Papers

Generative semantic segmentation exposes structured predictions as images, but direct color decoding is susceptible to color drift and boundary mixing, whereas latent-feature decoders that predict a separate output distribution may relegate the rendered image to an intermediate visualization. We present Semantic Prism, a conditional semantic-image generation-and-refinement framework with deterministic inference. A diffusion-distilled one-step generator renders a semantic RGB image; per-pixel distances from the rendered colors to a fixed class-color codebook define an explicit probabilistic interface. Hierarchical Generator Evidence Alignment spatially aligns multi-level generator features and uses a zero-initialized output projection to predict an additive residual in the interface logit space, retaining the image-defined interface as the reference for the final distribution. The interface and refined distributions further enable Contextual Interface–Hierarchy Disagreement (C-IHD), a fixed readout for ranking remaining pixel errors without an auxiliary predictor or additional forward pass. On the 500-image Cityscapes validation set, Semantic Prism achieves 72.07% mean intersection over union, 11.39 mIoU points above direct-interface decoding, with 0.41% expected calibration error. Matched-capacity ablations over three seeds support the benefit of jointly aligned multi-level evidence. A separately trained model attains 62.22% mIoU on BDD100K, while the Cityscapes-trained model reaches 46.89% mIoU under source-frozen transfer to the Adverse Conditions Dataset with Correspondences, without target-domain adaptation. Across all three datasets, C-IHD consistently improves the area under the precision–recall curve for pixel-error ranking over maximum softmax probability on the same segmentation predictions; on ACDC, it raises AUPR from 0.6580 to 0.7557.

In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy. However, Federated learning struggles to adequately train a global model when confronted with data heterogeneity and data sparsity among vehicles, which ensure suboptimal accuracy in making precise predictions for different vehicle types. To address these challenges, this paper combines Federated Transfer Learning (FTL) to conduct vehicle clustering related to types of vehicles and proposes a novel Hierarchical Federated Transfer Learning (HFTL). We construct a framework for DT-VANET, along with two algorithms designed for cloud server model updates and intra-cluster federated transfer learning, to improve the accuracy of the global model. In addition, we developed a data quality score-based mechanism to prevent the global model from being affected by malicious vehicles. Lastly, detailed experiments on real-world datasets are conducted, considering different performance metrics that verify the effectiveness and efficiency of our algorithm.

World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency. We ask whether action generation requires the evolving rollout trajectory or only its future representation. Across four WAMs on 40 simulated robotic manipulation tasks, paired closed-loop interventions show that blocking access to the future cache or reassigning its values changes execution and reduces success. Yet in the evaluated co-denoising settings, reusing one fixed final-clean key/value (K/V) cache throughout action denoising nearly preserves unmodified execution, with $1.7$–$1.9$ cm end-effector average displacement error. Obtaining this cache still requires iterative video generation. We therefore propose RIFT (Rollout-free Imagination via Future Tokens), which uses learned anticipation tokens to construct a complete future K/V cache in one backbone pass. On LIBERO, RIFT achieves $98.8\%$ overall success, outperforming all evaluated rollout-based methods while yielding a $3.1$–$9.2\times$ inference speedup. Without further training, it achieves $81.1\%$ overall success on the out-of-distribution LIBERO-Plus benchmark, a $+9.7$ percentage-point improvement over the strongest evaluated baseline. On RoboTwin, it achieves $92.9\%$ and $92.6\%$ success on clean and randomized scenes, respectively, the highest among the evaluated methods. On real-world manipulation tasks, RIFT achieves $45.3\%$ average success, a $+6.0$ percentage-point improvement over Fast-WAM-Joint. These results support rollout-free future conditioning without iterative video generation at deployment.

