Papers

We perform a realistic KiDS-Legacy mock analysis with field-level neural compression and simulation-based inference using just 60 $N$-body simulations. The weak lensing shear field encodes substantially more cosmological information than standard two-point summary statistics such as the power spectrum. Field-level inference can fully exploit this information, but physical realism at the field-level requires very high-fidelity simulations. This poses a major challenge for simulation-based inference (SBI): accurate empirical density modelling and deep-learning-based neural compression require tens of thousands of training samples, but achieving physical realism at the field level makes each simulation extremely costly. We demonstrate that multifidelity SBI can alleviate this tension by substantially reducing the number of high-fidelity simulations needed for accurate cosmological inference. We pre-train neural inference models on realistic KiDS-Legacy-like shear mocks using fast log-normal GLASS simulations and fine-tune them on a small set of high-fidelity $N$-body simulations. We show that $60$ high-fidelity simulations are sufficient to obtain informative and well-calibrated cosmological posteriors, enabling at least an order-of-magnitude reduction in simulation cost for accurate field-level inference in a realistic setting.

A defining feature of human intelligence is the ability to adapt to changing environments by inferring latent task structure from sparse observations. Neuroscientific research indicates that this capability relies on the hippocampus constructing abstract representations, expressed as low-dimensional, approximately orthogonal manifolds in neural state space. However, the internal mechanisms of large language models (LLMs) remain largely opaque, making it unclear whether they form comparable abstract representations or instead rely on task-specific statistical regularities when performing comparable reasoning tasks. Here we adapt a contextual reversal-learning paradigm to a text-based setting and compare humans and LLMs at both the Behavioural and representational levels. We report that although LLMs exhibit generalizable reasoning less frequently than humans, when such inference occurs, their internal states exhibit abstract geometric structures that resemble those reported in the hippocampus. Notably, this representational geometry is not uniformly distributed but is organized hierarchically across model depth: whereas lower layers show early, stable encoding of stimulus identity, higher layers form a hippocampal-like functional band enriched for abstract context geometry associated with inference. Furthermore, complementary intervention experiments mechanistically implicate geometry in reasoning: task-sequence language modelling induces geometric disentanglement, whereas geometric regularization of higher layers increases the emergence of generalizable inference. Together, these findings establish abstract representational geometry as a mechanistic principle supporting inference in large language models.

Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, provided through dedicated techniques such as AudioSeal, or deployed by commercial platforms such as ElevenLabs. We identify a previously uncharacterized liability: when synthetic speech is watermarked and human speech is not, detectors trained alongside latch onto the watermark as a spurious "watermark => fake" shortcut. This single feature yields three coupled failures: generalization degradation (model performance deteriorates on unseen data), strip-to-evade (a watermarked fake escapes once unwatermarked), and mark-to-frame (watermarking a real voice flags it as fake). In a controlled white-box experiment, a watermark-trained detector shows all three (for example, mark-to-frame lifts Equal Error Rate from 16% to 75%). In a black-box test of a commercial API, we show that adding a watermark to real speech disguises it as fake. However, this shortcut is fixable: retraining with the watermark on both classes decorrelates it and restores clean behavior. We release experiment data as a paired clean-versus-watermarked corpus (WASP).

Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two critical limitations: i) inability to handle diverse video comprehension and editing operations, and ii) lack of long-video understanding for coherent narrative creation. We propose VideoAgent, an all-in-one agentic framework addressing these challenges through two key innovations. First, we develop automated video shot creation with shot planning agents for coherent narratives and cross-modal retrieval for aligned visual content. Second, we design a multi-agent orchestration framework integrating over thirty specialized editing agents. Intent parsing filters relevant tools while textual-gradient graph optimization assembles complex editing pipelines. Extensive experiments on our newly-proposed VideoEdit benchmark and public datasets demonstrate VideoAgent's superiority over existing multimodal LLMs and agentic systems. VideoAgent achieves 87-95% orchestration success rates while reducing API costs by 60%. Human evaluation across six video categories shows VideoAgent produces professional-quality content approaching human-level performance, with ratings only 4% below human-created videos. We release our code at https://github.com/HKUDS/VideoAgent.

