Computation and Language
Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking
Taehyeon Kim, Hyunsoo Lee, Youngsoo Jang et al. (+1 more)
Large
reasoning models (LRMs) achieve strong performance by externalizing explicit
reasoning traces before producing the answer, yet suffer from overthinking challenge that allocates uniformly heavy computation to queries of varying difficulty. While proprietary models mitigate this via opaque routing, open-source LRMs still lack an efficient mechanism to internalize adaptive
reasoning due to both expensive training cost and limited disclosure of training recipes. In response, we introduce RPO (Root-
token Policy Optimization), a framework that enables LRMs to self-determine when to reason by training only the initial root
token (e.g., whether to invoke the <think> tag) via group relative reward and group-wise advantages. By focusing on this pivotal branching point, RPO drastically reduces training overhead and VRAM usage. Across multiple model families and scales, RPO learns difficulty-aware adaptive thinking at just ~2% of the training compute of prior adaptive-
reasoning methods.
Read the full abstract ▾
All authors Taehyeon Kim, Hyunsoo Lee, Youngsoo Jang, Moontae Lee
Computational Engineering
PROTEAN: Beyond De Novo Generation - Can LLM Agents Perform Text-Guided Protein Structure Editing?
Encheng Su, Xinping Liu, Yizhou Wang et al. (+11 more)
Generative AI has achieved remarkable success in de novo
protein design, yet
protein engineering typically begins with existing, characterized
proteins. The primary demand is targeted local editing, e.g., engineering a specific region to optimize affinity, alter immunogenicity, or improve stability, while strictly preserving core catalytic motifs and overall scaffold integrity. However, no standardized framework currently exists for carrying out and evaluating such edits. In current generative-design workflows, researchers often need to manually specify complex low-level parameters and rely on repetitive, trial-and-error sampling and evaluation across generative backends to search for viable conformations. While large
language models (LLMs) offer an intuitive interface to express these goals using natural
language, prevailing structure-generation models cannot directly interpret high-level human instructions. To bridge this gap, we introduce PROTEAN, a standardized
benchmark for text-guided
protein structural editing. PROTEAN comprises 380 sub-tasks spanning six intervention families and evaluates a two-stage pipeline in which an LLM translates natural-
language goals into backend-specific
geometric constraints and a generative model remodels the
protein backbone. A two-tier evaluation separates
geometric compliance, including target attainment and off-target scope fidelity, from biophysical realizability assessed by inverse folding and refolding consistency. Across five frontier LLMs paired with three backends, strict end-to-end biophysical success starts at just 7.0%. Ablation studies show that LLM constraint compilation is already highly accurate, whereas the main bottlenecks are backend-specific scope leakage and refolding failure. PROTEAN provides an open testbed for developing autonomous, multi-backend macromolecular design
agents.
Read the full abstract ▾
All authors Encheng Su, Xinping Liu, Yizhou Wang, Bozitao Zhong, Pengze Li, Jianyu Wu, Mingxiao Li, Xinzhu Ma, Aoran Wang, Liang Hong, Wanli Ouyang, Chen Tang, Houqiang Li, Shixiang Tang
Artificial Intelligence
Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation
Yufeng Li, Sheng Yao, Peng Zeng et al. (+5 more)
Long-term
memory supports
agents across sessions. Repeated
retrieval and write-back can let one historical claim occupy multiple
retrieval positions and influence current answers without independent evidence. Existing work examines
retrieval, updating, and question answering, leaving same-source record accumulation and post-correction persistence underexplored. Motivated by research in social cognition and
memory psychology on repeated exposure,
retrieval, and revision, we define
Memory Echo as the excess
retrieval exposure gained by historical information from the same source without additional independent evidence, and introduce MEchoBench to evaluate its emergence, correction resistance, persistence, and effect on answers. To address this phenomenon, we introduce the Family–Provenance–Authority framework (FPA). Specifically, FPA selects one representative per source family, conditions the eligibility of old records for the answer context on verified corrections, and constrains final answers with authoritative evidence. In paired replay on 190 fixed questions across four
memory frameworks, FPA raises accuracy from 0.825 to 0.920 with DeepSeek V4 Flash and from 0.782 to 0.916 with Kimi K2.6; mean Decision Contamination Effect falls from 0.106 to 0.030 and from 0.109 to 0.038, respectively. These results show that
agent memory can preserve traceable history without allowing repeated historical information to govern current decisions. The code is available at https://github.com/OrcasSam/
memory-echo-
benchmark.
