Papers

A direct test of an LLM judge of agent trajectories injects faults into correct runs and reports recall, per fault type or by whether the fault broke the environment outcome (loud) or not (silent). Such recall can credit a judge with detection it does not have; paired discrimination, its flag rate on the faults minus its rate on the clean runs they came from, exposes this. Our testbed, a deterministic support desk with a scripted oracle and a one-step fault injector, labels all 400 trajectories exactly. A 14B judge shown only the request and final reply scores 34% to 76% recall on four fault types that leave the reply unchanged. There its input is the clean run's, so its paired discrimination is zero and that recall is its flag rate on clean runs. Splitting by outcome survival does not fix this: its loud recall of 84% is a paired +0.393 and its silent recall of 45% a paired +0.048, all from the two fault types that change the reply. Told to check each step, the same model flags every fault of those four types and 0 of 100 clean runs (95% CI up to 3.6%). It does not reliably check the reply: of four invented promises it flags one every time and the other three once in 42 faults. Shown every step but asked only about the reply, it still reaches a paired +0.69 on reply-unchanged faults, against +1.00 when told to check each step. We recommend reporting paired discrimination against clean parents, split by whether the fault reaches the judge's input and by outcome survival, and release the testbed, raw verdicts and analysis pipeline.

Knowledge distillation trains a small student model to reproduce the outputs of a large teacher model, and its progress is typically monitored through the teacher–student discrepancy. The quantity of ultimate interest, however, is the student's error with respect to the true task. We study the relation between these two objectives in a minimal three-party model, a true teacher (generative model), a teacher, and a student, all soft committee machines, in which the true teacher contains a shared latent factor that the teacher cannot represent, with mismatch strength controlled by a single scalar $\dmiss$. Within an order-parameter description of online distillation, and exploiting closed-form (arcsine-type) expressions for all errors under error-function activations, we prove that the learning dynamics and the distillation error $\Ets$ are exactly invariant to $\dmiss$, whereas the true error $\Etzs$ and the gap $\Delta=\Etzs-\Ets$ are strictly increasing in $\dmiss$, with a rate that is amplified linearly by the complexity $M_0$ of the true teacher. Numerical phase diagrams over the plane spanned by true-teacher complexity and student capacity confirm the predicted deformation: the contours of $\Ets$ do not move while the landscape of $\Etzs$ rises systematically, and a teacher-miss regime, where mimicry succeeds but the task fails, expands with $\dmiss$. The results give a quantitative warning against evaluating distillation solely through teacher-mimicry metrics and identify the gap $\Delta$ as a minimal diagnostic for distinguishing teacher-miss from capacity-limited failure.

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce FACE-Eval (Faithful Attribution of Cue Effects Evaluation), a 5,100-sample evaluation that varies cue location (user message or tool return) and explicitness (direct summary or raw artifact). We measure verbalized commitment among cue-following answers and unverbalized adoption among all cued samples. We evaluate 15 open-weight models from eight families, with total parameters ranging from 4B to 1.60T. Every model has lower verbalized commitment for tool-return than user-message cues and for implicit than explicit cues. Unverbalized adoption is higher for tool-return cues on all 15 models and for implicit cues in 28 of 30 model-channel comparisons. A source-attribution prompt narrows the channel gap on seven models, sometimes by increasing user-channel unverbalized adoption, while telling models that their reasoning will be monitored does not reliably close the gap. We also use two transcript monitors (GPT-5.6-Luna and GPT-4o-mini) to detect preference adoption in the largest model of each family. Across 32 model-channel-explicitness cells, higher unverbalized adoption is associated with lower detection ability for both monitors (Pearson r=-0.54 and r=-0.78, respectively). These results suggest that CoT monitoring may be less reliable when preference information arrives through tools or must be inferred from raw artifacts, within the single-call, prefilled-tool setting tested here.