We study the multiplayer multi-armed bandit problem with information asymmetry under Bernoulli rewards, for three information structures: asymmetry in actions, in rewards, and in both. Replacing the Hoeffding-style confidence intervals of prior work with Kullback–Leibler (KL) divergence-based bounds gives strictly tighter regret guarantees in each case. We propose mKL-UCB, mKL-UCB-Intervals and mKL-DSEE, and show that the improvement factor is at least two by Pinsker's inequality and far larger when reward means are near zero or one. For asymmetry in rewards we prove that two arms' KL intervals separate after a deterministic number of samples, and that $M$ independent players accelerate elimination further.

Collections of diverse observations often share one acquisition, processing, geometric, or channel corruption, while only an unpaired clean reference set is available. For a prescribed low-dimensional correction shared across observations, the observed and clean reference sets support inference only through the response of fixed moments. We formulate this problem as two-sample moment calibration and report a rank-aware information state combining local rank, scaled moment sensitivity, source-separated covariance, and a moment compatibility residual. Full rank gives local moment identifiability, whereas kernel directions remain unresolved to first order. A unified linearization separates observed-set and reference-set uncertainty. Under covariance weighting, the weakest scaled singular value determines worst-direction asymptotic amplification. For an orientation-preserving planar-similarity correction shared across observations, ensemble centroids and a nonzero third-order complex moment yield closed-form global population identification of translation, rotation, and isotropic scale under matched-population and no-clipping assumptions. Controlled validation tests the predicted $N^{-1}$ and $\sigma_{\min}^{-2}$ laws, Gaussian efficiency, and interval coverage. Bounded applications report color corrected-output quality, channel magnitude-response calibration, and a separate paired geometric de-beautification result. The framework therefore reports missing or weak information instead of treating every fitted correction as identified.

Systems with costly gold outcomes and cheaper auxiliary observations must decide how much record linkage to retain. Complete pairing retains every joint counter, while separate margins retain none. Neither endpoint is calibrated to a declared finite-sample decision. Universal reconstruction can retain cycle directions invisible to the likelihood-ratio family. Family-exact storage can exceed what the decision requires because certified residual loss may fit within finite-sample slack. We introduce RCShift, which certifies two routes to sufficiency under a declared observation contract. Its exact mode characterizes minimum-cost family-exact storage through LR-visible cycle directions. Its approximate mode bounds reverse Le Cam deficiency. Its integer mode certifies whether a chosen set preserves the full experiment's minimum integer record count at specified size and power. In a rank-two witness, one aligned counter preserves a four-record minimum. An equal-cost misaligned counter and the margins require eleven records, while universal reconstruction requires two counters. A local perturbation has positive reverse deficiency yet retains the four-record minimum. Proof-checked scheduling bounds instantiate the contract before gold computation and yield exact reconstruction on the admitted tree support. RCShift turns partial-linkage storage into decision-calibrated measurement design for the declared family, costs, target, and common strictly positive support.

The increasing prominence of short-video platforms, coupled with the advanced commercialization of AI-generated content (AIGC) videos, has led to a shift in the types of video media trend consumed by users in their daily lives. Traditional user-generated content (UGC) is gradually being replaced by professional short dramas and AIGC entertainment. Consequently, VQA for contemporary media content has become increasingly important. This requires a unified evaluation framework that can handle diverse video content and evolving media trends. In this context, we introduce TREND-10K, a next-generation comprehensive VQA dataset consisting of the trend-driven part and the static part, containing $10,000$ videos across a wide spectrum of content types. The trend-driven part is based on the TREND-Search framework, which captures user preference profiles from trending lists on online platforms and formulates sampling strategies based on these profiles. The static part, on the other hand, is composed of supplementary samples selected from publicly available datasets. To support unified evaluation for various video types, we incorporate three evaluation dimensions: technical, aesthetic, and AIGC-trace. Experiments show that our dataset ensures high annotation quality and exhibits remarkable generalization across multiple content categories. In conclusion, our work presents a robust framework for advancing VQA, addressing challenges caused by the temporal evolution of user perceptual habits and preferences.