Read the full abstract ▾
All authors Yufeng Li, Sheng Yao, Peng Zeng, Dezhang Kong, Shi Lin, Changting Lin, Xun Wang, Meng Han
Artificial Intelligence
Autonomous 3D Visual-Thermal Inspection for Utility-Scale Solar Farms
Lachlan Tychsen-Smith, Mark Cox, Brett Wood et al. (+6 more)
Utility-scale photovoltaic (PV) inspection is dominated by aerial surveys, which are effective for identifying module-level hot
cells but provide limited visibility of critical components located under the array, including connectors, cabling, fasteners and structural elements. These assets are difficult to inspect consistently at scale, and their defects are often spatially small, partially occluded and difficult to localise from isolated images. We present an automated 3D visual-thermal inspection system (Tricorder) for under-panel PV asset inspection. The approach combines
LiDAR-inertial Simultaneous Localization and Mapping (SLAM) with geometrically calibrated RGB and thermal imagery and machine-learning-based object detection and segmentation. Detected assets are associated with the reconstructed 3D environment, allowing visual and thermal observations from multiple viewpoints to be spatially fused and localised. We demonstrate the approach on utility-scale PV data for MC4 connector detection and connection-state recognition, thermal anomaly identification, and detection of structural components including bolts, nuts and torque tubes. The results demonstrate a pathway from image-based inspection toward spatially grounded autonomous inspection, where defects are detected and linked to specific assets and their 3D locations within the solar farm.
Read the full abstract ▾
All authors Lachlan Tychsen-Smith, Mark Cox, Brett Wood, David Haddon, Kenrick Anderson, Benjamin Duck, Jim O'Malley, Noel W Duffy, Peyman Moghadam
Computation and Language
Connecting the Dots: Enduring Performance Gaps in ASR Systems Between Standard and Minority English Varieties
Alexander Metzger, Aruna Srivastava, Ruslan Mukhamedvaleev et al. (+5 more)
Automatic
Speech Recognition (ASR) system evaluations have consistently revealed performance disparities along lines of race, gender, socioeconomic status, and
language variety. While these disparities are well-documented, they are often (implicitly or explicitly) treated as issues that subsequent, larger, and more universal models will correct. We challenge this assumption of steady progress in reducing accent-related performance disparities, conducting a longitudinal evaluation of 16 prominent systems released between 2021-2025 across 8
datasets representing diverse English accent varieties. We find that the performance disparity between Mainstream US English (MUSE) and minority accents is stubborn, not reliably declining as a function of time. Specifically, while systems are reliably performant on MUSE, minority accents are subject to risks of large performance degradations between generations of systems, sometimes worsening by 65% absolute Word Error Rate. We argue that standard ASR
benchmarks enact an implicit
language policy privileging Mainstream US English varieties. As such, these performance disparities reflect systemic failures of
language technology development infrastructure that disproportionately affect underrepresented speaker populations.
Read the full abstract ▾
All authors Alexander Metzger, Aruna Srivastava, Ruslan Mukhamedvaleev, Eunjung Yeo, Syed Ishtiaque Ahmed, Nina Markl, Sachin Kumar, Farhan Samir
Machine Learning
Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
Shuang Wu
Gaussian process bandits exploit similarities among configurations to optimize
prompts,
retrieval systems, and
agent workflows. In these applications, however, inexpensive model-based evaluations can disagree with trusted task outcomes. We study selective verification when an action is chosen before a diagnostic is observed and trusted feedback is informative on an unknown set of diagnostic states. A finite reliability class and a finite RKHS signal dictionary describe these two sources of uncertainty. We construct a fixed audit design that combines reliability coverage with reward separation and establish a finite-time regret bound that accounts for a hard audit budget and the rounds needed to obtain informative observations. A safe adaptive extension mixes this robust design with predictable Chernoff allocations while preserving a uniform identification floor and exact expected acquisition-cost accounting. For signed-coordinate kernels, structured and diffuse reliability classes require different audit scales despite sharing the same reward geometry. Synthetic experiments distinguish these certified designs from an adaptive posterior heuristic and GP controls. Safe adaptive allocation reduces aggregate regret relative to the fixed design under the exact dictionary, but its finite-budget error certificate is numerically loose. Conditional-feedback errors can remove the heuristic's advantage and target perturbations can reverse it. Separate AI-task replays assess feedback correction and fitted-dictionary policies without establishing end-to-end validation of a learned selective-verification method.
Read the full abstract ▾
Numerical Analysis
POD-accelerated high-order multiscale method with corrected-basis reconstruction for transient multi-continuum problems
Jiayuan Peng, Hao Dong and Jiale Linghu
Multi-continuum models provide an effective macroscopic description of transient flow in fractured and highly heterogeneous porous media by introducing several interacting state variables at each macroscale location. Although high-order multiscale (HOMS) methods reduce the cost of resolving microscopic heterogeneities while recovering local oscillatory features, repeated solution of the coupled homogenized system and repeated high-order reconstruction remain expensive in long-time and large-scale three-dimensional simulations. This work develops a proper orthogonal decomposition (POD) accelerated HOMS framework for transient multi-continuum problems. A vector-valued POD space is constructed from snapshots of the coupled homogenized solution, and the resulting block system is projected onto a low-dimensional space. Two recovery strategies are considered. The first reconstructs the reduced homogenized fields and performs full HOMS assembly at every output time. The second applies the spatial part of the multiscale recovery operator to retained POD modes offline and evaluates the online solution by direct linear combinations of corrected bases and time-derivative bases. An error estimate between the fully discrete homogenized solution and its POD-reduced approximation is established for the coupled system. A recovered POD-HOMS estimate is then obtained by combining the HOMS consistency error with POD truncation errors propagated through value, gradient, inter-continuum exchange, second-derivative, and time-derivative recovery terms. Numerical experiments for two- and three-dimensional heterogeneous configurations show that the reduced solutions retain the accuracy and local oscillatory behavior of the corresponding HOMS solution while substantially decreasing computational cost.
