Machine Learning
HADRec: A Hierarchy-Aware Drug Recommendation Framework by Fusing Molecular Knowledge and Electronic Health Record
Junke Wang, Hongshun Ling, Li Zhang et al. (+4 more)
Accurate medication recommendation is central to clinical decision-making, directly determining therapeutic efficacy and patient safety. However, existing methods suffer from two key limitations: drugs are often abstracted as discrete
tokens, ignoring their molecular structures and pharmacological mechanisms, and the commonly used "flat" recommendation paradigm fails to leverage the hierarchical logic of the internationally standardized Anatomical Therapeutic Chemical (ATC) classification system. To address these issues, we propose HADRec, a Hierarchy-Aware Drug Recommendation framework that integrates molecular knowledge with electronic health records (EHRs). HADRec employs LLaMA-7B to encode clinical notes for rich patient representations and ChemBERTa to encode drug Simplified Molecular Input Line Entry System strings, building a global molecular knowledge base. A cross-
attention mechanism then performs deep
multimodal fusion between patient states and drug features. The framework further incorporates a hierarchical predictor and a novel consistency constraint loss to enforce strict adherence to ATC logical dependencies. Extensive experiments on MIMIC-III demonstrate that HADRec achieves state-of-the-art performance across Jaccard, F1, and PR-AUC. External validation on MIMIC-IV confirms strong generalization under distribution shifts, and calibration analysis shows well-calibrated predictive confidence on MIMIC-IV with ECE = 0.04, and Brier = 0.06. Counterfactual evaluation reveals clinically aligned
reasoning, disentangling disease-specific treatments from general care. Together, these results establish HADRec as a high-performance, interpretable, and clinically grounded pathway toward safe and reliable AI-driven medication recommendation.
Read the full abstract ▾
All authors Junke Wang, Hongshun Ling, Li Zhang, Jinjing Wu, Tong Shao, Fang Wang, Yuan Gao
Computation and Language
The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization
Chao Li, Shigeng Wang and Anbang Yao
Post-training quantization (PTQ) methods typically use sequential quantization that partitions a pre-trained LLM into a series of units (e.g.,
transformer blocks), with one unit quantized at each stage. State-of-the-art PTQ methods are predominantly learning-based, optimizing auxiliary quantization parameters (e.g., scaling factors, rotation
matrices, clipping thresholds, and adapters) via gradient descent to minimize a reconstruction loss. A common practice is to use mean squared error (MSE) as the reconstruction loss function, yet its induced optimization behavior remains largely unexplored. In this work, we take a holistic view of sequential quantization and systematically investigate how optimization evolves from the first quantization stage to the last, aiming for a deep understanding of optimization in learning-based PTQ schemes. Through extensive empirical studies spanning representative learning-based PTQ methods, LLM families, model scales, architectures, quantization settings and various tasks, we consistently uncover Optimization Imbalance: reconstruction loss magnitudes vary dramatically across stages, accompanied by highly uneven gradient magnitudes and parameter updates under MSE. We term the cross-stage range of loss magnitudes the reconstruction loss scale, and reveal that MSE translates the unexpectedly large reconstruction loss scale into highly uneven gradient magnitudes, which in turn lead to uneven optimization strength across quantization stages. This finding suggests a general principle for improving learning-based PTQ: optimization strength across stages should be decoupled from the reconstruction loss scale. Theoretically, we show that root mean squared error (RMSE) variants defined at the sample, channel,
token, and element levels naturally realize this principle through implicit gradient normalization, outperforming MSE significantly as a drop-in replacement.
Read the full abstract ▾
Robotics
Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies
Xuehui Yu, Eason Yu, Meiyi Wang et al. (+3 more)
Vision-
language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the action, and the policy needs a
memory of the history. Existing
memory methods decide what to remember by design, for example, keeping frames with large pixel changes, and show inconsistent gains across tasks. We view what to remember as an optimisation problem. From the POMDP formulation of imitation learning, we show that the optimal
memory maximises the conditional mutual information $I(a_t; m_t \mid o_t)$ between the action and the
memory given the current observation. Intuitively, this means preserving the action-relevant information in the history that is not already contained in the current observation. Based on our analysis, we propose Divide-and-Remember (D&R), a recursive
memory method that learns a
memory function $m_t = M(h_t)$ and scales to long contexts while staying compute-light. It involves two strategies: (1) the selection over the full history is divided recursively into subproblems of top-$K$ selection over $2K$
tokens, so that fixed-size, lightweight selectors learned end-to-end support an unbounded history; (2) all recursion blocks share one selector, which captures the selection rule common to every block and keeps the method efficient. On RoboMME, a
benchmark of 16 long-horizon manipulation tasks that require remembering when, where, what, and how to act, D&R achieves a state-of-the-art average success rate with consistent gains across all four suites under a budget of only 64
tokens; real-
robot experiments show the same gain. Code, checkpoints and more results are at https://dnr-
memory.github.io/
Read the full abstract ▾
All authors Xuehui Yu, Eason Yu, Meiyi Wang, Haozhe Du, Stefano V. Albrecht, Harold Soh
Robotics
NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields
Shota Kobayashi, Koki Seno, Daichi Yashima et al. (+1 more)
We focus on
language-conditioned flow-based manipulation, where
robot flows (
robot velocity fields) serve as embodiment-agnostic, motion-centric representations for leveraging data collected from multiple
robot platforms. This task is crucial because
language-conditioned manipulation is essential for practical robotic systems, yet scaling
robot foundation models remains limited by the labor-intensive collection of embodiment-specific data. Existing methods either coarsely approximate
robot flows with sparse keypoint displacements, or cannot handle
language-conditioned manipulation. To address this limitation, we propose NarrativeFlow, which models
robot flows as continuous velocity fields using a flow-matching formulation conditioned on
language. Accordingly, NarrativeFlow generates
robot flows that are physically consistent with real-world manipulation. To validate NarrativeFlow, we have conducted experiments on standard
datasets for
language-conditioned manipulation. The experimental results show that NarrativeFlow outperforms representative baseline methods on standard evaluation metrics. Furthermore, through real-world experiments, we show that NarrativeFlow achieves higher success rates than baseline methods across multiple manipulation tasks. The project page is available at https://shota0520.github.io/NarrativeFlow-project-page/
Read the full abstract ▾
All authors Shota Kobayashi, Koki Seno, Daichi Yashima, Komei Sugiura
Multiagent Systems
Can AI Scientists Coordinate at Runtime?