Structured pruning of attention heads provides a hardware-friendly way to compress Transformer language models. However, existing methods for measuring head-level importance require calibration data, gradient computation, or Hessian estimation. These requirements add extra overhead and make the methods depend on the data. Our work presents Magnitude Profile (MP) scoring, a training-free criterion for head importance that identifies dispensable heads through statistical outlier detection on weight row norms. Heads whose projection weights fall within the population bulk are pruned, while heads exhibiting outlier norms, which carry disproportionate representational capacity, are preserved. Our work further gives MP-G, a variant that handles Grouped Query Attention (GQA) by distributing shared key-value group scores across associated query heads. Across five models evaluated on WikiText-2 perplexity at 12.5%-50% head sparsity, MP-G achieves the best perplexity on OPT-6.7B at all sparsity levels (18.46 at 12.5%, 27.87 at 25%, 152.0 at 50%). MP-G also gives the best results on RoBERTa-large at 12.5% and 25% sparsity, with perplexity values of 7.27 and 10.28, outperforming calibration-dependent baselines including Wanda-Head, SparseGPT-Head, and Gradient-Head. It requires zero forward passes, calibration samples, or gradient computation. At 50% sparsity, head pruning yields up to 16% parameter reduction with 50% attention FLOP savings. Our results show that weight-only statistical scoring can match or outperform data-dependent methods for structured head pruning, providing a practical, zero-cost criterion for Transformer compression.

Ubiquitous robotic systems often lack traditional visual interfaces, necessitating resilient natural language interaction for maintenance and repair tasks. This paper presents a goal oriented agentic AI architecture designed to enable non-expert users to perform technical repairs through situated dialogue. The framework utilizes a multi-layered approach that decouples high-level strategic planning from reactive conversational execution to transform unconstrained human instructions into a structured hierarchy of goals. We conducted a study involving twenty participants to evaluate the system's efficacy using a physical hardware testbed. The architecture achieved a 95% task completion rate, and participants reported positive self-efficacy following real-time guidance that adapted to conversational diversions and linguistic variations. A comparative analysis with an online baseline revealed that the transition to a physical environment significantly decreased perceived social presence (p=.0005), and trust and competence, (p=.037), while the agentic framework remained robust throughout the interaction. These findings indicate that goal oriented agentic AI can support the sustainability of body-worn technologies by empowering users to perform critical maintenance in ubiquitous contexts.

Persona-driven techniques increasingly adapt large language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid, synthetic personas that flatten individual variation, rely on stereotypes, and miss the nuanced signals driving actual human preferences. We introduce profile behavioral grounding, a framework for extracting open-ended, high-fidelity user profiles directly from authentic, anonymized social media posts. We evaluate these profiles across two paradigms: train-time personalization via supervised finetuning (SFT) and non-parametric test-time multi-perspective reasoning. Across complex recommendation and open-ended query benchmarks, behaviorally grounded profiles consistently improve base models and outperform synthetic profile baselines, driving stronger parametric alignment and enabling richer, multifaceted reasoning. Our findings establish open-ended, behavior-derived profiles as a highly diverse and effective foundation for the next generation of personalized language systems. Our code base is available at https://github.com/ServiceNow/behavior-grounding.

Most evaluations for coding agents are conducted exclusively in English, which does not reflect real-world multilingual deployment. We present Terminal-Bench-LILT, a suite of 300 authentic coding tasks in ten languages: Arabic, Czech, German, Spanish, Hindi, Japanese, Korean, Serbian, Turkish, and Chinese. Each task targets issues specific to non-English software development that have no direct English equivalent, e.g., internationalization, encoding, text normalization, and cultural conventions. All tasks are authored by native-speaker programmers and validated through a multi-stage quality control pipeline. Evaluation of six frontier models reveals that even the strongest model reaches only 63.1% pass rate, with many tasks unsolved by any model. Performance varies substantially by language and does not track general coding benchmark rankings, highlighting that multilingual coding competence is a distinct and underexplored capability axis. Sample tasks are available at https://github.com/lilt/terminal-bench-lilt

