavior. Selected candidates are assessed with repeated runs and the SWE-bench evaluator. A 200-slot sibling slice yields 438 verified SFT, critic, filter, and preference records. These results show how harness, model, and data form a feedback system: harness
evolution expands current capability and creates learning signal for the next model; model updates motivate the next round of harness
evolution. HELIX provides an auditable interface for studying this recursive process. Code is available at https://github.com/HKUDS/HELIX.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
Musical Mirrors: The LLM as Sounding Board in Songwriting
Xiao Xiao
This paper examines a use of AI in creative practice as an interpretive sounding board for human-generated material, rather than the more familiar pattern of AI generation followed by human curation. Through the lens of resonance as theorized by Hartmut Rosa, I present a first-person case study of songwriting from July 2025 to March 2026, drawing on 16 original pieces in English, French, and other
languages along with piano solos. I describe a configuration in which resonance is not located between user and model, but in the author's deepening contact with their own material, mediated through the model. This kind of resonance was supported rather than inhibited by AI when sounding-board behavior was cultivated through sustained calibration by the user. Two failure modes appeared when calibration was absent: sycophantic drift and magical overinterpretation. This account suggests both the potential and the risks of AI as an interpretive partner in creative practice.
Read the full abstract ▾
Artificial Intelligence
AI Research Preference Models
Thomas Simon Foster, Bassel Al Omari, Tingchen Fu et al. (+30 more)
AI research
agents (AIRA) can now carry machine learning experiments from proposal through implementation and evaluation. Yet progress on frontier tasks is throttled by the cost of evaluations that can consume days of GPU time. When an
agent can propose far more candidates than it can afford to run, progress depends on its research preference: how it allocates a fixed execution budget across many candidates. We introduce AI Research Preference Models (RPMs) that predict which candidate solution is most promising, without paying the cost of running them all. We build RPMs from frozen pretrained
language models in two variants: an inference-only model that reasons over candidate plans, code, and previously executed solutions, and an agentic model that additionally runs small-scale pilot experiments. Integrated into the AIRA-dojo research
agent and evaluated on the machine learning research
benchmark AIRS-Bench, the two variants increase the average normalized score from 0.684 to 0.711 and 0.729, respectively. Both reach the unguided
agent's 24-hour performance in roughly 15 hours, using less than two-thirds of its execution budget, and together yield new state-of-the-art results on two AIRS-Bench tasks.
Read the full abstract ▾
All authors Thomas Simon Foster, Bassel Al Omari, Tingchen Fu, Thomas Mann, Carl Domond, Lucia Cipolina-Kun, Bhavul Gauri, Muna Aghamelu, Alexander D. Goldie, Eryk Helenowski, Jean-Christophe Gagnon-Audet, Alberto Pepe, Saba Nazir, Daniel Izcovich, Noam Levi, Rishi Hazra, Karen Hambardzumyan, Nicolas Baldwin, Xian Li, Martin Josifoski, Paris Giampouras, Masoud Jalili Sabet, Anya Sims, Hela Momand, Tatiana Shavrina, Despoina Magka, Jason Weston, Yulin Wang, Anirudh Goyal, João Henriques, Yoram Bachrach, Emily McMilin, Jakob Nicolaus Foerster
Artificial Intelligence · Cross-listed from cs.CV
CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification
Bingxin Yu, Xueli Wang, Jerry Zhou et al. (+6 more)
Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5). Although widely adopted in clinical practice, most deep learning approaches focus on binary malignancy classification, while multi-class prediction and explicit utilization of feature-level supervision remain underexplored, largely due to limited annotated data. In this study, we introduce the STN
dataset of 600 thyroid nodules with paired transverse and longitudinal ultrasound images, bounding box annotations, and complete labels for all five TI-RADS feature categories. Following the clinical decision process, we investigate how structured feature information can guide representation learning during training while requiring only images at inference. We demonstrate that text
embeddings derived from standardized feature descriptions form a stable surrogate representation for TI-RADS risk levels. Based on this observation, we propose CMCNet, which aligns image
embeddings to fixed textual
embeddings via a Center-Margin Contrastive Loss that simultaneously promotes intra-class compactness and inter-class separation. Experimental results show that this
embedding alignment strategy is more data-efficient and robust than direct multitask learning, and consistently outperforms InfoNCE, center loss, a strong multitask baseline, and a VQA-style
multimodal model, particularly in imbalanced settings. The
dataset is freely available at doi: 10.5281/zenodo.19125693 and the source code is available at: https://www.healthinformaticslab.org/supp/.
