Research

• Interface lock-in in multimodal spatial reasoning1 paper raises it · 1 addresses it

  Specializing a model on one spatial task (e.g., side detection) degrades performance on others (e.g., distance estimation), limiting general spatial intelligence.

  • ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligenceraises · addresses
• Lack of unified evaluation for work agents1 paper raises it · 1 addresses it

  Existing benchmarks fail to measure reliable work execution across tools, workflows, and open environments, hindering progress in agent systems.

  • Work Agents: Systems, Capabilities, and Optimizationraises · addresses
• Memory tax in long-horizon agents1 paper raises it · 1 addresses it

  Dedicated memory systems often underperform naive retrieval, as reorganizing information can obscure evidence and reduce net value.

  • Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
• Credit assignment in diffusion language models1 paper raises it · 2 address it

  Iterative denoising in DLMs makes it hard to attribute rewards to individual tokens, limiting reinforcement learning effectiveness.

  • DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Modelsraises · addresses
  • Multiscale Policy Optimization for Long-Horizon LLM Agentsaddresses
• Grounded significance testing for temporal hypotheses1 paper raises it · 1 addresses it

  Language models assert temporal patterns without rigorous statistical validation, risking incorrect conclusions in high-stakes domains like healthcare.

  • Testimony from Timelines: Evidence-Grounded Significance Testing of Temporal Clinical Hypothesesraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.LGOct 7▲ 14

  Coding-Agent Benchmarks Should Match Their Users' Task Flows

  Igor Slinko, Yaroslav Golubev, Sergey Titov

  The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which we call Production Sessions. Since our subject is interactive agents, we study the sessions with at least three user messages (33% of the sample). These long sessions differ from issue-derived benchmark tasks in two ways: (i) user requests span a far wider mix of task types - questions about the project's code, planning, review, refactoring, execution - and (ii) users switch between types throughout a session. Long-session samples from three public interaction corpora exhibit markedly different Task Flows (the distributions of session lengths, task types, and type-to-type transitions), so no single interaction distribution is universally realistic: benchmarks should name a target use case and calibrate to measurements from it. We present SWE-TaskFlow, an approach for transforming any issue-derived benchmark: it preserves the verified tasks and tests while steering the interaction toward a target Task Flow through prompt splitting and verifiable repository QA, with a TaskFlow Alignment Score (TFAS) for…

  CodePDF

  Summarize this
• arXiv cs.AIOct 7

  How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression

  Xijie Gong, Tingxu Han, Jiahao Zhang, Wei Song, Ziqi Ding +3

  Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds directly remains poorly understood. Agentic prompts are long and heavily scaffolded, combining role instructions, tool schemas, format templates, and the user's request across hundreds of tokens, creating a noisy, highly entangled context in which no single controllable variable for mechanistic analysis is obvious. To obtain such a variable, we propose a method that converts complex agentic prompts into minimal contrastive pairs in which a single request verb determines the tool-call decision: replacing an execution-verb (e.g., \textit{write}) with an analysis-verb (e.g., \textit{discuss}) reliably flips the decision, suggesting it is mediated by a compact internal state. We construct 500 such paired prompts across Python, Java, and C++ (300 for mechanistic analysis, 200 held out for evaluation). We trace the decision to a vector, $μ_Δ$, that is both causally necessary and sufficient and generalizes beyond the discovery prompts to native multi-turn $τ^2$-Bench trajectories and verb-free requests. Behavioral ablations show that the…

  PDF

  Summarize this
• arXiv cs.LGOct 7

  When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen

  Martin Hofmann, Patrick Mäder

  Networks that behave alike now can still learn differently when training continues. Work on loss of plasticity and critical periods shows that the path to a state shapes what follows; it does not show whether the path carries information that a measurement of the state itself misses. We ask when the training history of a network predicts its future learning better than its current state. In a main study, small multilayer perceptrons were trained under three history regimes (42 histories), and future learning was measured at four checkpoints by a short probe: a copy of the network trained for 100 updates on a new task. Before the prediction result was read, the protocol checked the probe. It responded monotonically to a function-preserving rescaling of hidden units, repeated measurements agreed (intraclass correlation 0.940, [0.903, 0.997], in the least reliable class, mean of three repeats), and a re-initialisation of units was visible directly after it but not 100 to 200 updates later. A history state of at most four dimensions did not improve on a calibrated model of the current state (gain -21.4%, 90% interval [-91.9, 8.1]; required in advance: 10%). A companion screen on…