In this paper, we present PromptKWS, a novel Prompt-guided keyword spotting (KWS) framework to improve the accuracy of open vocabulary KWS systems. In specific terms, we introduce the Prompt Phrases Prediction Network (PPN), an encoder-decoder architecture designed to effectively extract keyword prompts embeddings. we employ the PPN encoder to encode the keyword prompts and infuse the prompt embedding into the Prompt-guided KWS encoder by utilizing a Prompt-acoustic Multi-head Cross-attention (MHCA). Experiments show that PromptKWS improves the wakeup rate by over 10% compared to baseline system. Notably, another strength of PromptKWS is its ability to effectively leverage keyword prompts for adapting to complex real-world environments involving noise and pronunciation variations. In comparison to purely acoustic models, which often struggle in such situations, PromptKWS demonstrates remarkable performance, with an average accuracy improvement of over 15% in test sets.

Formal theorem proving with large language models remains challenging due to the difficulty of navigating large proof search spaces efficiently. Existing tree search approaches either feed verbose compiler error messages directly into the generation context, increasing context usage during search, or employ non-standard evaluation protocols that prevent direct comparison with established baselines. We propose a three-role Monte Carlo Tree Search (MCTS) framework that treats the Lean 4 compiler purely as a reward oracle using compiler output as a scalar signal for UCB-guided tree updates without feeding error content into the generation context. Our framework decomposes proof search into three roles: a generator for proof attempts, a decomposer for subgoal decomposition, and a critic for subgoal quality evaluation. We evaluate across 4 benchmarks spanning competition mathematics and physics (MiniF2F, PutnamBench, LeanPhysBench, PhysLeandata) with three prover models at standard proof attempt budgets (PAB@16 to PAB@256). Our method achieves 87.1% on MiniF2F with Goedel-Prover-V2-8B at PAB@256 and solves 26/659 PutnamBench problems at PAB@32 surpassing base sampling 18/659 at same proof attempt budget. Through an exhaustive axiom-level audit of every compiled proof, we further identify reward hacking in search-based theorem proving: DeepSeek-Prover-V2-7B produces proofs on PutnamBench that pass compilation and the standard sorry-token scan while depending on sorryAx. The audit removes 4 and 8 such proofs from whole-proof sampling at PAB@32 and PAB@128, and 11 and 19 from MCTS. We do not attribute these counts to the search procedure; we report them to establish that kernel-level auditing is necessary for compiler-verified evaluation.

Modern manufacturing enterprises operate heterogeneous systems – ERP, MES, PLM, SCADA, QMS, SCM – each with its own data model and API. The resulting silos prevent holistic analysis, delay root-cause investigation, and obstruct Industry 4.0 traceability. Point-to-point integration scales as O(n^2) and accumulates brittle dependencies. This paper presents an open framework for semantic graph unification of industrial digital threads. An ontology-driven RDF knowledge graph unifies data from 11 simulated sources across nine domains through a five-stage ETL pipeline with automated entity resolution spanning 97 owl:sameAs identity links. The ontology encompasses 78 RDFS classes, 108 object properties, and 243 data properties, drawing on ISA-95, OPC UA, eClass, the Asset Administration Shell, RAMI 4.0, and additional standards. An automated discovery engine applies nine strategy categories – cross-station correlation, alarm coverage, ECN impact, CUSUM/EWMA drift detection – to surface insights spanning system boundaries. The primary empirical result: blocking 24 cross-system tools reduces recall from 1.00 to 0.31 (F1 from 1.00 to 0.48), showing that 69% of discoverable signals require cross-system graph joins. Leave-one-out ablation confirms six of nine strategies contribute unique signals. Verification against a 65-signal manifest (16 positive, 49 null) yields F1 = 1.00 (95% Clopper-Pearson CI [0.79, 1.00]); as the manifest was author-constructed, this constitutes verification not independent validation. The graph is exposed to LLM agents via 287 Model Context Protocol tools as a SPARQL-native semantic layer. Five industry templates (aerospace, CPG, pharma, medical devices, turbine blades) demonstrate schema stability across manufacturing verticals.