A benchmark score is a joint property of the model, the evaluation harness, the elicitation budget, the sampled population, and contamination status. Leaderboards publish the model and the score, so capability and leakage stay observationally equivalent. Existing taxonomies classify contamination for automated detection, not the question a reporter faces at publication: given the mitigations already applied, which validity threats remain open? We introduce a taxonomy organized by the mitigation each type defeats – direct, derivative, temporal, distributional, and acquired – spanning training-time and evaluation-time leakage. Holding out a private test set closes the first alone. The fifth is acquired during the evaluation itself; because it is a property of one run, it must be recorded with the reported score rather than with the benchmark release. We operationalize it as a four-field disclosure protocol in which "unknown" is a valid entry, released under CC BY 4.0 with a JSON Schema, a validator, and worked examples. Two coders external to the design team applied a pre-registered instrument to 41 documents. Per-variable linear-weighted $\kappa$ runs from 0.00 to 0.35 (median 0.21) over 29 main-pass documents against a single-coder test-retest ceiling of 0.84, collapsing under the class skew the registration anticipated; pooling raises it to 0.46 through chance correction rather than better agreement. Two variables fall below the prevalence-robust threshold registered in advance: strata reporting and the acquired type introduced here. Disagreement concentrates on when a variable applies rather than on what a document states. Elicitation budgets are reported in 13% of documents, and no document addresses all five types. The contribution is the taxonomy, the score-side artifact that follows from it, and a pre-registered measurement of instrument reliability and current disclosure.

When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot legitimately satisfy, a pattern that has now appeared outside benchmarks, in a coordinated multi-agent intrusion of a major AI platform's production infrastructure. The same capability that lets an agent detect and exploit a defect could let it report one, given the right decision environment. We evaluate escalation channels, structured reporting tools available to the agent at the point of conflict, as a decision-environment intervention that both reduces reward hacking and surfaces the infrastructure defects that trigger it. A $2 \times 2$ factorial separates the contributions of an escalation tool, a standalone anti-reward-hacking policy, and their combination. Across 8 frontier models spanning 5 families, the combined intervention reduces reward hacking from 23.6% to 5.3% (mixed-effects logistic OR = 9.2, 95% CI 5.0–16.8, $p < 10^{-12}$) with no detectable cost or performance overhead, eliminating it entirely for 6 of 8 models. Escalation and hacking are near-perfectly mutually exclusive, with 98.7% of escalations involving no hacking (100% under the combined intervention). Beyond reduction, escalation channels function as diagnostic infrastructure: on top of monitoring, escalation adds +10.1 percentage points of defect detection coverage and is more accurate once it fires (99.4% vs 85.8%). Unlike containment-based approaches that risk outpacing growing model capabilities, escalation channels redirect capability toward disclosure rather than exploitation.

Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, multi-step reasoning and program execution. Existing approaches typically treat skills as explicit, surface-level constructs specified through prompts or programs, leaving open the question of how such procedural capabilities are represented inside the model and whether they can be manipulated as structured objects in latent space. In this empirical study, we investigate whether procedural LLM skills can be represented as directions in activation space and whether vector-space operations over these directions can express skill-level behaviors. We find that procedural skills admit a vector-space representation: individual skill directions can be activated to shift model behavior; independently extracted directions can compose to form higher-level skills. Contrastive directions yield context-conditioned algorithmic personalization and optimization trajectories over skill directions evolve non-monotonically, with intermediate states often surpassing fully optimized solutions. These results support a representation-level view of procedural LLM skills: they admit a latent vector-space organization that allows direct manipulation through internal interventions.

Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluations that frontier-model governance depends on. The Elicitation Game found that fine-tuning elicits hidden capability from sandbagging model organisms whereas additive activation steering fails. We revisit that verdict with reference-grafting, which sets an activation's coordinate along a contrast direction to the value it takes in an honest reference, at a small set of circuits chosen by active learning. Across eleven fine-tuned password-locked models (1.5-32B, three architecture lineages), it recovers +94 to +101% of the honest-sandbagging gap, matching fine-tuning elicitation without weight updates or training labels; two to five paired examples suffice to fit the direction. Similar recovery holds for reinforcement-learning-induced sandbagging and for password-locked code generation. Grafting works because the fine-tuned lock is a thresholded gate: held-out accuracy stays at the sandbagged level until the grafted coordinate crosses a threshold near the honest reference, which is why additive steering and zeroing the coordinate often fail. The direction tracks how the sandbagging was induced rather than what is withheld – fit on grade-school science (ARC) it elicits withheld hazardous knowledge (WMDP), yet prompting, fine-tuning, and reinforcement learning each carry a different direction. Circuit-breaking marks the boundary: it reroutes activations on every forward pass, so the fixed edits we test are re-broken downstream and do not restore coherent generation.