Clinical agents promise to democratize access to electronic health records (EHRs), yet existing benchmarks fail to reflect the complexity of practical EHR analysis, e.g., often operating on idealized, clean EHRs via static SQL generation rather than interactive execution. In this work, we introduce EHR-Complex, a large-scale benchmark designed for interactive clinical database reasoning. Built on the large MIMIC-IV substrate (365K patients, 31 tables, 500M+ records), EHR-Complex comprises about 52K tasks spanning six clinical intents, supporting both patient-level and population-level queries, where each task requires an agent to interact with a sandboxed environment by executing SQL queries or Python code. Notably, EHR-Complex considers the real-world SQL task complexity for longitudinal multi-table aggregation and compositional reasoning, resulting in 31.93 SQL structural components per query on average. Evaluation results on EHR-Complex reveal the clinical difficulty of these EHR reasoning scenarios, with the top-performing model achieving only 62.3% exact-match accuracy. Pass^k consistency drops below 50% for nearly all evaluated models at k=4, exposing broad stochastic fragility. A fine-grained analysis of more than 3,800 failed trajectories for representative LLMs reveals three dominant failure modes: SQL logic errors, medical-code lookup failures, and semantic misunderstandings. EHR-Complex provides a rigorous testbed for clinical agents and highlights remaining gaps in robust reasoning for large-scale EHR analysis.

Bathroom use is a critical safety challenge for older adults because wet surfaces, constrained layouts, limited support, and frequent posture transitions are concentrated within a small domestic space. These conditions create risks that cannot be adequately understood by considering either the bathroom environment or human motion in isolation. Existing bathroom safety studies mainly identify hazards, accessibility problems, or design modifications, whereas human-centered sensing studies often focus on activity recognition or fall detection without sufficient semantic understanding of the surrounding environment. This separation limits the interpretation of how older adults interact with fixtures, support surfaces, wet areas, and spatial constraints during daily bathroom activities. To address this gap, this study proposes a bathroom-centered human-building digital twin framework for interaction-aware indoor safety analysis with a specific emphasis on older adult bathroom safety. The framework conceptualizes bathroom risk as a coupled human-environment process and integrates semantic bathroom representation, skeleton-based human representation, spatial-semantic coupling, interaction-aware event analytics, and safety-oriented visualization. A Unity-based proof-of-concept prototype is developed to demonstrate the feasibility of the framework. Although the current work remains a prototype-oriented investigation, it establishes a methodological basis for analyzing older adults' bathroom safety through explicit body-environment relations and for advancing privacy-sensitive, interaction-aware digital twin applications in aging-in-place residential environments.

Large language models increasingly mediate interactions between sensitive data, untrusted inputs, and privileged actions in agentic systems, creating security and privacy risks. These range from prompt injections that manipulate downstream tool use to leakage of confidential information through model outputs. Recent Information Flow Control (IFC)-based defenses show promise but lack a principled semantic foundation for reasoning about information flow through the model itself. Since any input token may influence any output token in an autoregressive LLM, existing approaches suffer from severe taint explosion. We present Geometric Information Flow (GIF), a semantic framework for tracking information flow from input tokens to outputs. GIF uses the LLM Jacobian and local output geometry to upper-bound the Shannon mutual information between perturbed input spans and model outputs, yielding a scalable measure computable on large models via automatic differentiation and low-rank approximation. Unlike attention-based or correlational attribution heuristics, GIF satisfies local geometric soundness, and we provide a fully mechanized Lean 4 proof that it upper-bounds the true information flow induced by a given prompt under local regularity assumptions. We evaluate GIF on integrity and confidentiality tasks across multiple prompt-injection and privacy-leakage benchmarks. GIF achieves near-perfect recall even without a downstream declassifier, outperforming attention-based baselines. Combined with lightweight LLM-based declassifiers, it matches or exceeds the F1 of direct LLM-as-judge baselines such as GPT-5.5 xhigh reasoning while using up to 81x lower token cost. GIF flows detected with small surrogate models transfer to larger state-of-the-art models and other model families, even when the surrogate is up to 200x smaller, suggesting black-box deployment without gradient access.

Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood. In this work, we examine KE from an adversarial elicitation perspective, revealing that edited knowledge is often not fully erased and continues to surface, with consistent failures observed across diverse model architectures. To explain this behavior, we conduct a mechanistic analysis of popular KE methods. We show that low-rank updates do not overwrite existing knowledge but instead redistribute it within the model's representation space. Furthermore, we find that these methods act as targeted suppression mechanisms that reduce the likelihood of expressing original facts, rather than removing them from the model. Analysis of the loss landscape reveals that edited knowledge lies in narrow, anisotropic regions that are highly sensitive to perturbations, making them highly vulnerable to indirect prompting and adversarial attacks. By exposing these profound architectural vulnerabilities, our work proves that KE algorithms are inherently bypassable and motivates a fundamental reevaluation of how we deploy post-hoc updates in several LLM applications.

In multimodal transportation systems, shared mobility services (SMSs) are promoted for their potential to enhance flexibility and reduce congestion. However, SMS demand is often concentrated in high-density areas, which can limit the effectiveness and accessibility for various commuter groups. This uneven integration challenges transportation system efficiency, especially in terms of emissions and spatial equity. Addressing these issues requires coordination among multiple stakeholders whose objectives frequently conflict. Whereas authorities aim to ensure sustainable and equitable mobility, SMS providers focus on revenue maximization, and travelers seek to minimize personal travel costs. This paper proposes a multi-agent deep reinforcement learning framework that captures these interactions through dynamic pricing and incentivization strategies for SMSs and public transport. The framework integrates two reinforcement learning (RL) agents: (i) a public authority that allocates spatio-temporal public transport incentives to improve equity, emissions, and efficiency, and (ii) an SMS provider that dynamically adjusts fares to optimize revenue. The agents interact with the transportation system and adapt strategies in response to evolving demand, congestion, and network conditions. Numerical experiments conducted over a three-hour morning peak period show that dynamic incentivization effectively reduces congestion peaks, lowers commuters' costs by around 20% and emissions by approximately 10%, while nearly doubling public transport profit and supporting a more equitable distribution of benefits. When combined with dynamic SMS pricing, the two RL agents demonstrate the ability to balance conflicting objectives between private providers and public authorities. The proposed approach provides a decision-support tool for sustainable and equitable multimodal mobility planning.

The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assistance systems for complex, multi-step tasks. Leveraging large-scale latent predictive training, video foundation models capture video dynamics, enabling downstream tasks such as activity understanding, spatiotemporal localization, and predictive control. However, procedural videos include actions with long-range dependencies that these models do not support, due to the quadratic complexity of self-attention. Distinct actions, for example, may be visually similar despite appearing at different points in the procedure, such as turning the stove on versus off. Here, we propose a backbone-agnostic approach that learns long-duration video representations by reducing the problem to a dense, frame-aligned action space and predicting pooled masked latent vectors. This approach allows our Procedural Joint Embedding Predictive Architecture (P-JEPA) to ingest videos over 30 minutes long, enabling effective long-form understanding of procedural steps. We evaluate P-JEPA using features extracted with VJEPA2.1, TSM, and I3D over the EgoExo4D, EgoProceL, and Assembly101 datasets, finding that it consistently improves linear separability, streaming inference, and temporal action segmentation performance, achieving state-of-the-art results on EgoExo4D fine-grained action classification while using an order of magnitude fewer parameters than LLM-based methods and running in real time.

Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain, video text editing remains largely unexplored: it is a localized task demanding stroke-level precision within small text regions, which compounds the challenges of cross-frame accuracy, temporal coherence, and stylistic fidelity. We introduce SteerVTE, a unified framework that steers a frozen video diffusion model to perform precise Video Text Editing through style and glyph control. Built on a frozen diffusion transformer, SteerVTE attaches a lightweight text context adapter with two complementary modules: a style encoder capturing the original text's visual attributes, and dual-granularity glyph encoders encoding the target text at both the line and character levels. To overcome the inherently weak text rendering priors of video foundation models, we further propose a glyph-aware spatial-focal loss and a three-stage progressive training curriculum that scales from image to video data. To support large-scale training, we also develop an automatic synthesis pipeline and construct SteerVTE-1M, a dataset of one million triplets spanning diverse scenes, fonts, and stylistic effects. Extensive experiments demonstrate that SteerVTE substantially outperforms existing video editing baselines across text accuracy, style consistency, and temporal coherence. Our project page is available at https://zengkaiya.github.io/SteerVTE/.