Read the full abstract ▾
All authors Bingxin Yu, Xueli Wang, Jerry Zhou, Wenyan Wang, Li Wen, Lan Huang, Xin Feng, Fengfeng Zhou, Kewei Li
Artificial Intelligence
Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact
Zhelun Wu
Large
language models have made natural
language interfaces to databases (NLIDB) newly credible, but LLM text-to-SQL systems fail in a way that matters for deployment: a hallucinated column or a mis-aggregated total yields a fluent wrong answer, indistinguishable at the point of use from a right one. Where the consumer cannot inspect the generated query, as in enterprise AI deployments and operational dashboards, and increasingly where the consumer is a tool-using
agent rather than a person, accuracy alone is insufficient: nothing marks which answers to distrust. This is a reliability problem before it is an accuracy problem. We propose an architectural pattern for such systems, a trusted kernel with a generative shell, resting on one invariant: a component that can fabricate may influence which question the system answers, never which value it returns. A generative shell interprets underspecified input and phrases replies; a deterministic kernel matches fully specified questions against a bounded set of answerable question shapes and compiles them to queries by deterministic execution. The two meet at a confirmation the user reads before any value is computed, and requests the kernel cannot express are declined rather than approximated. We call this structural abstention, and distinguish it from the statistical abstention of selective prediction and calibrated confidence: refusal here needs no confidence estimate, because unanswerable requests are unrepresentable. We specify the pattern implementation-independently, give a five-decision recipe and work it across three domains, extend the invariant from returned values to the actions of agentic systems, and report a two-year production case study alongside two generative alternatives, a fine-tuned parser and a tool-
retrieval agent. We close against enterprise and reliability
benchmarks published since.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing
Yuji Ren, Chenkai Xu, Zhuocheng Gong et al. (+2 more)
Diffusion large
language models (dLLMs) accelerate
language generation by predicting multiple masks in a single forward pass. However, existing dLLMs can suffer from unreliable predictions in early denoising stages under aggressive parallelism strategies, leading to errors that can propagate to later stages. To tackle this issue, we present Consistency Forcing (CForce) for dLLMs, a
distillation method to force the mask predictions of early stages to align with those of later stages. CForce trains the model on pre-collected self-rollout trajectories, thereby improving training-inference
alignment. We introduce Confidence Adaptive KL Divergence as a
distillation objective to conjoin the merits of forward and reverse KL. We further provide a theoretical analysis for the consistency objective to explain why CForce can approximately minimize the prediction error of early stages. Critically, the same formulation applies to both mask-to-
token decoding and edit-capable decoding; in the edit-capable case, later
token-to-
token refinements provide additional supervision for earlier masked-state predictions. Experiments on non-edit and edit-capable LLaDA models show improved speed-quality trade-offs, especially under high-parallelism decoding budgets. Code is available at: https://github.com/inclusionAI/dFactory.
Read the full abstract ▾
All authors Yuji Ren, Chenkai Xu, Zhuocheng Gong, Jianguo Li, Zhijie Deng
Artificial Intelligence
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
Lu Yang, Shusheng Xu, Zhuoran Li et al. (+2 more)
LLM
agents increasingly maintain personal
memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or source authority to interpret conflict, treating one
memory as definitive converts unresolved conflict into an unjustified, overconfident action. Existing
benchmarks recover one answer from conflicting evidence, overlooking whether
agents recognize underdetermination, preserve alternatives, seek missing information, and choose appropriate actions. We introduce \underline{T}esting \underline{A}gents' \underline{N}avigation of \underline{G}enuine, \underline{L}atent, and \underline{E}ntangled
Memory Conflicts (TANGLE), a
benchmark for genuinely unresolvable
memory conflicts. It comprises 541 instances across 40 personas and three types: Context-Partitioned Conflict (CPC), Behavior-Oscillation Conflict (BOC), and Source-Contradiction Conflict (SCC). We evaluate two tracks—an oracle track with curated
memory and a pipeline track that extracts
memory from multi-session dialogues—on five dimensions: conflict perception, causal
reasoning, confidence calibration, clarification seeking, and
memory faithfulness. Experiments reveal pipeline challenges. With curated
memory, models recognize conflicts more reliably than they calibrate actions or seek targeted clarification. With end-to-end pipeline
memory, extraction fails to preserve conflict-bearing relations needed for downstream
reasoning. Policy comparisons show fixed rules are insufficient when actions must reflect conflict. These findings motivate Conflict-Aware Action Policy (CAAP), which adapts actions to each conflict using available evidence. TANGLE frames conflict handling as recognizing underdetermination, retaining conflicting evidence, and acting without forcing a definitive answer.