Zijian Liu, Yangzhixin Luo, Junyu Lu et al. (+6 more)
Multi-
agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestration, which typically relies on fixed workflows. In contrast, human scientists coordinate and adjust their division of labor at runtime. We therefore ask: can AI scientists also coordinate at runtime? To this end, we introduce Runtime
Agent Coordination (RAC), which selects
agents from existing AI-scientist hosts during execution, assigns scoped work contracts, and provides artifact-grounded verification. Verification informs subsequent
agents without blocking transitions or discarding artifacts. We conduct a single-seed exploratory evaluation across
Agent Laboratory, EvoScientist, and ARK on ResearchClawBench, preserving host models, tools, and permissions under host-calibrated budgets. Four cumulative conditions separate native execution, runtime communication, runtime selection, and the combined addition of contracts and verification. Runtime selection yields the highest observed mean score for each host; adding contracts and verification reduces these means, with host-dependent outcomes relative to native execution. These results motivate runtime coordination while exposing the limits of additional coordination mechanisms under constrained budgets. Code is available at https://github.com/systemind-team/Runtime-AI-Scientist.
Read the full abstract ▾
All authors Zijian Liu, Yangzhixin Luo, Junyu Lu, Yi Li, Yu Chen, David Xu, William F. Shen, Xinchi Qiu, Xisen Wang
Artificial Intelligence
RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation
Jingtan Wang, Sirajul Salekin, Young mok Jung et al. (+3 more)
Training a single LLM
agent jointly across diverse interactive environments has attracted increasing
attention as a route to generalist
agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly considering relationships between current rollouts across environments for
prompt-group selection. Meanwhile, as environments are learned at different rates, all-failure and all-success rollout groups can coexist within a batch, leaving those data without group-relative reward signals. Both challenges highlight limitations of relying solely on scalar rewards in multi-environment RL: they provide limited information about cross-environment relationships and no within-group reward contrast when rewards are identical. This motivates richer textual feedback, such as rubrics describing rollout behaviours, to guide learning. Beyond rubrics' usage as reward, we repurpose rubrics to guide both online data selection and policy supervision. An LLM judge tags each rollout using a predefined rubric vocabulary shared across environments. The resulting profiles guide the selection of data that aligns with the overall behavioural composition of the mixed-environment batch while limiting overlap with already-selected data. Available positive rubrics (describing desired behaviours) provide privileged context for an on-policy self-
distillation teacher, supplying additional
token-level supervision, while negative rubrics (describing undesired behaviours) guide subsequent rollout generation away from recurring failure modes. Together, these components form RISED. Across model backbones, RISED achieves the highest mean pass rate across environments and ranks first or second in every individual environment. Rubric-based analysis of RISED can further characterize the behavioural changes accompanying these gains.
Read the full abstract ▾
All authors Jingtan Wang, Sirajul Salekin, Young mok Jung, Javier Movellan, Bryan Kian Hsiang Low, Manjot Bilkhu
Machine Learning
Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection
Tian Lan, Yifei Gao, Yimeng Lu et al. (+6 more)
Time-series anomaly detection (TSAD) is difficult to generalize across
datasets because heterogeneous temporal dynamics imply different notions of normality and favor different detection criteria. While time-series foundation models provide transferable representations, coupling them with a fixed anomaly-scoring mechanism can overlook this variation. This motivates a different perspective on foundation-model-based TSAD: using foundation models to coordinate specialized anomaly criteria rather than directly imposing a universal one. Based on this view, we propose TS-Router, a generalist-representation, specialist-detection framework that estimates the relative competence of heterogeneous anomaly detectors from pretrained temporal representations and selects suitable specialists for each target series. To avoid relying on specialist-performance labels from real tasks, we derive soft competence supervision from specialists' relative performance on labeled simulated tasks. At deployment, routing requires no target anomaly labels, and only the selected specialists are fitted unsupervisedly on the target series. We bound Top-\(k\) set-competence regret under representation coverage and conditional competence stability. Across 16 real-world
benchmarks and four complementary evaluation metrics, TS-Router achieves the best overall average rank. Controlled ablations with multiple frozen TSFM encoders further support the use of pretrained representations for competence estimation and adaptive specialist selection. The code is available at https://anonymous.4open.science/r/TS-Router-D8FF.