  PDF

  Summarize this
• arXiv cs.LGOct 7

  The Identifiability and Observability of Deep Normalized Attention

  Pranav Venkata Konda

  We study which parameters of deep, unmasked, single-head attention are determined by its input--output function. For known positive nonconstant real-analytic normalizers, the function generically determines the effective scores and combined value map up to the signs induced by even normalizers. This proves the real-analytic case of a conjecture of Henry--Marchetti--Kohn, including softmax. We then classify exceptional fibers under explicit normalizer conditions, identifying when collapse makes later scores unobservable, and establish sharp Taylor orders for local identification. Near simultaneous query/key collapse, we compute the complete native Jacobian decay spectrum on separating finite input banks. For common first nonconstant normalizer degree $k$, layer $i$ has contact order $2k3^{i-1}-1$, with exact multiplicities and kernel dimension. High-precision and automatic differentiation calculations illustrate the resulting loss of numerical sensitivity.

  PDF

  Summarize this
• arXiv cs.SEOct 7

  TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution

  Shuangjie Yao, Hao Wang, Koushik Sen, Simin Chen, Baishakhi Ray +1

  Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all existing benchmarks still rely on the same decades-old criterion: a solution is correct if it passes a fixed set of unit tests. Such tests are often insufficient: they check only part of what the task requires, so agents can reward hack them or silently miss required behavior while still passing every test. As a result, higher benchmark scores may partly reflect better adaptation to the evaluator rather than better problem solving. Existing works focus on static test augmentation: they strengthen each task's tests once, before any trial is seen, and thus overlook how real trials actually fail. We introduce TestJack, a scalable framework for evaluating patches beyond fixed tests. For each trial, TestJack generates tests targeting prompt requirements the patch may violate, retains only tests passed by the ground-truth patch, and re-examines any trial failures. Each confirmed failure is thus supported by a replayable test. To reduce evaluation cost, we also introduce a lightweight variant which audits a random sample of trials in depth and…

  PDF

  Summarize this
• arXiv eess.SPOct 7

  Second-order optimization of variable projection SVM models and road abnormality detection

  Andrea Angino, Matthias Voigt, Rolf Krause, Tamás Dózsa

  We introduce a novel second-order optimization framework for minimizing so-called variable projection functionals. We demonstrate that the proposed framework is especially usefulfor the training of variable projection based kernel methods. In particular, the problem of efficiently training variable projection support vector machines (VP-SVMs) is considered. We show the effectiveness of the proposed training methodology in a real-world application, namely we demonstrate how second-order trust region algorithms can be used to train VPSVM models to recognize road surface abnormalities based on 1D signals obtained from a tire sensor.

  PDF

  Summarize this
• arXiv cs.CVOct 7

  Identity-Duplication Auditing in National-Scale Neuroimaging Repositories

  Jiheng Li, Michael E. Kim, Trent M. Schwartz, Yuhan Cui, Gaurav Rudravaram +17

  National-scale magnetic resonance imaging (MRI) repositories increasingly integrate data from different studies and institutions. However, subject identifiers assigned to study participants are typically specific to individual datasets, so the same person may appear under different identifiers when these datasets are aggregated, a problem we define as identity duplication. Such duplication can create leakage between training and test data and inflate apparent performance in downstream biomedical studies. Existing methods do not provide an end-to-end, image-based workflow to address this problem. In this work, we present HAPPEN, a human-in-the-loop pipeline for auditing identity duplication in T1-weighted brain MRI repositories. It combines SHA-256 fingerprinting for exact-duplicate detection with embeddings learned through supervised contrastive learning to retrieve near-duplicate candidates: pairs of non-identical scans that may originate from the same person. Retrieved pairs are reviewed as candidates in a locally hosted interface rather than automatically classified as duplicates. We deployed the workflow in a national-scale aggregated repository containing 95,129 scans and…

  PDF

  Summarize this
• arXiv q-fin.STOct 7

  Residual Learning in Empirical Asset Pricing

  Dexin Peng, Xiaoyu Wang

  Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existing empirical asset pricing literature provides strong benchmarks for shallow models. Residual learning allows neural network models in asset pricing to go deeper by preserving and refining their shallow counterparts. The out-of-sample Sharpe ratio for value-weighted long-short portfolios of deep residual models (2.07) is higher than that for the corresponding shallow ones (1.92) and more than twice that of the deep feedforward models (0.89). We show that model depth is a source of additional economic value in asset pricing. Residual learning can be used to deepen other neural-network-based asset pricing models if they contain intermediate layers. Our design also provides one way to scale asset pricing models, making native "large asset pricing models" more feasible.