Read the full abstract ▾
All authors Lu Yang, Shusheng Xu, Zhuoran Li, Tongkai Yang, Longbo Huang
Artificial Intelligence · Cross-listed from cs.LG
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
Chun-Hua Lin, Samuel Yen-Chi Chen, Yu-Chao Hsu et al. (+7 more)
Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training.
Federated learning addresses this practical
privacy constraint by enabling collaborative model training while keeping raw biosignal data at their respective sources. However,
federated ECG classification remains challenging due to limited client-side samples, imbalanced arrhythmia labels, and non-independent and identically distributed (non-IID) data across clients. These constraints require classifiers that are both communication-efficient and robust to cross-client distribution shifts. In this work, we evaluate a hybrid
quantum-inspired Kolmogorov-Arnold network (HQKAN) against a multilayer perceptron (MLP) for five-class arrhythmia classification on the MIT-BIH
dataset and three-class classification on the INCART
dataset under
federated averaging (FedAvg). Across multiple client configurations, HQKAN improves most aggregate and minority-class metrics while using 37.35% fewer trainable parameters and reducing communication cost by 24.89% on MIT-BIH; on INCART, it achieves corresponding reductions of 44.81% and 36.41%. These results indicate that HQKAN offers a compact, communication-efficient and robust alternative to the MLP baseline for
privacy-aware
federated learning on biosignal data.
Read the full abstract ▾
All authors Chun-Hua Lin, Samuel Yen-Chi Chen, Yu-Chao Hsu, Kuo-Chung Peng, Jiun-Cheng Jiang, Chi-Sheng Chen, Tai-Yue Li, Nan-Yow Chen, En-Jui Kuo, Hsi-Sheng Goan
Artificial Intelligence · Cross-listed from cs.CR
CipherSight: Robust Website Fingerprinting via Record-Resource Semantic Supervision under Distribution Shifts
Runhan Song, Qiqi Liu, Chuanzhou Pan et al. (+6 more)
HTTPS website fingerprinting (WF) aims to identify visited websites from metadata observable in encrypted traffic. However, real-world deployments introduce a significant out-of-distribution (OOD) problem caused by temporal and geographic changes, while previously unseen websites are common in open-world scenarios. Existing methods primarily learn from raw TCP packet sequences and struggle to capture stable and generalizable website representations, resulting in performance degradation under practical conditions. We propose CipherSight, a TLS-record-based hierarchical framework for robust HTTPS WF. Unlike existing approaches that rely on TCP packet sequences and are sensitive to transport-layer artifacts, CipherSight learns website representations from TLS records by jointly encoding multiple record-level attributes. It introduces a hierarchical architecture that captures both intra-flow dependencies among TLS records and inter-flow interactions across concurrent flows, enabling the model to exploit structural patterns in HTTPS traffic. Besides, to learn robust representations, CipherSight employs a masked record modeling (MRM) task to capture contextual traffic semantics and leverages fine-grained record-resource annotations as privileged supervision through structure-aware objectives and semantic
distillation. Experiments show that CipherSight achieves 95.41% accuracy across more than 2,000 website classes in the closed-world setting and maintains over 90% accuracy under both temporal and geographic drift, consistently outperforming all evaluated baselines.
Read the full abstract ▾
All authors Runhan Song, Qiqi Liu, Chuanzhou Pan, Zhenquan Ding, Youquan Xian, Chongru Fan, Lei Cui, Wei Wang, Zhiyu Hao
Artificial Intelligence · Cross-listed from cs.DB
Agentic Transaction: Towards ACID-Compliant Agent Systems
Zhaoyan Sun, Xiaoxiao Wang and Guoliang Li
Large
language model (LLM)
agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through
reasoning, tool use, code generation, and workspace manipulation. As
agents increasingly operate over persistent environments and multi-step workflows, they face challenges analogous to those addressed by transactional database systems: reliable execution, consistent outcomes, safe concurrency, and durable state management. We introduce the concept of an agentic transaction and propose an ACID-compliant
agent system framework that reinterprets the classical ACID properties for
agent execution through four semantic guarantees: Semantic Atomicity, Semantic Consistency, Semantic Isolation, and Semantic Durability. Together, these properties provide a principled foundation for building reliable
agent systems despite model uncertainty and dynamic execution environments. To instantiate this framework, we develop an ACID-compliant data
agent that realizes these guarantees through transactional exploration-execution-validation cycles, transactional skill hubs, confidence divergence-based validation, semantic dependency-aware isolation, and transaction-aware semantic state management. Experimental results on widely used
benchmarks show that our system achieves a 10.6% improvement over state-of-the-art
agents, including Claude Code. This work opens a broader research agenda on extending transactional principles and system architectures toward building trustworthy, scalable, and self-evolving AI
agent systems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen
Jiada Li, Xuesong Ye and Olamide Olowoniyi