Read the full abstract ▾
Artificial Intelligence
Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents
Kaiming Liu, Yuxuan Liu, Jinrui Ju et al. (+4 more)
Large
language model
agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incomplete. In our analysis of 100 user-
agent trajectories from SWE-chat, 56% of initial instructions omit requirements that later emerge as necessary, and 52% of the useful follow-up requirements could have been inferred from the project. A user states requirements from their own understanding of the task, and these stated requirements often differ from the true requirements that completing the task imposes. An
agent should therefore treat the instruction as evidence rather than as the objective, inferring the true requirements from the instruction and the environment and satisfying them even when the user is not yet aware of all of them. We call this ability outcome
alignment. In this work, we construct TiGanEval, a
benchmark of software engineering and research tasks. In every task the user genuinely lacks part of the requirements, each requirement stays discoverable from the code and runtime behaviour of the environment, and requirements the
agent infers are separated from those the user adds after observing delivered work. These properties together make outcome
alignment measurable. Evaluating eight frontier models including GPT-5.6-Sol, we find outcome
alignment broadly missing: the models lose 53 to 67 points of success rate when moving from the full specification to the partial instruction, and consequence feedback across four submissions does not close the gap. Furthermore, a plan-mode harness cannot compensate for the missing ability of the model itself, which places outcome
alignment among the abilities the next generation of models should be developed for.
Read the full abstract ▾
All authors Kaiming Liu, Yuxuan Liu, Jinrui Ju, Minyuan Ruan, Xuanyu Lei, Peng Li, Yang Liu
Emerging Technologies · Cross-listed from quant-ph
PADO-Pauli: A GPU-Accelerated Implementation of Pauli Propagation
Hyunwoo Kim and Youngseok Lee
Variational
quantum algorithms utilize parameterized
circuits many times during training, at new parameter values, over batches of data, and with gradients. Pauli propagation approximates the expectation values of such
circuits classically by evolving the observable in the Heisenberg picture as a truncated sum of Pauli strings. We present PADO-Pauli, a GPU engine for Pauli propagation that compiles a
circuit and its observables once into sparse
matrices in which each rotation angle contributes only a cosine and a sine factor, so every later evaluation reuses the compiled program. It evaluates batches of parameters and data inputs embedded as rotation angles. By default its gradients come from a vector-Jacobian product registered with PyTorch's automatic differentiation, so they flow through the angles to any classical layer that produces them. PADO-Pauli also provides truncation by Pauli weight and coefficient size, and noise channels. Zero-filtering removes terms that do not contribute to an expectation value in the all-zero reference state and makes the batched forward pass about 1.5 times faster. Compared to cuPauliProp on an NVIDIA A100, PADO-Pauli evaluates up to 10 times faster on 4 to 12
qubits and uses up to 3.1 times less
memory on 16
qubits. We check its accuracy against exact statevector simulation up to 28
qubits. These features make PADO-Pauli a practical toolkit for training variational
quantum algorithms, including
quantum machine learning models.
Read the full abstract ▾
Multiagent Systems
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Yiqing Peng, Hehai Lin, Zixuan Wang et al. (+7 more)
Large
language model (LLM)-based multi-
agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream
agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor different DoF configurations, while atomic-target conditions are more consistent across runs. In-domain retained experience brings the two branch profiles closer together. The same controlled sweep reveals a task-dependent coordination landscape: some domains exhibit higher-performing configurations, whereas others show flatter responses and no single configuration dominates across domains. In five of the six evaluated state, an intermediate DoF configuration achieves higher mean accuracy than both endpoints, demonstrating the value of exploring the coordination space between them. Together, these findings provide empirical guidance for studying and designing intermediate coordination regimes in LLM-based MAS.
Read the full abstract ▾
All authors Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu, Yi Han, Yangyang Zheng, Hao Wang, Qian Li, Chengwei Qin
Robotics
Learning Robot Policies for Whole-Body Mobility Assistance via Dynamic Human Motion Generation
Shikun Ban, Shohei Nagai, Qingyang Song et al. (+4 more)
Robotic assistance for human mobility could benefit care recipients and reduce caregiver burden during physically demanding tasks such as Sit-to-Stand (STS) and Lift-and-Transfer (L&T). Learning
robot policies for these whole-body assistive tasks is challenging: real-world data collection for human-
robot interaction is costly and safety-critical, making simulation an attractive alternative. Prior work, however, typically treats the human as static or minimally responsive and thus fails to capture the cooperative nature of mobility assistance. We present a simulation-based framework for learning whole-body assistive
robot policies. At its core is a human policy trained with an
adversarial motion prior that produces realistic care-recipient motion in response to the
robot's actions. A human-adaptive scripted controller interacts with this policy to collect diverse
robot demonstrations at scale. From these demonstrations, we train 3D
diffusion policies that map segmented human point clouds and
robot joint positions to whole-body actions for a mobile manipulator, without relying on privileged human state at deployment. The resulting
robot policies successfully perform both STS and L&T assistance in simulation. Preliminary experiments further demonstrate sim-to-real transfer for STS after fine-tuning on a small amount of real-world data.