Read the full abstract ▾
All authors Tian Lan, Yifei Gao, Yimeng Lu, Xuming An, Meng Wang, Yue Pan, Wenjun He, Chenghao Liu, Chen Zhang
Cryptography and Security
ABSENTIA: Detecting Broken Access Control Vulnerabilities in Web Applications
André V. Duarte, Aditya Oke, Rui Melo et al. (+7 more)
Broken access control, the failure of authorization, is one of the most prevalent web security risks. Unlike injection, a flow of untrusted input into a dangerous operation, authorization is a relation: who may act on what, not how data moves. Each application decides that relation for itself, so no rule written in advance carries to the next. An LLM
agent can infer it from the code, but with no systematic way to cover the application and prioritize what to inspect, its search stays undirected and access-control flaws go undetected. We present ABSENTIA, a security scaffolding that turns general LLM
agents into systematic vulnerability detectors for the backend of web applications, run as an audit by the developers and security engineers who maintain the code. Under its direction, the
agents build a graph that maps the application's routes to the code behind them. ABSENTIA then works route by route, applying invariant falsification: it infers the properties the code is meant to satisfy, and where one is not enforced, reports the route for maintainer review. We also release BAC-Bench, a
benchmark of 30 broken access control advisories across 25 repositories, 3
languages, and 9 frameworks, each published in 2025 or later, verified by a human auditor, and paired with its fixing commit, so credit requires flagging the vulnerable version and not the fixed one. ABSENTIA recalls 19 of them, 17 under paired credit, and an LLM verifier confirms 51% of its findings. CodeQL and Semgrep recall none, and an unstructured
agent on the same model recalls 3. In the OWASP
Benchmark injection categories, ABSENTIA leads the dedicated analyzers in Python and trails only CodeQL and IRIS in Java.
Read the full abstract ▾
All authors André V. Duarte, Aditya Oke, Rui Melo, Shubham Gandhi, Nachiket Kotalwar, Charmi Khandor, Danqing Wang, Arlindo L. Oliveira, Carolyn Rosé, Lei Li
Machine Learning
Variational Streaming Flow: Probabilistic Forecasting in Physical Time
Hans Hao-Hsun Hsu, Minseon Gwak, Soon Hoe Lim et al. (+2 more)
Probabilistic
forecasting is important for predicting complex dynamical systems because intrinsic randomness and incomplete observations can cause the same observed state to evolve into multiple plausible futures. While flow matching is a flexible approach for probabilistic
forecasting, it is computationally expensive. Streaming flow (SF) reformulates this approach to model temporal
evolution efficiently by learning a continuous velocity field directly in physical time. However, SF learns a deterministic velocity field. Thus, it provides only a single future trajectory for a given fixed initial state and observation history. To overcome this limitation, we introduce Variational Streaming Flow (VSF). Our approach learns a latent distribution that is conditioned on the dynamics of interest. In turn, this enables probabilistic
forecasting. Importantly, we retain the computational efficiency of SF by generating in physical time. Across deterministic and
stochastic dynamical systems, VSF demonstrates superior predictive accuracy and distributional fidelity. We demonstrate the advantage for both long-horizon rollouts exceeding 1,000 steps, and settings with bifurcating dynamics. Moreover, VSF can be integrated into existing Joint-
Embedding Predictive Architecture (JEPA)-based world models as a plug-and-play predictor to improve temporal dynamics and goal-directed success rate in
navigation, motion planning, and manipulation.
Read the full abstract ▾
All authors Hans Hao-Hsun Hsu, Minseon Gwak, Soon Hoe Lim, Pan Li, N. Benjamin Erichson
Networking · Cross-listed from eess.SP
Physics-Guided Bayesian Optimization for High-Dimensional Mixed-Variable MIMO Base Station Design
Koki Kanzaki and Koya Sato
This paper proposes a physics-guided
Bayesian optimization for high-dimensional mixed-variable multiple-input and multiple-output (
MIMO) base station (BS) design. The considered problem jointly selects a subset of candidate sites for BS deployment and optimizes the azimuth angles, downtilt angles, and transmit power spectral densities of the BSs, while each configuration is evaluated using computationally expensive site-specific ray tracing. To efficiently optimize the system configuration, the proposed method constructs a low-cost physics-based proxy from precomputed propagation information. The proxy-estimated communication coverage is used as the Gaussian process (GP) prior mean, and a residual GP with three-dimensional physical features learns the discrepancy between the proxy and full evaluations. Ray-tracing-based evaluations in two urban scenarios show that the proposed method achieves up to approximately 15 percentage points higher coverage than conventional and high-dimensional optimization baselines under the same evaluation budget.