Root cause analysis (RCA) in large datacenter networks is challenging because telemetry is noisy, partial, and asynchronous. Score-based approaches degrade under these conditions, often yielding unstable or incorrect attributions. We present CoreSec, a production RCA system that replaces weighted fusion with a PAM-style abstention algebra. Telemetry agents are composed using control flags that yield deterministic decisions and explicit abstention when evidence is ambiguous. CoreSec combines this algebra with topology-aware configurations that capture failure surfaces across Clos fabrics and converge monotonically as evidence accumulates. Deployed at hyperscale, CoreSec provides stable and explainable RCA behavior across diverse environments without retuning. Our experience shows that structured composition with abstention forms a practical foundation for automated RCA in real-world cloud networks.

Energy-aware LLM serving requires comparing configurations under realistic request shapes, yet exhaustive target-GPU profiling is costly and a cheap predictor can be dangerously confident outside its measured scope. We present TokenPowerSandbox, an evidence-gated workflow that combines an interpretable CPU-resident projector, short target-GPU probes, full-workload verification, and tamper-evident freeze-before-measurement provenance. On one NVIDIA H100 80GB serving Qwen2.5-7B-Instruct with vLLM, three anchor repeats and six development workloads calibrate workload transfer. The same frozen model is evaluated on a blind holdout and a separately predeclared no-refit confirmation totaling 51 post-freeze runs. Energy MAPE is 6.23% and 7.35%, with Spearman rank correlations of 0.976 and 0.933. However, a predeclared TTFT gate passes at concurrency four (9.27% MAPE) and triggers abstention below four (64.80%), showing why energy accuracy cannot certify latency.

Each row of a transformer's attention matrix is a probability distribution over tokens, and in trained models most of that probability lands on a single sink token, usually the first. Standard tools for comparing attention rows (cosine similarity, Jensen–Shannon divergence, Shannon entropy) therefore hinge on a choice papers rarely report: keep the sink, or drop it and renormalize. This choice can reverse conclusions. On ten pretrained models from five families, 17–47% of verdicts about which of two heads is more similar flip with the convention, and the most prominent structure in a standard BERT head-clustering pipeline is an artifact of it. The reason is that one-number summaries mix two questions: how much attention the sink takes, and how the rest is divided among the content tokens. Treating rows as compositional data separates them exactly: the Aitchison distance splits orthogonally into a sink term and a content term, entropy splits by an exact identity, and the content distance is characterized by invariances the transformer itself possesses. The separation matters in practice: most measured entropy collapse during training is the sink growing, not attention sharpening (30% of the drop at 70M parameters, 95% at 1B, 79% at 1.4B), and pruning heads with the wrong channel can inflate perplexity more than a hundredfold. We map where each convention is safe, test a frozen out-of-sample predictor (one confirmation, one abstention, one failure), and release code regenerating every number.

AI coding agent benchmarks rank agents with the Chen et al. (2021) pass@k estimator, but current implementations misapply it: they set n to the number of unit tests in a single submission rather than the number of independent rollout attempts, conflating test-suite size with attempt independence. We diagnose this operationalization error, prove it by counterexample, and propose reliability@k, the same estimator applied correctly, with n = independent rollouts and c = fully-passing rollouts per (task, agent) pair. In a synthetic multi-rollout benchmark, the misapplied metric inflates reported scores by 0.85-0.97 in absolute terms (0.96-0.98 reported vs. 0.00-0.12 corrected), and a cheap single-rollout proxy fails to substitute for repeated runs (Spearman $\rho = 0.417$). Motivated by evidence that functional correctness does not imply security safety, we additionally propose security-adjusted reliability@k, which counts only rollouts that are both functionally correct and free of high-severity insecure patterns. In an initial live-API test with three agents, the adjustment did not change any ranking under our current scanner and threshold, so we present it as a proposed complementary lens whose decisive evaluation requires better-powered future runs. Finally, a preliminary 5-task SWE-bench Verified pilot observes the same core concern in a real repository setting: macro-averaged hidden-test pass rate was 0.80 while strict task resolution was 0.20.