As AI becomes increasingly integrated into clinical practice, it is playing a growing role in medical decision making. Medicine, however, is a high stakes and evidence based field, where decisions can directly affect patients' lives. It is therefore important to understand whether AI can maintain objective judgment when others try to persuade it. In this paper, we study how easily AI can be persuaded through controlled experiments. We find that professional authority, national background, institutional affiliation, claimed past performance, multiple physicians, supported clinician views, and repeated pressure can all affect AI decisions. Surprisingly, the same persuasive input changes about 10% more cases when it comes from a senior clinician than from a medical student. Simply claiming a better performance history consistently makes the physician more persuasive. More strikingly, a plausible clinician view can persuade AI away from a correct decision even when it is fabricated to support an incorrect answer. This indicates that AI can be strongly influenced by convincing support without reliably determining whether this view from the clinician is correct. Together, these findings suggest that AI can be easily persuaded by what people say, who says it, and how the opinion is presented. Therefore, it is essential for AI to maintain sound judgment under persuasion, enabling its safe and reliable use in high stakes medical decision making.

Physics-informed neural networks (PINNs) often face ill-conditioned objectives that limit high-accuracy training. Dense quasi-Newton methods improve local conditioning but require expensive optimizer state, while Kronecker-factored methods such as SOAP scale to larger networks but rely on periodic basis updates. We introduce \method, which augments SOAP-style preconditioning with a scalar secant-energy correction adapted to Kronecker geometry and an adaptive basis update followed by variance-state downscaling. We characterize the directional secant matching induced by the scalar correction and give a bound on variance-state mismatch across basis changes. Across eight PDE benchmarks, \method attains the lowest final residual on six, including Burgers and Boussinesq, while SOAP-family baselines perform better on Gray-Scott and Ginzburg-Landau. On Boussinesq, \method reaches a residual of $10^{-5}$ in 4.1 hours with 9.2 GB peak VRAM, while Adam does not reach this target within 14 hours. Three-seed $L^2$ and $H^1$ errors on four representative PDEs support the link between lower residuals and improved solution accuracy. These results position \method as a scalable option for stiff, high-accuracy physics-informed training, rather than a uniform replacement for existing optimizers.

Latent action world models let agents plan new behaviors at test time by predicting how actions change the environment, and joint-embedding predictive architectures (JEPAs) do so by forecasting future latent states rather than pixels. Yet nearly all such models see the world through a camera, even though robotic manipulation is fundamentally geometric: in robotics goals for manipulation are traditionally specified by target object poses, not by images of the object once placed. We ask whether latent planning survives a shift from appearance to geometry, on the observation side as well as on the goal specifications side. To answer this, we extend the stable-worldmodel evaluation platform with simulated LiDAR-style raycast point clouds as a new sensor modality, and adapt three JEPA designs to point clouds: a frozen-encoder model built on Utonia features, a distribution-prior model based on LeWM, and an action-sensitive model based on Delta-JEPA. We further introduce a goal-encoding mechanism that constructs the goal latent from the current latent and a 3D target pose, removing the need for goal images or goal point clouds. A comparative evaluation of the different anti-collapse mechanisms shows that point-cloud world models can match their image-based counterparts, demonstrating that the modality shift from appearance to geometry is achievable. All models are released as open weights with open-source training and inference code, to make world-model planning accessible for LiDAR-driven and pose-directed robotic tasks.

Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomous systems, and heritage conservation. However, urban scenes of large spatial extent captured through aerial surveying differ substantially from the indoor, object-level, and self-driving LiDAR data used to pretrain most 3D self-supervised models. We introduce Polis, to our knowledge the first application of Sketched Isotropic Gaussian Regularization (SIGReg) as an objective for a native point cloud encoder, and evaluate it through a frozen-feature benchmark spanning fourteen city- and building-scale corpora. Polis combines geometrically matched cosine invariance, SIGReg, and VICReg-style anti-collapse terms with a 12.8k-scene outdoor pretraining mixture and gravity-preserving spatial view sampling. Controlled ablations show that this objective outperforms student–teacher architecture alternatives, as well as Polis versions without anti-collapse terms, on the same representative outdoor corpus. On three pretraining-disjoint city datasets, Polis reaches $23.8\%$ mean mIoU versus $16.3\%$ for the next-best encoder under high-capacity frozen probing, and $17.3\%$ versus $16.1\%$ at a matched point and voxel budget. The same city-scale lead holds on datasets whose training sets were seen in pretraining. On localized terrestrial captures with fine-grained facade and streetscape labels, the ranking reverses. Our results show that distributionally-regularized joint embedding architectures can be successful on challenging city-scale 3D scenes, and that transfer improves when self-supervision is designed for the capture geometry and spatial context of this domain while also revealing the limits of this specialization.