Read the full abstract ▾
Computer Vision
Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack
Haiming Zhao, Tai Wang, Kun Zhang et al. (+2 more)
Science teachers frequently search for documentary excerpts not by describing what appears on screen, but by querying the abstract concepts they intend to teach. This use case exposes a limitation of existing
language-based
video moment
retrieval methods, which typically assume that queries describe observable events, whereas instructional search requires retrieving concrete visual phenomena that instantiate an underlying scientific principle. We study this setting as concept-to-example
video retrieval, an abstract-needle-in-a-haystack problem where compact curriculum concepts must be grounded in temporally sparse documentary evidence. To bridge this abstraction gap, we propose Concept-Driven Domain Adaptation (CDDA), a three-stage framework for adapting two-tower
vision-
language models to concept-level
retrieval. CDDA treats concepts as intermediate semantic anchors: it first structures the textual
embedding space with textbook and teacher-handbook example-concept pairs, then transfers this concept-aware geometry to documentary visuals under a frozen visual encoder, and finally jointly adapts both encoders with sparse visual concept supervision. From a
geometric perspective, this staged
alignment reduces text-concept and
vision-concept angular gaps, thereby encouraging concept-level adaptation while preserving the pretrained model's concrete image description
alignment. On a curated middle-school physics
retrieval benchmark, CDDA achieves stronger pedagogically oriented concept
retrieval than several competitive
multimodal baselines, including Qwen3-VL-
Embedding-2B, while maintaining concrete image-text matching after adaptation.
Read the full abstract ▾
All authors Haiming Zhao, Tai Wang, Kun Zhang, Xicheng Peng, Zhiyang Li
Artificial Intelligence
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
Caiqi Zhang, Rujun Han, Zifeng Wang et al. (+4 more)
As LLM
agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened with a fixed base model, without access to reference answers or grading rubrics at test time. Repeated sampling yields multiple rollouts that can contain complementary correct claims, but we need a reliable verification mechanism to determine which claims to trust. We first find that disagreement often exposes correct alternatives, while consensus can conceal errors. These observations motivate VeriHarness, which turns the underlying LLM a generator uses into an agentic verifier by giving it a workspace, evidence tools, and reusable verification skills. A disagreement resolver checks competing claims against environmental evidence, while a consensus challenger tests shared claims and searches for omitted requirements. Their findings guide the selection and revision of the final artifact. Across five long-horizon workspace
benchmarks and two frontier models, VeriHarness achieves the highest selection scores among the evaluated baselines. Evidence-backed revision further improves average performance, bringing gains over a single rollout to 6.2 points with Gemini 3.5 Flash and 6.4 points with Claude Opus 4.8. We further show that verification skills can self-improve from failure feedback, demonstrating VeriHarness as a novel and critical approach for scaling long-horizon agentic verification. We release the full pool of approximately 26,000 rollouts across all five
benchmarks and both models, produced at a cost of over $100,000, to support future research on agentic verification.
Read the full abstract ▾
All authors Caiqi Zhang, Rujun Han, Zifeng Wang, Zoey CuiZhu, Nigel Collier, Tomas Pfister, Chen-Yu Lee
Distributed Computing
The Other Half of Workflow Portability: Evidence-Backed HPC Site Profiles with Agentic Discovery
Md Saiful Islam and Douglas Thain
Moving a workflow developed and tested at one HPC site to another rarely succeeds without some amount of trial and error. Package managers rebuild software environments, containers ship whole filesystems, and workflow specifications such as backpacks package a workflow with its software, data, and resource requirements. These approaches address one half of workflow portability: what a workflow needs. But none describes how a given HPC site must be used, and that missing half is why even a portable workflow requires manual adjustment at each new site. That gap includes the site's resource shape, storage configuration, network permissions, and operating policies. This information may be explicit in the batch system, hidden in the prose of documentation, or buried deep within a router's configuration, making it difficult for an automated deployment tool to turn site knowledge into useful deployment decisions. We propose the HPC site profile, a structured, evidence-backed document that makes this knowledge actionable. We automatically construct it in three steps that mirror where the information lives: measuring the login node, extracting typed fields from documentation with a bounded
language-model
agent, and submitting pilot jobs for eligible unresolved fields. Every field is verified against its evidence or discarded, so a rule, not the model, decides what enters the profile. The profile then preflights a workflow into an execution plan or an early, explainable failure. We build profiles at Purdue Anvil, TACC Stampede3, and Notre Dame CRC and present a case study of preflighting a real workflow.
Read the full abstract ▾
Computer Vision
RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation
Minsu Kim, Jaesung Choe, Jiwoo Lee et al. (+2 more)
Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has followed suit – yet existing methods remain confined to object-centric perception, neglecting spatial relations between objects. We formulate 3D spatial relation
segmentation in a feed-forward, pose-free multi-view setting: given a visually specified subject and a relational text query, the model segments the target across views without receiving its category name. To this end, we propose RelationVGGT, a novel feed-forward framework that integrates semantic features from a visual foundation model with geometry-aware representations from a 3D geometry foundation model and leverages a relation
transformer for subject-conditioned, cross-view relation prediction – requiring neither per-scene optimization nor known camera poses. We additionally provide a fully automated annotation pipeline built on ScanNet++ with VLMs and LLMs, enabling scalable training data generation for this new task.