Predicting spatial gene expression from hematoxylin and eosin (H&E)-stained images offers a cost-effective alternative to spatial transcriptomics (ST). However, existing methods treat H&E images as generic visual inputs and ignore their intrinsic biological hierarchy, where spatially organized cell types collectively form functional tissue microenvironments that govern local gene expression programs. To bridge this gap, we formulate H&E-to-ST prediction as a cross-modal semantic translation task and propose Path2ST, a hierarchically grounded autoregressive framework featuring three key components: (i) a Hierarchical Cell-Tissue Conditioning mechanism that fuses explicit and implicit cellular features with tissue-level semantic representations to construct hierarchical conditioning signals; (ii) a Scale-Adaptive Autoregressive Generation process over a hierarchical semantic vocabulary, enabling coarse-to-fine, biologically consistent expression synthesis; and (iii) SpectraLoss, a full-spectrum objective that jointly enforces ordinal fidelity, models transcriptional bursts, and aligns semantic structures with cell types. Extensive experiments on three datasets demonstrate state-of-the-art performance, validating that Path2ST generates highly accurate and spatially coherent transcriptomic profiles. The related code is released at https://github.com/RuochenLiu23/Path2ST.

As large language model (LLM)-based multi-agent systems become increasingly capable, coordinating agents under uncertainty becomes a fundamental challenge. Existing orchestration strategies typically rely on fixed interaction patterns and often lack mechanisms for assessing the reliability of intermediate reasoning steps, allowing errors and hallucinations to propagate through the system. This paper introduces a semantic-uncertainty-guided orchestration approach, HASSUM as a general framework for uncertainty-aware coordination in multi-agent systems. The method estimates uncertainty using semantic entropy and semantic density, which measure trust at the level of answer semantics rather than output probabilities. These signals enable adaptive orchestration decisions, including output verification, selective reprompting, additional deliberation, and confidence-aware response selection. Because the approach operates independently of any particular agent architecture, it can be integrated into a broad range of hierarchical and collaborative multi-agent systems. The evaluations demonstrate an implementation within a hierarchical agent framework and evaluate it on StrategyQA, JailbreakBench, and TruthfulQA benchmarks. Across tasks that require complex reasoning and are prone to ambiguity or hallucinations, uncertainty-guided orchestration yields more reliable outcomes than uncertainty-unaware coordination. Semantic entropy and semantic density in tandem outperformed either metric alone. Ablations testing different thresholds and model sizes demonstrated that both influence the effectiveness of semantic metrics. The results suggest that semantic uncertainty is a practical and general-purpose signal for improving robustness and trustworthiness in agentic AI systems.

Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data. We introduce Equilibrium Forcing (EqF), a simplified framework for video denoising generative models without noise level conditioning. EqF pioneers modular training- and inference-time designs for noise-unconditional generation that decouple learning the denoising field from sampling. This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample, improving video quality and consistency on challenging autoregressive video generation benchmarks. Extensive analysis elucidates exactly how removing the noise level conditioning enables EqF's data-dependent inference properties to surpass the performance of standard noise level-conditional denoising video methods.