  PDF

  Summarize this
• arXiv cs.LGOct 7

  Sequential Pretraining Favors Large Models

  Mohnish Harwani, Yujia Zheng

  Large neural networks often acquire capabilities that small models fail to learn. Does this stem from large models learning more representative features, or from being more robust to unaccounted-for adverse effects introduced during training? We define and quantify one such adverse effect, primacy bias, as the extent to which exposure to early data distributions impairs later learning. We show that small models can allocate learning capacity inefficiently toward early distributions, whereas sufficiently overparameterized models are robust to this effect. This inefficiency is particularly consequential in pretraining, where foundation models often encounter heterogeneous data distributions sequentially rather than jointly. As a result, small foundation models can struggle to learn distributions encountered late in training, which is particularly harmful when later data emphasizes desirable capabilities such as code, mathematics, and reasoning. Motivated by these findings, we introduce Exposure Therapy (ET), a simple regularization that promotes more efficient allocation of learning capacity during sequential pretraining. We demonstrate that ET improves foundation models'…

  PDF

  Summarize this
• arXiv cs.LGOct 7

  Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student

  Haorong Han, Jidong Yuan, Chixuan Wei, Yongqi Sun

  Semi-supervised learning (SSL) relies on two core mechanisms: self-training under the Teacher-Student (T-S) framework and joint optimization of labeled and unlabeled losses. Despite their effectiveness, we find both mechanisms introduce distinct optimization pathologies. First, parameter coupling enforces strict synchronization between teacher and student, where strong regularization on the student degrades the teacher's fitting ability, thereby limiting the permissible generalization intensity. Second, the imbalance in gradient update consistency between labeled and unlabeled losses drives the shared parameters to prematurely converge to labeled-dominated local minima, creating a bottleneck for global optimization. To address both issues, we propose the Pioneer Student (PiS), an auxiliary branch that operates in an independent parameter space and periodically transfers accumulated knowledge back to the T-S model. Extensive experiments show that PiS is a universal plug-and-play module that consistently improves mainstream SSL methods.

  PDF

  Summarize this
• arXiv cs.CLOct 7▲ 3

  Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning

  HyeonSeok Lim, SeungWoo Song, Inho Won, Hoyun Song, Jihyo Kim +1

  Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We propose the Language-Aware Skeleton Exploration Framework (LASEF) to study skeleton-language choice in multilingual mathematical reasoning. Across math benchmarks, model scales, and languages, we show that English skeletons yield a small positive tendency on average, most visible for smaller models and low-resource languages. However, few language-level gains remain significant after correction, and English is not universally optimal. Combining greedy decoding, multi-rollout evaluation, translation ablation, and cross-benchmark validation, we further find three patterns of skeleton-language effects: directionally consistent, evaluation- and benchmark-dependent, and asymmetric negative. These effects cannot be fully explained by generation quality alone. Overall, skeleton language is a context-dependent design variable that requires multi-level exploration. All resources are released at https://github.com/lhsstn/LASEF.

  PDF

  Summarize this
• arXiv cs.LGOct 7

  Lightweight and Versatile Learned Optimization by Recombination of Gradient History

  Minyoung Choi, Dalta Imam Maulana, Wanyeong Jung

  This paper presents a lightweight and versatile learned optimizer that dynamically recombines gradient history, represented as averages over disjoint time spans. The optimizer reduces the prediction space to one scalar coefficient per gradient average, shared by multiple parameters. Progressively averaging older gradients minimizes memory cost of long history, while keeping their contributions independently accessible. A 37k-parameter network trained in 0.87 GPU-hours generalizes zero-shot to unseen tasks, lowering validation loss by 9.1% and 0.4% on BERT-Tiny and GPT-Tiny, and improving test accuracy over Adam by 3.5 %p on a Vision Transformer and by 2.7 %p on average across nine graph models, with FLOPs overhead as low as 0.3%.