Read the full abstract ▾
All authors Minsu Kim, Jaesung Choe, Jiwoo Lee, Yu-Chiang Frank Wang, Seon Joo Kim
Computation and Language
A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models
Yingzhu Zhao, Vlad Pandelea, Han Yuan et al. (+4 more)
Large
language models (LLMs) have been increasingly used for financial document analysis, including earnings call transcripts (ECTs). Beyond generating standalone claims, users increasingly prefer grounded analyses that pair claims with verifiable citations from source documents to enable independent validation. However, evaluating such analytical claims typically requires extensive expert annotation, which is costly and difficult to scale, and real-world financial analysis commonly involves long context-question-answer triplets, further increasing task complexity. To address these challenges and
benchmark the current landscape of grounded analysis by LLMs, we propose a numeric evidence evaluation method that enables groundedness assessment without reliance on expert annotation. We also introduce an automated
dataset construction pipeline and construct ECTs-100 from the top 100 constituents of the S&P 500 to support
benchmark of both groundedness and correctness. In addition, we examine conscious incompetence, a practical failure mode in financial analysis in which LLMs must detect when available evidence is insufficient and refrain from producing unsupported
hallucinations. Empirical results show that LLMs perform well in groundedness but face notable limitations in correctness, with informational insufficiency presenting an additional challenge.
Read the full abstract ▾
All authors Yingzhu Zhao, Vlad Pandelea, Han Yuan, Bo Hu, Wuqiong Luo, Li Zhang, Zheng Ma
Machine Learning
Structure-agnostic Causal Representation Learning
Arman Behnam and Binghui Wang
Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the causal structure a priori, yet different structures demand fundamentally incompatible invariance constraints, and misspecification leads to representations that discard predictive information. We introduce SaCRL, a framework that jointly identifies the causal structure and learns the corresponding invariant representation without prior structural knowledge. Our approach formulates structure selection as a soft optimization over candidate invariances using HSIC-based violation metrics, with adaptive weights that automatically concentrate on the achievable structure. We provide theoretical guarantees for structure identification, including under random-feature approximation, invariance satisfaction, and out-of-distribution generalization. Empirically, SaCRL recovers the true structure on synthetic and semi-synthetic
Bayesian-network
benchmarks, outperforms fixed-invariance baselines on Colored MNIST, achieves state-of-the-art accuracy on three DomainBed
benchmarks (PACS, VLCS, OfficeHome), and degrades gracefully under structural misspecification and limited environment diversity. Code is available at: https://github.com/ArmanBehnam/sacrl.
Read the full abstract ▾
Information Retrieval
RPTune: Learned Context Curation for LLM Catalog Search
Chuxuan Hu, Hejie Cui, Norman Huang et al. (+3 more)
For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage
retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context window does not ensure that the model can use it effectively, since LLMs do not exploit long contexts uniformly. We therefore study in-context catalog search through two complementary questions: (1) how to curate and present catalogs to the LLM, and (2) how to adapt the LLM for product selection on curated contexts. We propose RPTune, an end-to-end framework that couples learned catalog curation with LLM post-training using automatically generated, catalog-grounded supervision. An encoder-reorganizer curator orders and prunes products guided by downstream LLM feedback, while the resulting curated catalogs in turn improve the effectiveness of LLM post-training with a context-relative reward. We evaluate RPTune on 7 real merchants spanning distinct retail verticals, using 100 complex conversational queries per merchant. RPTune consistently improves search accuracy across both proprietary and open-weight LLMs, with context curation yielding gains of up to 31.4 percentage points and post-training adding a further 10.3 points on average.
Read the full abstract ▾
All authors Chuxuan Hu, Hejie Cui, Norman Huang, Shubham Kumar Bharti, Wang-Chiew Tan, Sercan Ö. Ar{\i}k
Artificial Intelligence
Cybernetic and Epistemic: A Missing Vocabulary for Trustworthy Agentic Delegation
Jérémie Lumbroso
As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it — a shift CS-education researchers have begun to name. This shift exposes a vocabulary gap: the field asks for "human oversight" without a working distinction between the two things
language does in a delegation channel — coordinate action (cybernetic: words succeed when the world comes to match them) and coordinate understanding (epistemic: they succeed when they answer to the world and a hearer can check that they do). The failure this names is not cybernetic
language but epistemic-form
language doing cybernetic work: explanation-shaped output calibrated for approval rather than truth. Oversight that checks only whether an output was approved is satisfiable by rubber-stamping; oversight that holds an
agent accountable requires the
reasoning behind its work be retrievable and checkable. We present three delegation episodes — illustrations, not controlled evidence — in which epistemic engagement proved practicable while remaining auditable, one public record where a recommendation was withdrawn on its own stated terms, and one failure case illustrating oversight that requires no reasons for its discretionary choices. We propose a criterion for agentic-system governance, alongside existing technical trust properties: every consequential choice should carry the condition under which it would have gone otherwise, in a form a third party can test. Without such a condition, a third party cannot distinguish a decision from a rubber stamp. We give the criterion an operational form — a two-part reconstruction test scoring a delegation record by whether a second reader can predict what the
agent does under a perturbation — and a deliberation-recording convention, ORRCF, that makes the condition a required component of every recorded choice.