Videos are available on our project page: https://rchi-lab.github.io/human-gen-mobility-assistance/
Read the full abstract ▾
All authors Shikun Ban, Shohei Nagai, Qingyang Song, Hanxi Wan, Eric Zhao, Thomas Wang, Zackory Erickson
Robotics
I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation
Wensi Ai, Christopher Luey, Karthik Dharmarajan et al. (+7 more)
Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-horizon whole-body mobile manipulation, where long horizons amplify compounding errors and coordinated arm, torso, and base motion makes exhaustive demonstration coverage impractical. We introduce I3L, an integrated hardware and learning system that combines whole-body correction with iterative policy refinement to address this last-mile reliability gap. Its low-cost, open-source JoyLo+ interface uses policy-tracking leader arms and touch-triggered takeover to enable coordinated corrections across the body parts, while iterative deployment and retraining allow operators to target failures of the updated policy. We evaluate I3L across three
robot embodiments and eight simulated and real-world tasks, including four long-horizon whole-body mobile manipulation tasks. Controlled simulation experiments show that four-round HG-DAgger achieves the highest final success on both tasks. Under this protocol, I3L improves autonomous success over the base policies by an average of 68.3 percentage points and achieves at least 90% success on every task, outperforming demonstration-only training by 35.6 percentage points on average with the same number of training trajectories. Averaged across tasks, takeover duration per episode decreases by 72% over four rounds. Together, these results show that I3L helps close the last-mile gap between offline training and reliable deployment and provides practical insights into collecting and using corrections for long-horizon whole-body mobile manipulation.
Videos, visualizations, and appendix are at https://i-3l.github.io/.
Read the full abstract ▾
All authors Wensi Ai, Christopher Luey, Karthik Dharmarajan, Evans Han, Yunfan Jiang, Stef Ren, Jianwen Xie, Jiajun Wu, Li Fei-Fei, Ruohan Zhang
Computation and Language
Auditing Failure Attribution: Label Predictability and Judge Behavior
Tianyang Xu and Jing Gao
Failure-attribution
benchmarks ask an LLM judge which step or
agent caused a failure. A high score should mean the judge checked the faulty step against the run (a cross-step check). However, spurious signals (surface cues) that predict the annotation can produce a high score. In this paper, we propose four tests to separate checking from cue use. Input restriction asks whether partial input predicts the annotation. Cue following checks whether moved cues change answers. Residual accuracy scores judges where cue-only predictors fail. Aggregation asks whether the failure mix or metric changes rankings. Real observations motivate these tests: on three
benchmarks, simple predictors match or beat GPT-4.1. In two Who&When Pro systems, a classifier reading one step's
reasoning finds 95-100% of faulty steps, motivating input restriction. In one of them, error injection leaves no
reasoning after the faulty step; judges fine-tuned on its labels beat GPT-4.1 by 41 points. Adding task-related
reasoning after that step moves this cue: fine-tuned judges lose 31-99 points, but zero-shot judges lose at most 9, motivating cue following. On Aegis, blaming every
agent matches GPT-4.1 on micro-F1 but trails by 19 points in exact-set accuracy, motivating aggregation. We recommend reporting these tests when developing failure-attribution
benchmarks.
Read the full abstract ▾
Robotics
The Human–VLA Communication Gap: What Humans Leave Implicit and What Policies Cannot Recover
Yiqing Xu and Jiajun Wu
A
robot may know how to perform a task yet fail when a human asks for it naturally. We study this human–VLA communication gap by separating an information gap, where task semantics, grounding, or event structure remain unresolved, from a residual execution gap, where even a fully specified task depends on how it is organized and invoked. To do this, we characterize how people naturally express demonstrated objectives and evaluate controlled variants of the same physical tasks, with detailed analysis on $\pi_{0.5}$ and consistent trends on $\pi_0$-FAST and Cosmos3-Edge. Our study reveals that humans increasingly compress instructions as tasks grow, relying more on contextual grounding and implicit execution structure. Current policies are misaligned with this behavior: they tolerate grounding dependence relatively well, but struggle when task semantics or event structure must be reconstructed. Even after the information gap is resolved, execution remains sensitive to command granularity and invocation state. These findings identify concrete targets for human-centered policy learning and interfaces that better bridge natural human objectives to
robot behavior. Project website: https://commgap.github.io/.