  PDF

  Summarize this
• arXiv cs.AIOct 7

  SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models

  Miao Yu, Hao Huang, Lu Yuan, Yunpeng Li, Kun Wang +1

  Safety interpretability advances the study of Large Language Model (LLM) alignment from behavioral constraints driven by data or algorithms towards a deeper understanding of internal mechanisms. However, existing works have focused primarily on safety-related representations, attention heads, or neurons after alignment, while largely overlooking the safety mechanisms in pretrained-only models and their evolution across alignment checkpoints. To address this, we propose SafeEvo, an interpretability framework from the circuit (sparse subgraphs of an LLM) perspective. SafeEvo first applies an optimization-based extraction algorithm to identify weak refusal circuits in pretrained base LLMs that can independently express refusal behavior. Causally ablating these circuits completely eliminates the base model's refusal of harmful inputs. SafeEvo then traces the evolution of refusal circuits across successive alignment checkpoints and finds that their structures change progressively, suggesting that the alignment tax may result from refusal-circuit updates affecting utility-related parameters. To validate this, SafeEvo introduces Safety Circuit Alignment (SCA), which confines safety…

  PDF

  Summarize this
• arXiv cs.CVOct 7

  STORK: Spatio-Temporal Observation of uterine contRactions via neural networKs

  Melissa Schween, Tristan Gottwald, Jordina Aviles Verdera, Lisa Story, Mary Rutherford +1

  Uterine contractions in fetal MRI are typically identified manually and discarded, limiting insights into contraction dynamics. We formalize Uterine Contractile Activity Detection (UCAD) as a weakly-supervised learning problem and introduce STORK, a multi-instance learning model trained on dynamic MRI series using only coarse, series-level labels. STORK factorizes 3D spatio-temporal convolutions into parallel branches across temporal hyperplanes to capture coherent tissue motion without the cost of full 4D convolutions. Per-frame embeddings, combining intensity and Demons-estimated displacement fields, are aggregated by a linear mean-pooling head. This ensures that frame-level contraction scores can be recovered post-hoc without frame-level training supervision. Evaluated on around 700 multi-vendor dynamic fetal MRI series, STORK achieves a series-level AUROC of 95.0% and AUPRC of 94.6%, substantially outperforming 3D ResNet and ConvNeXt baselines. Grad-CAM analysis suggests that the model draws on predictive features extending beyond the placenta into the uterine tissue, offering an automated tool for richer phenotyping of uterine behavior.

  PDF

  Summarize this
• arXiv cs.LGOct 7

  COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning

  Zicheng Hu, Zhijian Zhou, Xuan Zhang, Yuchen Liu, Cheng Chen +5

  Asynchronous RL accelerates large language model post-training by decoupling rollout generation from optimization, but trains on stale trajectories. Existing methods primarily correct token-level policy mismatch through importance-ratio control in the actor objective. We show that this \emph{policy-side correction} alone is insufficient: advantage estimates also inherit mismatch from behavior-policy continuations, which we term \emph{advantage staleness}. We derive exact bias and variance decompositions for a general two-channel actor update, revealing nonseparable coupling between policy-weight and advantage-estimation errors: their interaction induces multiplicative bias terms, while squared policy weights amplify advantage uncertainty in gradient variance. This motivates the hypothesis that policy- and advantage-side correction should be coordinated. We introduce Coupled Off-Policy Correction (COPC), an actor--critic method combining token-level ratio masking with two-sided clipped-ratio weighting of TD residuals for return and advantage estimation. Joint parameter sweeps across staleness levels support this hypothesis: the effect of one correction parameter depends on, and…

  PDF

  Summarize this
• arXiv cs.HCOct 7

  Structured pre-generation elicitation versus single-shot prompting in AI-assisted enterprise decision-making: a randomised online experiment

  William Scott-Jackson

  Generative AI speeds, and mostly improves, professional work, but there is concern that users who delegate both the production and the evaluation of an answer may accept weak output and engage less with the underlying reasoning (cognitive surrender). Interventions proposed so far, such as unassisted practice or slowing adoption, sit outside the working task. We tested a different approach: an interactive metacognitive scaffolding layer (Cognistance, a prototype developed at the Oxford Centre for Impact Research (OCIR) that asks users to clarify context, choose a strategic direction and explain their reasoning before the AI generates a deliverable). Mean composite quality was 32% higher with the scaffold, with the same direction for every rater. Gains were largest for trade-off articulation and strategic coherence and absent for technical specificity. A large part of the aggregate effect reflected rescue of weak prompts: floor-scored (off-task) deliverables fell from 34% to 5%. Among participants whose own prompt already stated the data-localisation problem, the advantage was 21%. Treatment participants reported greater involvement and took about 2.4 minutes longer on average…

  PDF

  Summarize this
• arXiv stat.MLOct 7

  Scalable Logistic Gaussian Process Density Regression with Kinetic Langevin Sampling