Read the full abstract ▾
Computer Vision
Video-Index: A Curated Meta-Benchmark for Video Understanding
Enxin Song, Yinuo Xu, Shusheng Yang et al. (+2 more)
A
video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence. We introduce the attack pyramid, five levels of shortcut attacks with increasing access to each item, and audit 115
video benchmarks with it. On 35
benchmarks, attackers that never see a frame approach full-
video accuracy. On 51
benchmarks with temporal probes, shuffled frames keep a median 96% of full-
video accuracy. Near-duplicate questions make up at least half the items in 63
benchmarks. We screen 505,518 question-answer pairs from 112 of them into an audited pool.
Agents turn evaluation requests into specifications, and a deterministic selector with a red-team gate composes reproducible
benchmarks. We release
Video-Index, the 210 hardest verified items under these attacks in each of four capability groups, 840 items from 76 sources. With the same fixed input, Claude Opus 5 outscores every open-source model by over 37 percentage points, and
agent tools add about 20 more, yet all systems leave room to improve efficiency and accuracy. Blog: https://www.enxinsong.com/blog/
video-index/ GitHub: https://github.com/Espere-1119-Song/
Video-Index Hugging Face: https://huggingface.co/
datasets/
Video-Index/
Video-Index
Read the full abstract ▾
All authors Enxin Song, Yinuo Xu, Shusheng Yang, Wenhao Chai, Jiatao Gu
Computation and Language
Role-aware Heuristic Episodic Attention for Conversational LLMs
Wanyang Hong, Zhaoning Zhang, Yi Chen et al. (+5 more)
Large
language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three related failure modes:
attention pollution, dilution, and drift. We propose REA (Role-aware Heuristic Episodic
Attention), a context-management framework that assigns different persistence and representation policies to instructions and episodic interactions. Instructional
Memory retains identified global constraints in a dedicated prefix. Episodic
Memory preserves user inputs and compresses model replies, while heuristic
retrieval selects raw text, compressed representations, or omission for each historical turn. On Long-MT-Bench+, REA improves the judge score from 6.32 to 7.36 on a 10-point scale, a 16.5% relative gain over the Vanilla baseline, and reduces average latency by 2.91$\times$. Additional evaluations show aggregate gains on three backbones spanning 1.7B-7B parameters and on Chinese and English role-playing tasks. These results support role-aware context management as a practical approach to maintaining conversational continuity and instruction adherence.
Read the full abstract ▾
All authors Wanyang Hong, Zhaoning Zhang, Yi Chen, Libo Zhang, Baihui Liu, Linbo Qiao, Zhiliang Tian, Dongsheng Li
Computation and Language
Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles
Alexei N. Skurikhin, Emily M. Taylor and Nathan A. DeBardeleben
As large
language models (LLMs) move from standalone assistants into agentic workflows, evaluation must extend beyond scalar leaderboard accuracy to account for operational reliability, cost, latency, and
token efficiency. We use an agentic ensemble of small
language models (SLMs) with an SLM-judge-mediated feedback loop as a case study for such beyond-leaderboard evaluation. On the 541-
prompt IFEval
benchmark, the best ensemble achieves 97.34% strict
prompt accuracy, exceeding the strongest standalone LLM baseline, gpt-5.4, by 5.81 percentage points while operating in a lower-cost regime. We then analyze the tokenomics and operational behavior behind this gain, including cost per sample,
token composition, useful-output goodput, feedback-loop recovery, latency decomposition, and performance across instruction categories and constraint counts. Our results show that agentic SLM ensembles can trade additional test-time
tokens and orchestration overhead for improved instruction-following fidelity, motivating multi-dimensional evaluation protocols for future agentic AI systems.
Read the full abstract ▾
Computer Vision
Two Clocks in Diffusion MLLMs: When Answers Stabilize Before Rationales Unfold
Keuntae Kim and Yong Suk Choi
An answer candidate in a masked
diffusion MLLM can stabilize while its rationale is still unfolding. We distinguish retrospective stabilization of the logged candidate from
token commitment, and examine these two clocks relative to rationale generation. Analyzing our results across three visual question-answering
benchmarks, we find that 89.4-98.1% of the rationale-side canvas remains unwritten at stabilization in single-block, EOS-suppressed LaViDa runs. On V*Bench, reducing block length from 128 to 8 changes this fraction from 89.4% to 1.7%, together with answer coverage and the eligible observation window. Under EOS-enabled prompting, direct instructions improve Nemotron's overall accuracy by 15.0 and 19.5 percentage points on M3CoT and ScienceQA, but reduce LaViDa/V*Bench accuracy by 11.0 points. A symmetric decomposition associates the larger absolute component of each change with coverage rather than conditional accuracy. Matched-canvas image ablations measure visual sensitivity alongside answer stabilization, separating the two temporal readouts. Together, these measurements distinguish answer stabilization, rationale unfolding, and visual sensitivity, and identify coverage as the larger component of the prompting differences.