The rapid adoption of AI coding assistants and autonomous agentic development systems has coincided with major changes in the pace and structure of open-source software engineering. Yet empirical longitudinal evidence of these changes at the team level remains limited. We present a descriptive longitudinal analysis of seven engineering metrics: pull request (PR) throughput, cycle time, contributor diversity, PR comment density, merge rate, new-author participation, and PR size. Metrics were computed from all merged PRs in two high-velocity AI infrastructure repositories, vLLM (February 2023-June 2026; 18,290 PRs) and SGLang (January 2024-June 2026; 14,938 PRs). We segment development into four eras aligned with major changes in AI-assisted software development and examine human- and bot-authored activities. Both projects show substantial increases in development velocity and AI-developer collaboration signals. PR throughput increased 21x in vLLM and 17.9x in SGLang, while bot-authored PRs accounted for less than 0.2% of this growth, indicating that the increase was overwhelmingly human-driven. In the latest era, median cycle time was 1.04 days for vLLM and 0.62 days for SGLang, while P90 cycle times reached 16.8 and 14.3 days, respectively. Monthly unique authors increased steadily in both projects, suggesting broader contributor participation. PR comment density increased 4.2x in vLLM and 3.8x in SGLang, with bot comments contributing an estimated 15-20% of the increase. In contrast, PR size remained relatively stable across eras. Overall, AI-assisted development is associated with higher throughput, broader contributor participation, and increased AI-developer collaboration signals in high-velocity open-source software development.
Read the full abstract ▾
Artificial Intelligence
MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends
Chaoqun Zhan, Qiang Zhou, Guannan Li et al. (+2 more)
Most
agent-
memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether
memory supports interdependent, multi-session task completion. We compare MemoryLake, a structured multi-track
memory backend, with Mem0, text-
embedding-3-small vector RAG, and a long-context control across all five MemoryArena domains. The systems share the same
agent framework, requested gpt-5-mini model alias, task samples, and scoring code; the
memory integration is the intentionally changed component. Because each backend bundles write,
retrieval, consolidation, budgeting, and
prompt-assembly choices, the study is a matched system-level comparison, not a representation-only ablation or a cost-matched experiment. On the shared evaluation sets, MemoryLake has the highest observed success rate (SR) in mathematics (9/40), physics (12/20), and progressive
retrieval (4/20). Every system has zero SR in travel planning, and web shopping yields a single bundle-level success (long context, 1/150); MemoryLake ranks third on both the travel soft process score and shopping step match. Following MemoryArena's suite-level convention, a post-hoc equal-weight average over the five SRs is 20.5% for MemoryLake versus 13.6% for the best comparator. These are point estimates: sample sizes are modest, confidence intervals overlap, and we do not report paired significance tests. A separate MemoryLake-only run over all 221 progressive queries yields a failure-counted SR of 26.7% (59/221) and is not a baseline comparison. The results support a workload-dependent view of
memory backends and an observed lead among the four evaluated systems on the shared sets; they do not establish
benchmark-wide state of the art or a causal advantage of representation structure.
Read the full abstract ▾
All authors Chaoqun Zhan, Qiang Zhou, Guannan Li, Zhenqiang Huang, Qianjin Wang
Artificial Intelligence · Cross-listed from cs.SE
Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model
Stephanie Jarmak
AI coding
agents are commonly evaluated as models but deployed as systems. Their reliability depends not only on model capability, but on the harness, execution state,
retrieval,
memory and state management, permissions, review interfaces, and resource allocation. This monograph examines those boundaries and develops a framework for evaluating and operating coding
agents reliably. It synthesizes 164 scholarly works, 100 practitioner records, 29
benchmark records, and 17 author-system case records through a structured multivocal review, targeted update audits, software-engineering coverage analysis, and distributed-systems evidence synthesis. Across this evidence, many apparent model failures originate elsewhere in the system, while improvements at one layer often fail to propagate to end-to-end outcomes. Evaluation and operation are treated as a dependency chain in which weaknesses in task construction, execution environments,
retrieval, state management, verification, or observability can invalidate downstream conclusions. The monograph contributes a versioned catalog of 206 reliability records: 193 gated practices, including 56 developed in depth, plus 13 research leads; an evidence ledger; a framework for dependency and repair asymmetry across the
agent lifecycle; measurements and failure cases from operated
agent systems; runnable evaluation and reliability protocols; and five reusable
agent skills with evidence maps. Together, these provide a system-level methodology for distinguishing model capability from infrastructure effects, designing defensible evaluations, and building systems that recover safely when components fail. The review is structured rather than exhaustive, evidence strength varies by topic, and results depend on workload and configuration. The methods record which search lanes were executed, which remain unexecuted, and limits on evidence-grading claims.