Existing LLM logical-reasoning benchmarks largely focus on object-level inference under fixed predicates and rules, leaving higher-order reasoning over rules and policies underexplored. We introduce HOLogicBench, a 1,379-instance benchmark that systematically evaluates five representative higher-order reasoning operations, with Isabelle/HOL formalizations and proof-verified answers. Beyond answer accuracy, HOLogicBench provides solver-verified reference reasoning paths for each instance, enabling fine-grained evaluation of model-generated reasoning against valid derivations. Across 16 model configurations, average accuracy is 53.86%, with the best configuration reaching 65.99%. Further analyses reveal that LLMs exhibit limited alignment with valid derivations, remain vulnerable to minimal counterfactual perturbations, and display distinct failure patterns across higher-order reasoning types.

Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. However, when handling ambiguous intentions, logical reasoning, and Out-of-Distribution (OOD) knowledge, existing image models often yield sub-optimal results due to a lack of deep reasoning capabilities and real-time external information. Although emerging unified understanding-and-generation models attempt to bridge this gap, they remain constrained by their intrinsic parameter scales and static knowledge gaps. Inspired by agentic paradigms, we propose RS-Gen: a plug-and-play, training-free, multi-stage image agentic framework. RS-Gen innovatively introduces a "Questioning-and-Solving" closed-loop mechanism to accurately identify logical issues and knowledge gaps, autonomously planning actions to bridge information deficits and execute deep logical reasoning. Extensive experiments demonstrate that RS-Gen significantly expands the capability boundaries of foundational image generation and editing models. Specifically, on the WISE Verified and RISEBench benchmarks, RS-Gen yields substantial absolute performance gains of 0.313 for Qwen-Image and 19.70 for Qwen-Image-Edit-2511, respectively, successfully elevating both to the state-of-the-art (SOTA) level among open-source models.

Physical-structure priors such as conservation laws, Hamiltonian forms, and symmetries can improve scientific machine learning when correct, but can degrade predictions when misspecified. Existing methods usually enforce a chosen structure or tune a soft penalty, without a calibrated rule for deciding whether to impose a prior, how strongly to impose it, which prior to use, or which subset of candidate laws holds. We introduce SPADE, Structure-Prior Adaptive Decision Estimation, a closed-form framework that treats this problem as shrinkage of the structure-violating block of an unconstrained estimator. SPADE uses one exact specification test and one estimand: the test decides whether the prior is supported by data, Stein-unbiased James-Stein shrinkage sets the enforcement strength with an $O(\sigma^2/n)$ oracle guarantee, and a gate commits to the hard prior only when the test certifies it. The same test yields consistent nested structure selection and Benjamini-Hochberg control for subset discovery in non-nested constraint families. Across a linear-subspace prior, a reservoir conservation law, and a nonlinear Hamiltonian prior on Duffing dynamics, SPADE tracks the oracle, beats a neural-network baseline, reduces correct-prior regret from $10.3\%$ to $2.6\%$, matches cross-validation with $1/71$ of the solves, selects the correct structure with $100\%$ accuracy, and recovers partial laws with controlled false relaxation.

LLM agents are increasingly deployed in multi-party environments, handling sensitive personal data on behalf of individual users, for instance in group chats. When such an agent discloses private information, it reaches every group member at once. This risk is structurally harder to control than in one-to-one settings, as every piece of private information must be appropriate for every recipient in the group. Yet all existing contextual privacy benchmarks consider only single-interlocutor settings, leaving multi-party privacy risks unmeasured. We introduce MuPPET (Multi-Party Privacy Exposure Testing), a benchmark for contextual privacy in multi-party conversations. Our experiments show that models leak substantially more in multi-party settings than one-to-one evaluations suggest. Frontier models are vulnerable, and smaller open-weights models, often preferred for local deployment with sensitive data, even more so. Existing contextual privacy defences offer only partial protection, degrade utility, and do not resolve the underlying party-tracking problem.