Read the full abstract ▾
Computer Vision
A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions
Giyeong Oh, Junghun Park, Yuhan Bae et al. (+1 more)
Recaptioned image-text corpora are now standard for text-to-image (T2I) training, with
vision–
language model (VLM) captioners replacing sparse alt-text by dense descriptions. A recaptioned corpus is a supervision distribution induced by a documented captioning policy ($\pi$), captioner ($V_c$), and source corpus ($C$). Length-correlated proxies miss caption-register artifacts and downstream T2I
benchmarks entangle the corpus with training choices, so this distribution is hard to audit at corpus scale. We introduce a reusable matched-budget audit framework for recaptioned supervision distributions $D_{\pi,V_c,C}$: at a fixed text budget of $B = 64$ it reports a five-axis profile spanning
prompt-side coverage, image-conditioned faithfulness, and caption-surface health, with claimed controllable basic units (CBU) as the common claim unit. We instantiate the framework on seven paired comparisons over five public source corpora. Across the four cross-corpus pairs, the released surface raises supported CBU per caption by $+3.39$ to $+6.36$ under both Qwen and Gemma Judges, and on CC12M the same framework exposes a long-vs-dense frontier that is consistent across both judges and four budgets. We release the audited multi-source recap corpus ($\approx$ 490M) together with the audit-artifact bundle.
Read the full abstract ▾
All authors Giyeong Oh, Junghun Park, Yuhan Bae, Youngjae Yu
Artificial Intelligence
PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
Ronghua Li, Zi Liang, Zhishan Li et al. (+1 more)
Supervised fine-tuning (SFT) on offline
agent trajectories is the standard approach for training specialized tool-using
agents, but forcing models to imitate
reasoning and actions
token by
token may harm other capabilities (e.g., general
reasoning, tool calling, code generation) of the base model. In this work, we focus on studying how to better balance the trade-off between acquiring new capabilities and preserving existing ones during
agent trace SFT. By comparing several baselines in our setup, standard SFT improves the target
benchmark while lowering several non-target
benchmark scores; meanwhile, simply constraining distributional drift using KL penalty or limiting the update magnitude did not avoid this regression trend. Motivated by recent
token-wise adaptive learning objectives, this work proposes Privilege-Guided SFT (PG-SFT) to leverage turn-level information gain of
agent trajectories as an indicator to adjust supervision strength. PG-SFT yields a more favorable observed trade-off on the evaluated
benchmarks, substantially reducing distributional drift and broad capability degradation at the cost of slight degradation in target-task performance. Our findings suggest that balancing the acquisition–retention trade-off depends not only on whether the model is anchored to its base behavior, but also on where and how strongly supervision should depart from that behavior.}
Read the full abstract ▾
All authors Ronghua Li, Zi Liang, Zhishan Li, Shinan Liu
Machine Learning
GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
Geyi Yang, Zikun Qu, Xiang Li et al. (+4 more)
The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled. Compared with harness optimization for non-GUI
agents, automatically optimizing this harness poses three coupled challenges: reconciling model intent with observed visual effects, diagnosing failures under variable execution outcomes, and identifying recurrent failure patterns across tasks and translating them into reusable runtime changes. We introduce GUI-HARVEST, an automatic harness optimizer that enables self-improving GUI
agents with frozen backbone models. First, to ground diagnosis in observed action effects, it aligns model outputs and executed actions with before-and-after screenshots, tying findings to specific interface transitions. Second, to account for execution variability, it treats repeated runs of the same task as a joint evidence unit, using within-task comparisons to locate outcome-relevant behavioral differences. Third, it consolidates verified findings across tasks into recurring failure patterns, maps them to bounded source-code edits with predictions recorded before evaluation, and checks the predicted behavioral effects alongside task performance through repeated execution. Experiments on OSWorld-Verified show consistent held-out gains across six general-purpose open, GUI-specialized open, and proprietary backbone models; Qwen3-VL-32B-Instruct gains 12.33 points on the full suite. Frozen-harness transfer improves GPT-5 by 13.87 percentage points on WindowsAgentArena at 50 steps without further optimization. With the same backbone and initial harness, GUI-HARVEST outperforms Self-Harness and Meta-Harness, suggesting that GUI-specific diagnosis and validation help harness improvements generalize to unseen tasks. The code is available at https://github.com/GaryYang12345/GUI-HARVEST.
Read the full abstract ▾
All authors Geyi Yang, Zikun Qu, Xiang Li, Zhiyong Wang, Min Zhang, Shipei Zeng, Zhongxiang Dai
Artificial Intelligence
ABDA-NL: A Natural-Language Scenario Explorer for Argument-Based Reasoning
Shawn Bowers, Martin Caminada, Haoyang Liu et al. (+1 more)
ABDA-NL adds a natural-
language interface to ABDA, a system for argument-based discussion using ASPIC- knowledge bases under grounded semantics. Users see which conclusions are accepted, rejected, or undecided, open an interactive rendering of the grounded discussion game to learn why, explore what-if alternatives by suspending assumptions and rules or changing preferences, ask questions that are answered from a scenario's reference documents, and author new facts, assumptions, and rules in plain English. A large
language model provides the bridge between
language and formalism: it answers questions from the documents and the current state of the scenario, and it translates plain-English edits into candidate formal statements. The deterministic ABDA engine remains the sole source of arguments, attacks, and acceptance labels, and every proposal of the model is validated and confirmed by the user before it takes effect.