Read the full abstract ▾
Game Theory
A Matroid Generalization of Weighted Popular Matching: Characterization and Algorithm
Yuni Iwamasa, Yusuke Kobayashi, Ryoga Mahara et al. (+1 more)
We study a problem that unifies two major generalizations of popular matchings in the one-sided preference model. In a bipartite graph in which each vertex, or applicant, on one side has preferences over the adjacent vertices, a matching is called popular if it does not lose a head-to-head election against any other matching. Since the seminal work of Abraham, Irving, Kavitha, and Mehlhorn, who gave the first
polynomial-time
algorithm for finding a popular matching, numerous generalizations of the popular matching problem have been investigated. Two prominent directions are weighted popular matchings, in which each applicant is assigned a voting weight, and popularity problems under matroid constraints. The former admits a
polynomial-time
algorithm due to Mestre, while the most general form of the latter is the popular common independent set problem, for which a
polynomial-time
algorithm is given by Kavitha, Makino, Schlotter, and Yokoi. In this paper, we introduce the weighted popular common independent set problem, which simultaneously generalizes weighted popular matchings and popular common independent sets. Our main result is the first
polynomial-time
algorithm for this problem. A key ingredient of the
algorithm is a solution-independent characterization of weighted popular common independent sets, which we establish in this paper. As consequences of our algorithmic result, we obtain
polynomial-time
algorithms for several previously unresolved problems, including weighted popular matchings with matroid constraints and weighted popular branchings.
Read the full abstract ▾
All authors Yuni Iwamasa, Yusuke Kobayashi, Ryoga Mahara, Kenjiro Takazawa
Computer Vision
AttenIR: Aligning Dense Visual Attention with Mesh Warping for Unsupervised Image Retargeting
Yun Zhang, Zhiruo Zhang, Lifei Zhu et al. (+5 more)
Image retargeting aims to resize images while preserving salient content free from distortion and stretching. Recent learning-based solutions reduce reliance on traditional hand-crafted features and optimization procedures, leading to more efficient and generalizable performance. Nevertheless, existing approaches still struggle to preserve global structure and content fidelity. To address these limitations, we propose AttenIR, an unsupervised image retargeting framework requiring no manual labels, based on content-aware mesh warping, which ef- fectively couples dense visual
attention with sparse mesh constraints. We for- mulate the mesh deformation as a vertex displacement regression task. Guided by saliency priors, our method jointly optimizes scale, structure, and geometry preservation losses. By combining dense visual
attention with semantic features, it achieves robust, unsupervised retargeting without manual annotations. Our primary contributions include (1) a lightweight unsupervised method for image retargeting that ensures content fidelity and preserves global structure, and (2) a coarse-to-fine projection strategy to align dense visual
attention priors with sparse mesh constraints, enabling content-aware deformation at the pixel level. Experiments demonstrate that our method achieves competitive and superior performance compared with both traditional and state-of-the-art learning-based methods.
Read the full abstract ▾
All authors Yun Zhang, Zhiruo Zhang, Lifei Zhu, Zhe Zhu, Tong Li, Fang-Lue Zhang, Shengjuan Liu, Xinyuan Zheng
Computation and Language
Geometric Structure Predicts Per-Example Neighborhood Loss Under PCA Truncation
Sriram Loganathan, Gokul Anand and Ragavan Arivazhagan
Dimensionality reduction can preserve the average performance of text
embeddings even when a substantial fraction of their dimensions is removed. Aggregate metrics, however, do not reveal whether degradation is distributed uniformly across examples. We study per-example neighborhood stability under PCA truncation across static word
embeddings and modern sentence encoders. Per-item neighbor retention varies widely and is predictable from
geometric properties of the representation and its
alignment with the retained PCA subspace. The fraction of centered-vector energy retained by the truncated subspace is strongest for CBOW and RI, with neighborhood contrast leading on SkipGram and the modern/Matryoshka settings (GTE approximately tied), while local density is associated with retention in marginal analysis but adds little unique information once energy and contrast are controlled (R-squared increments 0.001 to 0.010). Local intrinsic dimensionality accounts for more variation than density on modern sentence encoders in pairwise comparison. On SciFact, query density predicts
retrieval degradation under aggressive compression; on NFCorpus the primary 32d association does not replicate, and a direct variance-restriction test leaves that null unresolved. Average compression performance conceals systematic per-example variation that geometry makes visible.
Read the full abstract ▾
Artificial Intelligence
Coupled Harness–Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su et al. (+8 more)
Large
language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's tool-use policy. The tools supply the solving capability, from diagnosing structure in the data to fitting candidate equations; the policy plans and orchestrates their use. Yet existing systems adapt only one part, keeping either the toolset or the model fixed, which leaves the corresponding failures uncorrectable. We develop a coupled
evolution framework that improves both parts from the same verifiable fit-error signal. In the tool-
evolution phase, an
agent grows an executable tool library from a small set of generic numerical operations by diagnosing its own failures: it authors a new tool when a capability is missing and revises its selection rules when the right tool went unused. In the policy-
evolution phase, a small open model (roughly 3B active parameters) is fine-tuned on successful tool-use trajectories collected with the frozen library, on training formulas screened to be disjoint from all evaluation
benchmarks. Ablations show the two phases are complementary: with no tool library at all the same model solves almost nothing, the tools account for most of the gain, and trajectory training adds a further gain that is largest on the most difficult problems. The full system solves 79.1/71.3% of LSR-Synth problems at fit tolerances $10^{-2}$/$10^{-3}$, reaches 63.8% pooled accuracy on the distributionally different SRSD-Feynman panel, and obtains a normalized CP3-28 aggregate of $-7.27$. These results suggest a broader recipe for scientific
agents: let the model and its instruments improve each other under verifiable feedback.