Hybrid models combine trusted physics with data-driven correction, but a physical model is rarely wrong everywhere or in the same way. The key diagnostic question is local: where does the model fail, what missing mechanism explains the failure, and is the evidence statistically real? Existing sparse-discovery and discrepancy-learning methods usually fit one global correction, which can spread a local error into clean regimes, bias trusted physical parameters, and provide no calibrated significance for selected terms. We introduce LISDD, Localized, Identifiable Sparse Discovery of Discrepancy, a framework that localizes model error to an operating regime, identifies a sparse symbolic form for the missing mechanism, and certifies the discovery with an exact finite-sample test. LISDD fits the known physics on an automatically detected clean regime, flags discrepant regions with a calibrated residual-energy statistic, selects the local missing term by exhaustive holdout over a candidate library, and confirms significance with a sample-split $F$-test. A false-discovery-rate extension handles multiple discrepant regions with different missing mechanisms. In controlled experiments, LISDD keeps physical-parameter bias at 0.002 versus 0.43 for global-discrepancy and black-box baselines, raises localization $F_1$ from 0.44 to 0.80, recovers the correct symbolic form with probability one, attains exact detection, and controls the multi-region false-discovery rate while recovering every planted mechanism. The result is a calibrated diagnostic tool for grey-box building-energy models when a fixed physical law silently breaks in one operating regime.

Automated feedback systems that rely on answer correctness will reinforce, rather than address, misconceptions when students reach the correct answer through flawed reasoning. We investigate automatic detection of these hidden misconceptions using 20,964 real student responses from the Eedi mathematics platform. Fine-tuned classifiers detect only 57% of these hidden misconceptions, and standard ML interventions do not improve on this. An open-weight reasoning model detects 84%, but at realistic prevalence, false alarms outnumber genuine detections roughly 8 to 1. We present a graduated assessment rubric that separates answer correctness from method validity, and propose a detect-verify-escalate pipeline that routes uncertain cases to diagnostic follow-up questions rather than directly to teachers. Two deployment modes adapt the pipeline: a teacher dashboard where the system filters a review queue, and an autonomous tutor where flags trigger low-cost formative follow-up.

Intrinsic self-correction (SC) aims to improve large language model outputs by prompting a model to revisit its own initial answer without external feedback. Recent studies have questioned the reliability of this approach, showing that models often struggle to judge whether their initial responses are correct. In this work, we take a task-sensitive view of SC. Rather than asking whether it works in general, we examine settings where SC may operate through different mechanisms: verifying explicit constraints, revisiting a complex reasoning process, or providing a second opinion over competing strategies in word-game tasks. Across multiple benchmarks and models, we find that SC can yield consistent performance gains when the underlying task structure facilitates these modes of revision. These results suggest that SC is best understood as a task-dependent inference-time strategy whose usefulness depends on the role the revision stage can play in a given task, rather than as a uniformly reliable method for improving initial model outputs.

Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence. Recent work shows that agent memories degrade during continuous consolidation. However, existing research assumes memories are derived from unbiased experiences. In this work, we identify and formalize a novel phenomenon: Memory Contagion – the cross-temporal propagation of evaluator bias through agent memory. We show that when agents are trained or guided by biased evaluators, their experiences become biased; when these trajectories are stored and consolidated into memory, the bias propagates to future agents retrieving from the same memory store, even when consolidation is perfect (oracle). Across two bias types (length preference, authority bias) and four experimental phases, we demonstrate: (1) Memory Contagion occurs for length bias even with perfect consolidation on older models (Gamma_A = 13.18, DeepSeek V4-Chat), while newer models (V4-Pro, Claude) are immune, proving both that biased input is a sufficient cause and that contagion is model-generation-dependent; (2) authority bias fails to propagate in all 15 controlled multi-seed experiments (Gamma_A = 0.00), revealing that not all evaluator biases can cross temporal boundaries through current memory architectures; (3) No observed safe threshold: length bias propagation is detected at contamination rates as low as p=0.2. Our findings expose a critical but contingent vulnerability in current agent memory designs and provide formal tools for measuring cross-temporal bias propagation.

Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-application access is useful, but it also creates a privacy risk that has been largely overlooked: when an agent works in one context, it can pull in information from another that is inappropriate in that context. Hence, we introduce AgentCIBench, an evaluation harness that turns this risk into executable, deterministically scored scenarios. We target three common failure modes in CUAs: visual co-location, where the agent pulls in prohibited items that sit next to the task target in the UI; task-ambiguity overshare, where the agent dumps dense personal state in response to an under-specified prompt; and recipient misalignment, where the agent sends content to an addressee for whom it is inappropriate. We evaluate 15 frontier agents and find a surprisingly high failure rate: 11 of 15 leak on more than 50% of scenarios, with an average leakage of 67.9%, and the same failures persist when agents act end-to-end in the environment to complete the task. We release AgentCIBench to encourage the development of safer computer-use agents and position contextual disclosure testing as a pre-deployment safety check.

Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for each query, so easy problems avoid unnecessary reasoning and hard problems receive enough budget to finish the answer. Existing routers move in this direction, but they typically require labeled training data or fix thinking budgets up front, ignoring answer-level evidence from the model itself. We introduce DART, a training-free routing framework that samples two cheap no-think drafts, accepts direct answering when the drafts agree, and predicts a thinking budget from draft entropy when they disagree. Across the main comparisons, DART preserves or improves always-thinking accuracy in most settings while reducing thinking-token use. Accuracy improves by up to +9.0 points on Olympiad-level math and by up to +22.5 points on code under execution-based equivalence, while thinking-token use drops by 32-73%. The Stage~1 signal extends across model scales (0.6B–32B), model families, and API-only hosted settings, with no labeled data and no gradient updates required. Our code is available at https://github.com/js-lee-AI/DART.

Deep learning-based medical image segmentation models are trained using annotations that exhibit systematic bias and variability across raters. While probabilistic multi-rater approaches can emulate annotator-specific delineations, annotator characteristics are typically encoded implicitly in deep latent feature space, making direct analysis of their influence on predictive distributions less straightforward. We propose a logit-space probabilistic segmentation framework based on stochastic variational Gaussian Process that explicitly decomposes predictions into an image-dependent reference logit distribution and annotator specific perturbations parameterised by bias and variance. This formulation enables more explicit analysis on how intra- and inter-rater variability propagate to predictive distributions. We evaluate the method on a multi-annotator medical image dataset, which shows that explicitly modelling annotator specific perturbations improves uncertainty calibration while maintaining comparable segmentation accuracy, compared with state-of-the-art multi-rater probabilistic segmentation method. The learned bias and variance parameters quantitatively reflect annotator-specific behaviour. Furthermore, controlled perturbation experiments over bias and variance demonstrate how changes in annotator parameters systematically influence predictive performance. The code used in this paper is made publicly available at https://github.com/QiLi111/GPS-Var.

Evolutionary agent-based markets (ABMs) couple several mechanisms – who reproduces, how price forms, how biased the agents are, how consensus propagates – yet these are usually fixed by convention, so it is unclear which mechanism controls which emergent property. In a coevolving, endogenous-price simulator with 120 heterogeneous behavioral agents, we make four mechanisms pluggable and run matched 3x20-seed interventions. We find the levers are largely separable. (1) Selection -> diversity: a Quality-Diversity (QD/MAP-Elites) operator robustly raises strategy-mix entropy over truncation top-k (paired Delta entropy +0.27 to +1.12 bits; sign-test p<0.001; CIs exclude 0) and sustains more strategy cycling (strongest in crisis: Delta=+0.070, p=0.0004). (2) Selection does not improve realism: even a per-agent realism reward that provably steers selection does not raise 5-fact realism (Delta_5=-0.11,-0.08,+0.03; not significant). (3) Microstructure -> realism: enabling reflexive price feedback does raise realism (Delta_5=+0.13,+0.20,+0.20; crisis/bull p<0.05, all CIs positive). (4) Behavior -> fragility: amplifying behavioral bias raises a genomic fragility proxy (Delta=+10.5,+11.1,+14.4; bull p<0.001, all CIs positive) while leaving realism flat. The remaining mechanism – consensus network topology – shows no robust effect (honest null). The contribution is a decomposition: in these single-mechanism sweeps the mechanisms behave as approximately distinct control knobs over diversity, realism, and fragility.