Agentic "Continual Learning Harnesses", systems that pair an LLM with retrieval or memory to improve from feedback without retraining, have shown growing value in cybersecurity. But their value is conventionally measured by gains against labeled benchmarks, an approach that often fails in operational security settings. Benchmark labels are scarce, stale, and unrepresentative, so a practitioner often cannot tell whether a given harness helps at all or which of two is better for their task. Traditional LLM-as-a-judge offers little signal because it is no stronger than the agent it evaluates, and distillation is unreliable on scarce, sporadic, and biased labels. We propose a framework for evaluating learning harnesses end-to-end without a labeled benchmark, grounded in the scaling hypothesis. A stronger teacher model provides sparsely sampled corrections to a smaller student with a continual learning harness. We score a harness by how much its student converges toward the teacher over time. Across security tasks, model families, and harness designs, we show that improvement relative to the teacher correlates with improvement relative to a held-out gold standard, validating teacher-relative lift as a proxy for true harness uplift when labels are absent. We further show that LLM-as-a-judge between similarly powered models yields no usable signal. These results suggest that a teacher-sized model can be improved through the same harness when humans provide the same kind of sparse, high-precision corrections.

Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate. But aggregate gains say little about individual samples: an update can still cause sample-level regression, where a response correct under the old model becomes incorrect under the new one. This paper studies how to predict such regressions from signals available at inference time. We compare single-model signals (confidence, logit margin, attention entropy) against cross-version signals (output KL divergence, likelihood drift, token-level KL, representation drift) under a unified added-value test that isolates each signal's gain over a confidence baseline. Across six benchmarks in three task families (multiple-choice question answering, or MCQ; math reasoning; code generation) and six model update pairs, we find that (1) signal effectiveness is task-dependent: confidence is strongest on MCQ and simpler math, while likelihood/KL signals give the most frequent gains on harder math and code; (2) no signal is universally best across model updates either; and (3) some cross-version signals stay informative even when confidence fails, including without labels, which supports a proof-of-concept selective fallback that routes high-risk samples back to the old model. Practitioners can use these task-level patterns to choose which regression signal to trust for a given update. Code is available at https://github.com/jiashengsally/llm-regression-signals.

The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval toward experiential intelligence for continuous personal learning.

Natural language provides robots with a flexible task interface, but target ambiguity in embodied environments arises not only from user intent; it can also result from missing taskrelevant physical evidence in the current observation. Existing interactive disambiguation methods primarily obtain additional information by asking the user, whereas occlusion, restricted viewpoints, unreadable text, and unobserved targets require the robot to actively change its observation. We propose an active-perception framework for embodied target disambiguation that uses active observation as the backbone for information acquisition and uses a vision-language model to decide, on the basis of accumulated visual evidence and interaction information, whether to continue observing, request clarification, or complete target selection. Active observation can both directly recover missing discriminative evidence and reveal object names, labels, and semantic attributes, thereby improving user clarification when it remains necessary. Real-robot experiments show that the framework combines physical information acquisition and userintent clarification within a unified embodied disambiguation process.

Detection of misunderstanding is an urgent problem to solve because communication has moved away from real-time, in-person interaction and is increasingly handled by AI-mediated channels. This shift cuts communicators off from the resources repair depends on faster than new means of detection are being built. In this paper we analyse misunderstanding as a layered process in which a divergence is generated, may then be amplified, and is either detected and repaired or left to persist unnoticed. Consolidating accounts from nine fields of research that do not ordinarily cite one another, we identify eleven exact failure modes and show that each operates at a specific point in a communicative process rather than anywhere within it. Those points give eight analytical layers, derived from the literature rather than adopted from an existing model. Eight of the mechanisms primarily generate a divergence, two primarily amplify one already present, and one governs whether a divergence is detected and repaired. We model the eight layers formally, extending information and communication theory from the transmission of signals to the reconstruction of meaning, and we supply a source-by-source evidence matrix that makes every rating auditable, a coding manual, and nine analysed dialogue cases. No prior classification of misunderstanding both locates mechanisms at points in the process and types them by function.