Read the full abstract ▾
Artificial Intelligence
Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference
Yunchu Han, Zhaojun Nan, Sheng Zhou et al. (+1 more)
Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and
memory resources. To enable energy-efficient DNN inference, most existing studies focus on dynamic voltage and frequency scaling (DVFS) for adjusting the computing frequency, while the impact of
memory frequency on the inference performance has been greatly overlooked. In this paper, we consider the impact of
memory frequency and computing frequency on DNN inference time, and jointly optimize these two frequencies together with communication resources for energy-efficient DNN inference. Based on a realistic inference time model, we formulate an optimization problem to minimize the energy consumption of all mobile devices under the deadline constraint. For local inference, we derive a near-optimal closed-form solution via convex optimization, while an optimal closed-form solution for transmission power is obtained for edge inference with the given bandwidth. Furthermore, we propose a low-complexity heuristic
algorithm to effectively solve the overall problem with
polynomial time complexity. Simulation results based on measured data show that the proposed near-optimal solution for local inference can achieve optimal performance under strict deadline constraints, with a performance gap of up to 2.5% compared with the optimal solution. Meanwhile, our proposed
algorithm significantly reduces the energy consumption of devices by up to 10.4% compared to other methods.
Read the full abstract ▾
All authors Yunchu Han, Zhaojun Nan, Sheng Zhou, Zhisheng Niu
Artificial Intelligence · Cross-listed from cs.LG
Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directions
Qinglin Yang, Chen Qiu, Hongyuan Zhang et al. (+3 more)
Large
language models (LLMs) have become core components of cloud-based intelligent services in academia and industry, yet their training and deployment are hindered by high computational costs, data centralization, and
privacy concerns.
Federated learning (FL) offers a decentralized training paradigm that enables clients to collaboratively train a learning model without sharing raw data, making it a promising solution for
privacy-preserving LLM training and
reasoning. This paper presents a comprehensive survey of
federated prompt learning (FPL) to review recent advances in integrating the
federated learning paradigm and large
language models, answering the following research questions: RQ1: The fundamental motivations, characteristics, and enabling technologies of FPL, and how it differs from conventional FL and full-model
federated fine-tuning; RQ2: The trade-offs FPL approaches exhibit in performance, communication efficiency, computational overhead, scalability, personalization, and heterogeneity handling; RQ3: The remaining security,
privacy, robustness, and system challenges, along with key future research directions. To this end, we systematically examine existing FPL methods across the full model lifecycle: pre-training, fine-tuning, and practical applications, while discussing security,
privacy, and robustness issues and summarizing existing defense mechanisms. Finally, we highlight open challenges and future directions, aiming to help readers understand how the insights drive research in FPL.
Read the full abstract ▾
All authors Qinglin Yang, Chen Qiu, Hongyuan Zhang, Pengdeng Li, Yuan Liu, Zhihong Tian
Artificial Intelligence · Cross-listed from cs.CL
ASSERT: A Measurement Pipeline for GenAI Audits
Riccardo Fogliato, Abhinav Palia, Xiawei Wang et al. (+11 more)
Audits of generative AI (GenAI) systems often summarize behavior as a reported rate: how often the audited system complies with policy. Researchers and stakeholders use that rate to compare systems, track regressions, and gate deployment. A reported rate reflects both the system under audit and the measurement choices behind it, so a change in the rate can leave it unclear whether the system or those choices moved. We introduce ASSERT, a specification-driven measurement pipeline for GenAI audits that ties each reported rate to a written specification of the measurement choices used to produce it. ASSERT helps draft a behavioral rubric and test cases, then runs the audit against a GenAI system and returns a reported rate. In a case study on conversational deception, we observe that the reported rate moves substantially with the dialogue setup, the simulated user, the judge, and the evidence bar for non-compliance. These measurement choices substantially change the reported rate and can reorder GenAI system rankings. Because each reported rate is tied to an explicit specification, differences across audits are easier to attribute and interpret.
Read the full abstract ▾
All authors Riccardo Fogliato, Abhinav Palia, Xiawei Wang, Emily Sheng, Chad Atalla, Jean Garcia-Gathright, Nicholas Pangakis, Sharman Tan, Dan Vann, Hannah Washington, P. Alex Dow, Heba Elfardy, Hanna Wallach, Sandeep Atluri