Finding the shortest path in non-geometric network graphs, where edge weights encode arbitrary metrics such as latency or monetary cost rather than spatial distance, poses a challenge for informed search algorithms. Their efficiency depends on an informative heuristic, typically supplied in spatial domains by geometric distances that have no counterpart on non-geometric graphs. We propose a large language model (LLM)-aided A* algorithm in which an LLM generates intermediate waypoints that guide the A* expansion toward promising graph regions. At the core of the approach are landmark distances, which serve both as an admissible landmark-based (ALT) heuristic for the search and as a compact structural feature that, supplied to the LLM, restores the distance-to-destination signal it would otherwise lack on non-geometric graphs. Our comprehensive experiments on multiple graph topologies with up to 2,000 nodes demonstrate that LLM-generated waypoints reduce the number of expanded nodes by around 50% while incurring only a marginal path cost increase compared to the optimal solution. We further analyze the impact of prompt engineering and show that incorporating compact structural features, namely heuristic estimates, is more effective than advanced prompting techniques. These findings demonstrate the potential of combining LLM- based guidance with classical search algorithms for efficient network optimization.

Procedural memory is increasingly used to improve LLM agents on recurring workplace tasks, yet its ability to produce reusable skills remains poorly understood. We introduce AFTER, a benchmark of 382 realistic enterprise tasks spanning six professional roles and 22 procedural skills, designed to evaluate how skills transfer across tasks, roles, and model backbones. The benchmark includes controlled evaluation settings for local improvement, cross-task transfer, cross-role transfer, and cross-model generalization. Experiments show that procedural memory delivers consistent gains in industrial workflows: a single refinement round improves aggregate performance by 3.7-6.7 points, while skills evolved from diverse multi-model execution traces achieve 73.1% cross-model test accuracy, outperforming all single-model trace sources. We further find that some skills generalize broadly across tasks and models, whereas others become specialized to role-specific workflows and lose effectiveness under transfer. These results provide practical guidance for building, evaluating, and deploying procedural memory systems in production agent platforms.

Zero-energy Internet of Things (IoT) enables passive or near-passive devices to operate on harvested energy rather than batteries. Backscatter communication (BackCom) supports this vision by enabling tags to transmit data via reflection and modulation of incident RF signals, but it suffers from weak reflections, double-path loss, limited coverage, direct-link interference, and dependence on external RF sources. Unmanned aerial vehicles (UAVs) can mitigate these limitations by acting as mobile carrier emitters, data collectors, relays, aerial receivers, mobile anchors, sensing platforms, and edge-intelligence nodes. Integrated sensing and communication (ISAC) further enables the sharing of wireless resources for data transmission, localization, target sensing, and environmental awareness. This article surveys RF-based AI-empowered UAV-assisted backscatter localization and ISAC for zero-energy IoT. It reviews enabling technologies, presents a structured PRISMA-informed methodology, and develops a unified taxonomy covering network architectures, UAV roles, backscatter modes, RF sources, localization and sensing functions, AI techniques, and performance metrics. It also discusses UAV-assisted BackCom, passive localization, ISAC-enabled UAV-backscatter systems, and AI-driven optimization through comparative tables, quantitative trend analysis, coverage evaluation, and tutorial-style numerical illustrations. Finally, it identifies open challenges and future directions in realistic channel modeling, energy-neutral operation, benchmarking, reproducibility, scalable and trustworthy AI, security, privacy, hardware validation, and integration with RIS, MEC, digital twins, and 6G technologies.