Large Language Models (LLMs) are increasingly integrated into software engineering workflows, helping developers write, debug, test, and maintain code. While prompt wording and structure are known to influence model performance, the impact of psychologically inspired prompt framings remains unexplored. This study investigates whether different psychology-based communication strategies that humans use to persuade or motivate others can lead to more effective prompt framing, which may, in turn, affect LLM behaviour in coding tasks. Drawing on Yukl & Falbe's well-known taxonomy, we operationalized eight influence tactics (like rational persuasion, ingratiation, and exchange) into reproducible prompt templates. These prompt templates were evaluated across five leading open-weight LLMs using two widely adopted benchmarks: LiveCodeBench and SWE-bench Verified. We assessed the resulting code output on four key software quality dimensions: functional correctness, quality, maintainability, and security. Our results show that certain influence-induced prompt framings, particularly those emphasizing urgency, were associated with reduced correctness and security. This work presents the first large-scale empirical study of influence-induced prompt framing in software engineering tasks, offering insights into how linguistic cues may shape LLM outputs. We conclude with practical insights for designing transparent and interpretable human-AI interactions in code generation.

In sequential decision making, an agent typically observes its environment and acts at every timestep. However, such active participation may not always be necessary; tasks such as brewing coffee include periods that are served equally well by letting the environment evolve without constant monitoring and control. During such periods, the agent could simply wait to conserve its resources, or redirect its attention to another task. We capitalize on these opportunities by training a "waiting policy" that decides where and how long to wait. This involves forgoing sensing to commit to a wait action, representing a deliberate pause for a set number of timesteps. We formalize "learning to wait" as minimizing the frequency of sensing and decision making without sacrificing task performance (e.g., the total amount of time to complete a task). To train a waiting policy, we propose an approach that employs reinforcement learning with lexicographically ordered objectives. In experiments across 4 discrete-state household tasks and 3 continuous-state environments, we show that our approach successfully learns waiting behaviors, and can adapt pre-trained policies to wait where appropriate. While different tasks permit different amounts of waiting without sacrificing task performance, our approach consistently finds solutions with significant waiting, sometimes waiting for over 50 percent of the task duration.

Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neuroscience, but their mechanistic basis is not fully understood. We introduce a verbal-only LLM conflict task in which a prompt stem elicits a default same-color completion and an explicit rule either agrees with (congruent condition) or conflicts with (incongruent condition) the completion. Gemma-2-2B and six Pythia models ranging from 410M to 12B parameters showed strong default same-color tendencies, and six of seven models showed strong congruency effects. Using causal attribution analysis, attention analysis, and attention ablations, we identified distinct processing pathways in these LLMs: a pathway involving short-range attention to a superficial color cue that is preferentially activated in the congruent condition, and a pathway involving long-range attention to the rule prefix that is preferentially activated in the incongruent condition. Fine-tuning that strengthened the default same-color tendency had divergent effects on task conditions, reducing incongruent performance while increasing congruent performance. In contrast, increasing rule set size selectively impaired incongruent performance. These converging findings support an account in which congruency effects in this task arise from competition between an in-weight default mapping and an in-context rule-based mapping. More broadly, our findings illustrate how LLMs can serve as model systems for mechanistic analysis of competition between default and rule-governed response tendencies within a single learned network.

Full justified representation (FJR) is among the strongest known satisfiable proportionality axioms for approval-based committee elections. Recent work has shown that an FJR committee can be found in polynomial time, but verifying whether a given committee satisfies FJR remains coNP-complete. We introduce FJR+, a strict strengthening of FJR and EJR+ that can be verified and satisfied in polynomial time. We then analyze the Residual-Budget Greedy (RBG) algorithm and prove that it selects a partial committee such that every size-$k$ completion satisfies FJR+. This freedom allows us to use sequential Phragmén to obtain a priceable completion. The resulting rule always satisfies FJR+ and the sub-core, and it is priceable whenever at least $k$ candidates receive an approval. We also obtain a Droop-quota version of FJR+. Finally, we extend FJR+ to approval-based participatory budgeting with arbitrary project costs. A project-specific version of RBG computes this property in polynomial time and can be continued to a priceable outcome satisfying a cost-based version of the sub-core.