Read the full abstract ▾
All authors Pengze Li, Jiaquan Zhang, Encheng Su, Yunbo Long, Zihang Zeng, Xinping Liu, Han Zhang, Junchi Yu, Shixiang Tang, Aoran Wang, Xi Chen
Machine Learning
HiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data
Chuanqi Lao, Junzhou Huang and Qiao Liu
Estimating potential outcomes under alternative treatment sequences is essential for personalized decision-making, but remains challenging with high-dimensional
covariates and time-varying confounding. In this study, we propose HiSTOR (High-dimensional Structured Treatment-Outcome Representation), an end-to-end framework that integrates nonlinear dimension reduction with longitudinal counterfactual prediction. The central idea is to learn structured low-dimensional representations of both current patient states and evolving histories, according to their shared and distinct relationships with treatment assignment and outcomes. This extends latent-space
covariate adjustment to longitudinal settings, jointly addressing
covariate dimensionality and historical complexity. The resulting framework supports one-step and multi-step outcome prediction under specified treatment sequences. Experiments on CVSim and CancerSim demonstrate the superiority of HiSTOR across varying
covariate dimensions, confounding strengths, and prediction horizons compared to state-of-the-art methods. To sum up, HiSTOR offers a unified approach to connecting high-dimensional
covariate adjustment with longitudinal potential-outcome prediction.
Read the full abstract ▾
Artificial Intelligence
DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?
Jiaheng Dong, Shihong Tan, Gongping Huang et al. (+3 more)
End-to-end (E2E) full-duplex spoken
language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriate interaction actions as conversations unfold. However, existing
benchmarks lack a structured action-level formulation, often evaluate action occurrence rather than success, and provide limited coverage of diverse real-world conversations. We introduce DuplexAct, a
benchmark for evaluating interaction action taking in E2E FD-SLMs. DuplexAct defines a three-level action taxonomy spanning eight interaction actions and 24 corresponding interaction conditions. We further characterize successful action-taking through immediate execution and subsequent follow-through, and develop action-specific evaluation metrics for both. DuplexAct contains 4,691 test instances spanning casual conversation, meetings, customer service, and interviews, including 2,531 instances derived from real-world conversational recordings. Together, DuplexAct provides a structured and real-world-grounded framework for systematically assessing how E2E FD-SLMs participate in ongoing spoken interaction.
Read the full abstract ▾
All authors Jiaheng Dong, Shihong Tan, Gongping Huang, Jean Honorio, Abhirup Ghosh, Ting Dang
Information Theory
Distribution-Dependent Improvements of McDiarmid's Inequality via Rényi Divergence
Amedeo Roberto Esposito, Adrien Vandenbroucque and Michael Gastpar
We investigate whether Rényi divergence can sharpen McDiarmid's inequality and its distribution-dependent refinement induced by KL divergence. Starting from Marton's transportation proof, we show that its transport inequality fails in general when KL divergence is replaced by Rényi divergence of order $0<\alpha<1$. For sums of independent bounded random variables, however, the additivity of Rényi divergence allows us to adapt the argument and derive concentration bounds. For Bernoulli sums, these bounds strictly improve on the distribution-dependent bound induced by KL divergence over a range of deviation thresholds. We also establish a distribution-dependent refinement of Gilardoni's inequality relating total variation to Rényi divergence, providing explicit constants for our general concentration bounds.
Read the full abstract ▾
Machine Learning
Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning
Sungjun Lim, Adrian Robert Minut, Nico Carlsen Daheim et al. (+3 more)
Multi-sample
reasoning measures candidate coverage, the probability that at least one of $K$ candidates is correct. However, minimizing the average loss of individual attempts does not directly optimize candidate coverage. We therefore formulate finite-$K$ posterior learning, which trains a distribution over solver parameters to reduce the probability that all $K$ independently generated candidates fail. To optimize this objective efficiently, we propose a Fenchel-Bregman (FB) approach that requires only one posterior draw per update, rather than the $K$ used by direct Monte Carlo optimization. FB first uses an exact Fenchel reformulation to separate problem-specific weights from the posterior update, enabling one-draw posterior updates. It then applies a closed-form Bregman update to track these weights through an exponential running average of observed failures, reusing the same draw. We instantiate FB with IVON, a variational optimizer for Gaussian posteriors over solver parameters, yielding Fenchel-Bregman IVON (FBI). Across diverse recursive and autoregressive
reasoning tasks, FBI improves candidate coverage. In a matched comparison, it achieves comparable Pass@10 using 12.3% of the direct Monte Carlo baseline's measured training time per update.