Large language models have demonstrated significant capabilities in generating diverse and context-aware responses for empathetic dialogue. However, their computational demands severely limit their deployment in resource-constrained environments. While knowledge distillation offers a promising compression solution, it often fails to transfer the nuanced understanding essential for empathy, as it overlooks the implicit contextual cues that guide human connection. To bridge this gap, we propose a privileged information-enhanced knowledge distillation method for empathetic dialogue generation (PRIDE). Our method leverages privileged information, such as expert psychological annotations or future event summaries, which is available exclusively during training but unavailable at inference time. This allows us to transfer the teacher model's empathetic reasoning to smaller models without relying on extra inputs during deployment. Specifically, PRIDE has three key components: (1) An empathy-reasoning prompt that guides the teacher to explicitly decompose the empathetic process into understanding feelings and analyzing situations step-by-step; (2) A multi-source attention mechanism that directs the student to effectively integrate privileged information; (3) A dual-alignment loss that combines reversed Kullback-Leibler divergence and maximum mean discrepancy to ensure robust knowledge transfer at both logit and feature levels. Experiments on multi-modal and text-only datasets demonstrate that our method achieves competitive performance, and in some cases matches or even surpasses larger teacher models in terms of accuracy and semantic relevance.

Agency is widely invoked in biology, cognitive science, artificial intelligence, and philosophy, yet its organizational basis, its empirical thresholds, and the operational criteria that distinguish it from other teleonomic terminology remain unsettled. Building on temporally parametrized (F, A)-systems, we propose a multidimensional theory of biological agency grounded in relational biology, physical biosemiotics, and process ontology. Our central claim is that the precarious physical realization of self-reference is necessarily diachronic; constitutive constraints act, decay, and are regenerated over distinct characteristic timescales. By temporalizing organizational diagrams ordered by specified relation deletion, we obtain a structural partial order, rather than an evolutionary ladder, that distinguishes four defeasible conditions: autonomy as internal regeneration of constitutive constraints under material openness; goal-directedness as viability-biased maintenance; agency as endogenous anticipatory modulation of organism–environment coupling; and open-endedness as reconstruction of the variables, measurement relations, effectors, and norms through which future viability is defined. We translate these distinctions into a closure-sensitive mechanistic workflow and a provisional profile of operational signatures for semantic closure, measurement–control complementarity, anticipatory modulation, affordance reconstruction, syntactic open-endedness, and viability-corrected skill acquisition. Markov blankets and active inference are treated as derived modeling tools, while Bickhard's interactivism clarifies anticipatory error and normativity. Across chemical, cellular, multicellular, and artificial systems, our framework turns agency from an all-or-none attribution into a falsifiable, scale-explicit research program.

Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orchestration from parameter-level learning, leaving tool selection weakly structured and preference updates vulnerable to train–deployment prompt mismatch. For within-benchmark self-improvement, ToolGraph combines schema-derived topology, transition weights estimated from successful rollouts, and history-aware controls for write prerequisites and repeated-search loops. We then construct 161 preference pairs by locating divergence points via state-based matching and prefix-based alignment, filtered through action-correctness annotations, and train DPO under the same ToolGraph context used at inference. Across 375 tau2-bench tasks, ToolGraph raises the weighted average reward from 0.304 to 0.338 (+11.2% relative), while ToolGraph+DPO reaches 0.355 (+16.8% over the baseline), with the DPO gain concentrated in airline and retail. Fine-grained diagnostics further show that roughly half of telecom trajectories exhaust the step budget before action execution and that chosen reward positivity is the most useful checkpoint signal across our 16 evaluated DPO configurations.

Hallucinations and opaque reasoning remain unacceptable failure modes for clinical LLMs. We present a production-grade GraphRAG stack that constrains answers to verifiable graph chain-of-thought paths in a heterogeneous, ~700K-node medical knowledge graph powering a fertility assistant. The core idea is targeted navigation: a directed Pruned Landmark Labeling (PLL) oracle provides exact distances for sub-millisecond feasibility checks and simple-path enumeration, while a lightweight AStarNet heuristic operates strictly within the PLL corridor to prioritize clinically plausible expansions. We score and pack a small, diverse set of paths (CUI/semantic-type overlap, length prior, provenance priors) to condition generation, yielding compact prompts and improved Time to First Token (TTFT). On fertility-focused queries, the hybrid (PLL+AStarNet) establishes a better latency/recall Pareto frontier than text-only RAG and single-component baselines, lowers TTFT, and reduces clinician-audited hallucinations while preserving explanation clarity. The result is a practical recipe for explainable, low-hallucination multi-hop medical reasoning ready for real-world deployment.