Read the full abstract ▾
All authors Shawn Bowers, Martin Caminada, Haoyang Liu, Bertram Ludäscher
Data Structures and Algorithms
Best of Two Worlds: Combining High and Low Resolution to Compute Viewsheds on terrains
Laura Toma
The viewshed of a point $v$ on a grid terrain $T$, viewshed$_T(v)$, is defined as the set of grid points in $T$ that are visible from $v$. We describe a novel
algorithm for computing viewshed$_T(v)$ using a multi-resolution approach: Given a parameter $k >1$ that represents the block size, we create a grid $T'$ which is a lower-resolution version of $T$, such that each point in $T'$ corresponds to a block of $\lceil \sqrt k \rceil $-by-$\lceil \sqrt k \rceil$ points in $T$. The key of our approach is using $T'$ to speed up the computation of viewshed$_T(v)$ while not introducing approximation. We compute viewshed$_T(v)$ in two steps: First we compute the viewshed of $v$ on $T'$, while maintaining the invariant that any block in $T'$ that is labeled as invisible may not contain any visible points. Thus, the first step's role is to use $T'$ to filter out blocks in $T$ that are guaranteed to be invisible. The second step considers the blocks that were labeled as visible in $T'$ and computes the visibility of their points with full accuracy using the data in $T$. Overall the
algorithm runs in $O(n + \frac nk \lg \frac nk + k \lg k + l \cdot \lg n)$, where $l$ is the total size of visible blocks in $T'$. When $k = \Omega(1)$ and $l = o(n) $, the running time of our
algorithm improves on the previous best bound of $O(n \lg n)$. Our experimental results show the performance of the new
algorithm in practice and a speedup of more than an order of magnitude compared to previous
algorithms.
Read the full abstract ▾
Computation and Language
ReHoPER: Receding-Horizon Planning for Enhanced Reasoning
Saeed Ahmadnia and Cornelia Caragea
We propose ReHoPER, an inference-only, zero-shot method that improves large
language models'
reasoning by generating and answering intermediate questions along multiple paths before the final answer. It iteratively plans a horizon of candidate intermediate questions, selects one to answer, and replans from the updated history. ReHoPER is task-agnostic, using the same generic instructions across
datasets and models without labeled data or task-specific
prompt design. Across multiple
datasets, including iLLC, a new controlled
benchmark for compositional
reasoning, ReHoPER outperforms strong baselines, with the largest gains in the most compositional settings. Our implementation and the iLLC generator are publicly available to support future work.
Read the full abstract ▾
Robotics
ShowerFlex: Achieving Pseudo-Static Balancing in a Continuum Shower Hose
Zhiyu Ren and Girish Krishnan
With the global population rapidly aging, maintaining independence in Activities of Daily Living (ADLs), particularly bathing or showering, has become a critical challenge. Older adults who sit while showering currently have limited options, often relying on rigid overhead showerheads or flexible hand-held hoses that require continuous gripping and precarious user maneuvers, increasing the risk of falls. To address this need, this paper introduces a highly articulated, pseudo-static balanced continuum mechanism designed specifically for accessible bathing assistance. The proposed mechanism features a modular continuum architecture composed of friction-locked ball-and-socket joints (loc-line), seamlessly integrated with a retractable spring-loaded reel for effective
gravity compensation. This hybrid design achieves an intuitive "Push-and-Stay" interaction logic, maintaining an approximate static
equilibrium with ergonomically low actuation force, without any external electronic power, while significantly minimizing the force needed for repositioning. Theoretically, we established a recursive forward kinematics framework to construct the
geometric model of the structure, coupled with a comprehensive static
equilibrium analysis to evaluate the system's holding capacity across its 51-DOF structure. Numerical simulations utilizing Monte Carlo methods validate the system's morphological adaptability and stability at various extreme positions within a standard bath space. Physical experiments further validate the prototype's real-world performance, confirming its intrinsic static stability against
gravity and ensuring that the actuation force remains well within the ergonomic capabilities of older adults. Ultimately, this research provides a low-cost, intrinsically safe showerhead design that reduces physical strain, restoring dignity and autonomy in personal hygiene.
Read the full abstract ▾
Sound
RMS-AQA: A Two-Stage Spatial Audio Question Answering Benchmark for Real-World Domestic Environments
Peihao Chen, Qing Wang, Lichun Fan et al. (+12 more)
Embodied assistants in domestic environments must infer what happened, where and when it occurred, and how to respond. To address this, we introduce RMS-AQA, a spatial audio question answering (SAQA)
benchmark for real-world domestic environments. The
benchmark features a two-stage question-answering (QA) format to comprehensively assess the ability of audio-
language models (ALMs) to first ground audible sound events and subsequently perform complex spatio-temporal
reasoning based on that grounding. To maximize acoustic realism, our
dataset combines authentic real-world first-order Ambisonics (FOA) recordings with high-fidelity synthetic data generated using measured room impulse responses (RIRs). Furthermore, we provide a lightweight spatial plug-in that injects FOA-format data into frozen audio-
language backbones. Experimental results reveal that the primary challenges stem from concurrent sources, far distance, and sim-to-real domain gap between RIR-synthesized and authentic recordings.
Read the full abstract ▾
All authors Peihao Chen, Qing Wang, Lichun Fan, Yufeng Hao, Zhifeng Kong, Mengyao Zhu, Hengyi Hong, Hang Chen, Hang Su, Yujie Jian, Chao-Han Huck Yang, Shichao Hu, Jun Du, Jian Luan, Ke Li