Read the full abstract ▾
All authors Sungjun Lim, Adrian Robert Minut, Nico Carlsen Daheim, Mohammad Emtiyaz Khan, Kyungwoo Song, Thomas Möllenhoff
Machine Learning
Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning
Yutong Chen, Zhichao Xu, Rui Liu et al. (+1 more)
Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent sampling, without fully using the information gathered along the way, such as known wrong answers and environment feedback. We propose LEAF, which injects a dynamic, problem-specific
memory into the context before every rollout. The
memory contains the most recent response, its reward, and other environment feedback. It is updated after every verifier call. We decouple policy updates from rollouts and update the policy through self-
distillation. On four
benchmarks and two open models, LEAF accelerates exploration by about 4x compared with a random sampling baseline. On unseen test sets, it improves accuracy over the strongest baseline by 1.59 and 1.83 percentage points on the two models, while using less compute than any RL baseline. These results highlight the potential of LEAF in improving both exploration and learning efficiency. Code is available at: https://github.com/on1262/LEAF
Read the full abstract ▾
All authors Yutong Chen, Zhichao Xu, Rui Liu, Kunpeng Liu
Machine Learning
CoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement Learning
Guangcheng Zhu, Yingfan Ma, Xing Zheng et al. (+7 more)
Rubric-based reinforcement learning (RL) evaluates responses against explicit criteria to construct rewards, offering a viable way to train large
language models on open-ended tasks. However, standard methods compress criterion-level feedback into scalar rewards and assign uniform
token advantages, leaving structured rubric supervision underutilized. Recent work seeks finer-grained guidance by treating rubrics as privileged information to derive self-
distillation targets, but the resulting learning signal is not grounded in criterion outcomes and can lead to reward degradation. This motivates us to reframe the problem as criterion-aware credit assignment, where privileged rubric information serves as a relevance cue for credit allocation rather than a source of imitation targets. Accordingly, we propose CoCA, which derives criterion-level credits from group-relative outcomes and allocates them across
tokens based on criterion-induced distribution shifts, yielding both outcome-grounded and fine-grained learning signals. Empirically, CoCA achieves an average gain of +4.2% over standard rubric-based RL across medicine and science
benchmarks, demonstrating more effective learning on open-ended tasks.
Read the full abstract ▾
All authors Guangcheng Zhu, Yingfan Ma, Xing Zheng, Haobo Wang, Shenzhi Yang, Kai Tang, Zhengqing Zang, Bowen Song, Weiqiang Wang, Gang Chen
Computation and Language
Understanding Machine Taste: Aesthetic Agreement Across Foundation Models in K-pop
Kaishen Wang, Yucheng Pan, Xuehao Cui et al. (+2 more)
As foundation models enter creative industries, understanding their aesthetic preferences becomes an important step toward AI-assisted creative decision making. In this work, we investigate how foundation models evaluate creative content and characterize their “machine taste” using K-pop songs and music
videos as a testbed. We formulate aesthetic evaluation as a pairwise ranking problem and systematically examine pairwise inter-model agreement, group-level consensus, and cross-modal preference
alignment. Our results reveal stronger pairwise inter-model agreement and group-level consensus in visual evaluation than in audio evaluation, while preferences across the two modalities remain weakly aligned. We further examine how visual consensus rankings relate to real-world popularity using historical YouTube viewership data, finding positive but varying correlations across artist groups. These findings provide initial insights into machine aesthetic preferences and lay the groundwork for future AI-assisted creative decision making that considers creative content, artist identity, audience preferences, and
market dynamics.
Read the full abstract ▾
All authors Kaishen Wang, Yucheng Pan, Xuehao Cui, Hanling Tian, Heng Huang
Computer Vision
DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation
Yangming Zhang, Ling Yi, Datong Li et al. (+4 more)
Low-rank adaptation (LoRA) often underperforms full fine-tuning. We investigate this performance gap through a tangent-space lens: factorized updates are confined to the tangent space of the current low-rank factors, leaving gradient components outside this space unexploited. An analysis of ten representative LoRA variants reveals that these residual components account for most of the gradient energy and exhibit strong spectral concentration. Motivated by this finding, we propose Dynamic Tangent LoRA (DT-LoRA), which partitions a fixed rank budget into a stable branch and a dynamic branch to capture the principal residual gradient directions. We show that these directions define the optimal update of a local quadratic model under orthogonal-complement and rank constraints.
Matrix-free randomized SVD recovers them without materializing the residual gradient, while controlled write-back preserves accumulated updates and stabilizes training within the allocated rank. DT-LoRA adds no trainable parameters or inference cost over LoRA. Experiments across computer
vision and natural
language processing tasks demonstrate consistent improvements over LoRA and its variants. Moreover, despite being a general-purpose adaptation method, DT-LoRA outperforms task-specific approaches to open-vocabulary domain generalization for semantic segmentation, achieving state-of-the-art results. Code is available at https://github.com/Snipine/DT-LoRA.