  Daniel Paulin, Ádám Jung, András A. Benczúr

  Conditional density estimation targets the full distribution of a response given covariates, as required, for example, for per-galaxy photometric redshifts. We develop a scalable Bayesian estimator based on the logistic Gaussian process. The log conditional density has a separable covariance: a Matérn kernel along the response, represented in a truncated Fourier basis on a circle, and a covariate kernel represented by Nyström features, which accommodate non-stationary kernels with input-dependent amplitudes and length scales. Instead of a Laplace or variational approximation, we sample the latent field of this finite-feature model. Given the hyperparameters, its posterior is strongly log-concave with a uniformly bounded Hessian, and we draw from it by simulating kinetic Langevin dynamics with symmetric minibatch splitting in Kronecker-whitened coordinates. Marginal-likelihood gradients follow from Fisher's identity as posterior expectations. Under the conditions of our analysis their bias is controlled by the sampler's step size and run length, and the predictive averages over the non-Gaussian latent posterior instead of a Gaussian around its mode. On photometric-redshift…

  PDF

  Summarize this
• arXiv cs.AIOct 7

  Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents

  Hong Su

  Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefinitely. However, existing memory mechanisms mainly retrieve, summarize, or compress past content and do not directly learn when particular kinds of thinking should be activated or discover new thinking knowledge from temporally dispersed experiences. This paper proposes a situation-conditioned thinking memory framework that transforms historical reasoning experience into a lightweight policy for predicting what should be thought about in the current situation, while leaving detailed reasoning to a large language model. Situations may represent temporal or spatiotemporal evolution rather than only current states. Temporary experiences are also periodically analyzed across multiple independent episodes to identify repeated long-range regularities, which are consolidated into new thinking knowledge and further internalized by the lightweight policy. Experiments show that the learned policy achieves 1.000 F1 on temporal-rule generalization, improves DeepSeek reasoning F1 from 0.789 to 0.868, reduces online processing time from 0.3636 ms…

  PDF

  Summarize this
• arXiv cs.AIOct 7

  Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study

  Lin Wu, Zhe Xu, Hongyi Wang, Feifei Zhou, Wei Deng +8

  Purpose: To compare dual- and single-suggestion AI support for radiographic interpretation by residents, particularly when the shared AI suggestion was incorrect. Materials and Methods: This prospective, multicenter, randomized three-arm reader study was conducted at three hospitals in China from July to September 2026 (ChiCTR2600129243). After specialty stratification, 132 residents with fewer than 3 years of clinical experience were randomized 1:1:1 to GPT-5.4 alone (group A), GPT-5.4 plus Kimi-K2.6 (group B), or GPT-5.4 plus Gemini-3.6 Flash (group C); 123 were analyzed. Participants interpreted 60 radiographs before and after AI support. The primary outcome was accuracy change. Welch ANOVA and Holm-adjusted t tests compared support conditions; HC3 linear models assessed specialty interaction. Results: Among 123 residents (mean age, 24.1 years +/- 1.4; 65 women), radiology residents showed greater accuracy improvement with dual- than single-suggestion support (B-A, 6.69 percentage points [95% CI, 0.97-12.40]; C-A, 7.87 percentage points [95% CI, 1.64-14.11]; Holm-adjusted P = .030 for both), whereas accuracy change did not differ in non-radiology residents (P = .20). When…

  PDF

  Summarize this
• arXiv cs.ROOct 7

  Adaptive Code Generation for Controlling Robots

  Justus Flerlage, Thorsten Wittkopp, Alexander Acker, Odej Kao

  Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based autonomy, as natural language represents the only medium capable of articulating complex goals beyond the capacity of finite instruction sets. While Large Language Models (LLMs) offer a path toward natural language goal description, their integration introduces significant challenges: the formalization gap between imprecise intentions and executable actions, the taxonomy gap induced by unpredictable environments, and the challenge of maintaining temporal state and progress awareness. This work introduces an architectural framework that enables robotic control by leveraging generative AI. The system follows a dual-AI design: an LLM translates high-level intentions into executable program code restricted to a formal robotic library and constrained by verifiable syntax, while a Vision-Language Model (VLM) provides semantic grounding via a distillation process. To ensure robustness, the framework incorporates environment-driven replanning triggers based on geometric and semantic thresholds, complemented by continuous…

  PDF

  Summarize this

• Character recognition OCR12+20.0%
• AI tutors15+15.4%
• Channel state information13−7.1%
• Electrocardiogram ecg35−12.5%
• Supervised & diffusion models94−15.3%
• Machine learned interatomic36−23.4%
• Stochastic gradient descent25−26.5%
• CAD models11−26.7%