Read the full abstract ▾
All authors Yangming Zhang, Ling Yi, Datong Li, Jinliang Ding, Xiaojie Wang, Tiecheng Song, Zhaolong Ning
Artificial Intelligence
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Yewon Han, Jisu Jeon, Suhyun Choi et al. (+5 more)
Egocentric
multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystanders. Yet existing safety evaluations do not distinguish whom a response would harm, and score only whether a model refuses. Pooling all harms into one refusal rate hides two failures: a model may protect one target but not another, and it may refuse without understanding the risk, or understand it and comply anyway. We present STOU, a
benchmark of 2,902 egocentric
video-audio and
video-text queries whose potential harm targets the user (Self), co-present individuals (The Others), or society at large (Others). Our evaluation decouples safety understanding from refusal behavior: beyond refusal, we score whether the model recognizes the user's intent, the presence and target of harm, and its downstream consequences. Across 10 open and closed source omnimodal and
multimodal LLMs, we find that refusal varies systematically with the harm target, and that models often recognize a harm yet still assist with it. These results show that refusal rates alone cannot certify an assistant as safe, and that safety
alignment must account for who would be harmed. Project page: https://onedayoneyeah.github.io/safety-for-whom
Read the full abstract ▾
All authors Yewon Han, Jisu Jeon, Suhyun Choi, Juan Yeo, Minsoo Jo, Gihoon Kim, Hyunggyu Lim, Taesup Kim
Cryptography and Security
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Jerrold Huang, Junwei Quan, Saiyue Lyu et al. (+2 more)
Agent skills turn natural-
language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the review load manageable. We present SkillScreen, a compact decision model trained to score skill maliciousness directly from SKILL$.$md in a single forward pass. On MaliciousSkillBench, SkillScreen flags 20-25% of benign skills at 99% recall on unseen attack families, substantially fewer than the word-level classifier and prompted LLM judges tested. Under the same training protocol, it also generalizes better than a fully fine-tuned encoder to unseen sources. Yet unfamiliar benign sources sharply increase false positives, showing that recognizing new attacks does not ensure reliable screening of new skill collections. Our results demonstrate the value of task-trained decision models for high-recall skill screening. Project page: https://jerroldh.github.io/SkillScreen-webpage/
Read the full abstract ▾
All authors Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge
Machine Learning
TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
Yuqian Fu, Kaiwen Jiang, Zijun Song et al. (+3 more)
Large
language model (LLM)
agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning–acquiring new skills often degrades previously mastered capabilities. Existing post-training paradigms face a fundamental trade-off: Supervised Fine-Tuning (SFT) is sample-efficient but prone to severe forgetting, while Reinforcement Learning (RL) preserves prior capabilities but converges slowly without expert guidance. To bridge this gap, we introduce Trigger-based Supervised Reinforcement Learning (TSRL), a framework that integrates the strengths of both paradigms through an adaptive, state-dependent expert supervision mechanism. TSRL employs RL as the optimization backbone, activating SFT selectively on "hard states" where the policy fails. Theoretically, we show that restricting supervision to failure states derives an upper bound on the cumulative parameter updates, thereby reducing forgetting compared to full SFT. Empirically, TSRL achieves consistent gains across three
agent benchmarks (ALFWorld, WebShop, and Deep Search) at both 7B and 32B scales. In continual learning scenarios, our method retains up to 9.6 points more capability on prior tasks than SFT->RL baselines, while matching or exceeding target-task performance.
Read the full abstract ▾
All authors Yuqian Fu, Kaiwen Jiang, Zijun Song, Jiawei Wang, Yuanheng Zhu, Dongbin Zhao
Cryptography and Security
Beyond Model Scaling: Rethinking Sequence Construction for Transformer-based Network Intrusion Detection
Zeeshan Zulkifl Shah, Muhammad Ikram, Dali Kaafar et al. (+1 more)
Transformer-based network intrusion detection systems (NIDS) have shown strong potential for detecting multi-stage cyberattacks, yet most methods construct input sequences using fixed temporalization schemes rather than treating sequence construction as a systems design decision. In flow-based intrusion detection, timestamp-based windowing often fragments related attack activities while merging unrelated communications, reducing the behavioral context available to
transformers. We present a unified pipeline abstraction that decomposes
transformer-based NIDS into four design dimensions (traffic representation, temporalization,
transformer backbone, and prediction aggregation) and propose session-coherent temporalization, which constructs sequences from communication sessions instead of fixed time windows. Experiments on three complementary intrusion detection
datasets show that temporalization is the dominant factor governing
transformer performance: session-coherent temporalization more than doubles Macro-F1 over timestamp-based windowing, enabling lightweight
transformers to achieve up to 0.95 Macro-F1 at substantially higher inference throughput than pretrained models. We further vary the
transformer size from 0.65M to 3.38M parameters and find that larger
transformer models provide no measurable accuracy improvement despite substantially higher computational cost, while zero-shot cross-
dataset evaluation shows only modest gains under domain shift. These results indicate that preserving communication-session semantics, rather than scaling
transformer capacity, is the key to accurate and efficient
transformer-based intrusion detection.
Read the full abstract ▾
All authors Zeeshan Zulkifl Shah, Muhammad Ikram, Dali Kaafar, Yipeng Zhou