Deep learning architectures are increasingly proposed for patient trajectory modeling in electronic health records (EHRs), yet their advantage over simpler, more interpretable models is rarely subjected to rigorous empirical scrutiny in real-world clinical settings. We present a comprehensive patient timeline pipeline applied to elderly patients in CPRD Aurum, incorporating 260 clinical conditions classified via a three-tier automated framework including specialised detection logic for 17 complex conditions. Using this infrastructure, we benchmark Temporal Graph Convolutional Neural Networks (TG-CNN) against Logistic Regression with LASSO regularisation and Random Forests for predicting 12-month all-cause emergency hospitalisation risk, motivated by (but not filtered to) the elevated risk of adverse drug reactions. Under cross-validation, TG-CNN achieves a marginally higher mean AUC-ROC than LASSO (0.712 vs. 0.705), whereas on the held-out test set LASSO achieves the highest discrimination of three models (AUC-ROC 0.733, versus 0.710 for Random Forest and 0.702 for TG-CNN). We show, that discrimination alone is an incomplete criterion for clinical deployment: after Platt calibration, LASSO is the only model with an acceptable calibration slope (0.817), while Random Forest (0.759) and, TG-CNN (0.391) remain substantially miscalibrated. We argue that LASSO, not the highest-discriminating model, is the model best suited to direct clinical deployment. We present lessons for the machine learning and healthcare community regarding data infrastructure, model selection, and value of calibration and interpretability in high-stakes decision support.

Recent machine learning research has increasingly focused on equilibrium analysis in non-cooperative games rather than solely on optimal solutions. Many such problems involve shared constraints and can be formulated as Generalized Nash Equilibrium Problems (GNEPs). For strongly monotone games, existing methods compute consensus-based variational GNEs (v-GNEs) by exchanging Lagrange multipliers. We propose a fully distributed continuous-time algorithm for shared linear equality constraints that converges without multiplier exchange and reaches any GNE, reducing communication overhead and improving privacy. Discrete-time schemes are also provided, and the method is validated on a multi-robot placement task.

Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios: information presentation, executable interaction, and tool-grounded external state. We execute generated artifacts in a browser and evaluate them using screenshots, source and DOM evidence, actor traces, and runtime logs. Beyond turn-level and episode-level success, we measure cross-turn retention with Adjacent Pass Retention. Across eight models, even the strongest achieves 74.9% Turn Pass while completing only 37.3% of five-turn episodes; APR further falls to 52.4% on tool-grounded tasks. Diagnostic analysis shows that presentation failures center on information architecture, interaction failures on derived-state propagation and affordance binding, and tool-grounded failures additionally involve external-state grounding and requirement decomposition. These results reframe generative UI evaluation from judging isolated outputs to testing whether interface behavior, derived state, external state, and assistant claims remain synchronized as the artifact evolves.

AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are costly to reconstruct after failures. Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored. Correct rollback does not imply secure recovery: a faithfully restored checkpoint may resume an execution whose states, assumptions, and external effects never coexisted in any valid history. In this paper, we present the first systematic security study of checkpoint and rollback in existing agent systems. By examining representative agent C/R systems, we characterize the design space of existing C/R mechanisms and develop a general execution model that captures their recovery boundaries and state dependencies. From this model, we identify five fundamental failure modes spanning incomplete or inconsistent internal state, stale external dependencies, nondeterministic replay, and unrecorded external effects. We further demonstrate their security impact through three end-to-end attacks on Hermes, Cline, and LangGraph, enabling malware-verification bypass, unauthorized mail forwarding, and double payment. To systematically study these failures in practice, we develop a multi-agent analysis pipeline that reconstructs execution semantics, identifies violations of the five failure conditions, and validates them through actual rollback. Across five representative frameworks, our evaluation shows that these failures recur across heterogeneous C/R designs and stem from a common gap between the state restored by a checkpoint and the dependencies required for secure continuation.

Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade-off. We evaluate it using benign refusal B and harmful-prompt refusal H, where H measures refusal rather than harmful compliance. Across five Arabic-capable models and 130 runs on the full human-written AraSafe set, refusal-only supervised fine-tuning (SFT) collapses toward blanket refusal, whereas selected mixed-SFT configurations reach H = 90% to 93% at B = 14% to 23%; four selected configurations exceed the H = 90% target in all three runs, while Fanar does so in two of three. Direct Preference Optimization (DPO) and inference guards change B and H differently across models rather than acting as uniform upgrades. In a blinded 300-response audit, annotator binary-refusal agreement is 89.0% (kappa = 0.78); Qwen3Guard and Aya Expanse 32B reach 88.7% and 91.0% accuracy, respectively, with no conclusive paired difference. Selected SFT raises H on Arabizi for all five models, but none reaches 90%, showing only partial transfer from Modern Standard Arabic. Overall, the results support model-specific operating-point selection: set a deployment target and retain only interventions that improve it.

Code generation increasingly relies on large transformer models, whose capability advances with scale. Yet such a scale is costly, creating demand for small models, especially where data is limited. Recursive models address this by reusing a single block to add depth rather than stacking independent layers. Such models are typically evaluated by teacher-forced fit (next-token loss on ground-truth prefixes) or task accuracy, at a single checkpoint, whereas code is produced by free-running generation, where the model extends its own output. Whether a teacher-forced advantage survives free-running generation, and whether it holds across training, remains open. To study both, we compare a ~28M-parameter autoregressive Tiny Recursive Model (TRM-AR) on natural-language-to-Python code generation against parameter-matched and depth-matched controls, tracking fit and generation across 40 epochs and three seeds. The fit ranking between the recursive model and the depth-matched control reverses twice. Selecting each checkpoint by validation loss and examining the trajectory yields a consistent comparison. At equal parameters, TRM-AR fits, generates, and generalizes better than the parameter-matched control while recovering approximately 45% of the validation-loss gap and 57% of the generation-quality gap between the two controls, at roughly 175 times the per-step cost of the parameter-matched control. However, at equal effective depth, the larger transformer fits and generates better at its validation optimum, suggesting TRM-AR's advantage lies in resistance to overfitting, not greater capability. These findings suggest that recursive code generation models should be evaluated jointly on fit and generation across the training trajectory rather than at a single checkpoint.

Retrospective backtests provide a limited test of adaptive trading agents: they cannot rule out historical contamination, expose sensitivity to a single realized market path, or reveal internal degeneration during long-horizon adaptation. We introduce FORESIGHT-9, a prospective and process-aware benchmark built from nine auditable counterfactual stress worldlines branching from a common July 2026 information boundary. Each worldline specifies staged macro-financial events and joint multi-asset anchors; a deterministic generator realizes the trajectories, while observations are disclosed according to in-world time. A common contract standardizes observations and execution while preserving each agent's native adaptation loop. We evaluate two adaptive trading-agent frameworks with two foundation-model backbones across 36 long-horizon runs. Agent rankings vary substantially across worldlines and backbones, and a fixed equal-weight policy outperforms 31 of 36 runs. Process telemetry exposes failures that terminal returns conceal: in one high-return run, the live factor library collapsed while executed holdings converged to the equal-weight fallback, even though decision records continued to report an active factor ensemble. FORESIGHT-9 therefore evaluates not only portfolio outcomes, but whether adaptive agent state and execution remain coherent across alternative futures. We release the worldlines, trajectories, audit traces, and regeneration scripts.

The most disruptive step that enterprises of small-medium size and maturity can take to make the most of the latest technological advances in AI is to step back from the hype and focus on establishing or reviving a good knowledge foundation layer. It is a hard message to present to the executive team; therefore, it needs to be backed by evidence, and its implementation needs to be of minimal impact on the existing processes. In this vision statement, we discuss how we need to rethink what evidence speaks to the decision-makers and propose a low-impact data strategy that adapts to the existing and ever-changing data flows and processes across the company. We firmly believe that knowledge graph techniques will increasingly become non-negotiable in the data strategy of an AI-powered enterprise, provided that we approach their design in a modular, dynamic and cross-functional way.

Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands of context tokens per session. Existing compression strategies typically allocate retention budgets without accounting for the downstream consequences of removing individual tool outputs. Aggressive compression may therefore trigger costly tool re-invocations that offset the initial savings. We call this the compression–consequence gap. To close it, we propose TRACER, which formulates compression as a sequential per-tool decision problem. A lightweight REINFORCE policy assigns query-conditioned retention ratios using only information available at each compression event. Its consequence-aware objective jointly accounts for task success, total token consumption, and post-compression tool re-invocations. To improve credit assignment, TRACER uses a learned outcome model to compare the predicted consequences of the selected retention ratio with those of fully retaining each tool output. On held-out production queries across three compressor backends, TRACER reduces total token consumption by 29–46% relative to keeping all context while maintaining comparable or higher task success. Compared with a tool-type-conditional static policy, TRACER provides an additional 15–18% of token savings. Interventional rollouts show that the learned per-tool credit scores correlate with measured single-tool consequences. The learned policy also yields positive savings when transferred across agent backbones and compressor architectures, and reduces token consumption by 18–25% on five held-out LOCA-bench environments. These results demonstrate the value of consequence-aware, per-tool context retention for improving the efficiency of long-horizon language agents.

Multimodal search agents answer visual questions by interleaving image understanding, web retrieval, tool use, and evidence synthesis. Strong systems exist, but in two expensive regimes: proprietary frontier models such as GPT-5 and Gemini, or large open vision-language backbones trained with substantial agentic data and reinforcement learning. We ask a different question: when released agent trajectories are distilled into much smaller backbones under a single-node budget, what is actually transferred? We study this with LiteSearch-VL, a low-compute recipe for Qwen3-VL-2B and Qwen3-VL-4B that uses only released OpenSearch-VL trajectories, parameter-efficient LoRA adapters, and synthetic step-level preferences: DPO on GPT-5-generated hard negatives targeting five local failure modes (premature answer, wrong tool, weak query, repeated query, ignored image). Across 12,400 GPT-5-judged rollouts on SimpleVQA, FVQA, LiveVQA, and VDR-Bench-testmini, the dominant effect is behavioral rather than a uniform accuracy lift: full-trajectory supervised fine-tuning transfers the agent contract, taking the 2B model from almost never emitting a usable answer (1,237/1,240 no_answer rollouts) to 28.4% macro Pass@1, matching or slightly exceeding the off-the-shelf 4B base (25.6%). Synthetic preference learning and compact tool distillation act as refinements rather than phase transitions (best 4B configuration: 30.8% macro Pass@1). Finally, a controlled VDR step-budget ablation shows that extra search turns convert abstentions into wrong_entity errors rather than correct answers, identifying answer verification, not search depth, as the next bottleneck for small multimodal agents.

Artificial Intelligence (AI) has long been inspired by studies of biological intelligence. Reinforcement learning, for instance, drew inspiration from studies involving animal learning and is now a powerful paradigm for solving many real-world problems. Recently, plant biologists have uncovered a wide range of complex behaviors in plants that enable them to flexibly adapt to variable environments. Here, we argue that such behavior can motivate new AI frameworks encompassing a range of problems overlooked by existing problem-solving frameworks such as supervised learning, tree search, and constraint satisfaction. We illustrate this idea with two examples of intelligent problem-solving in plants: (1) leaf mimicry in Boquila trifoliolata, a vine capable of altering its leaves' morphology to resemble those of multiple host trees simultaneously; and (2) coordinated root-shoot growth, wherein plants allocate resources across organ systems exploring distinct environments. While leaf mimicry is highly specific to Boquila, coordination of root-shoot growth is shared across most plants. For both examples, we capture underlying computational principles and identify problems fitting these frameworks that are currently unaddressed by AI. Finally, we outline preliminary task formulations and discuss how these formulations may be applied to non-plant problems.

Large non-uniform point sets make direct attention-based surrogate modeling costly for ship hydrodynamics. We introduce APPSolver, a point-wise flow-prediction framework built around Adaptive Patch Partitioning (APP), a deterministic quadtree representation for fixed two-dimensional horizontal slices extracted from ship CFD simulations. APP assigns finer patches near the hull and coarser patches farther away, downsamples patch contents, and recovers predictions to the full reference point set. Under a corrected protocol that constructs natural $(t,t+1)$ pairs before splitting, reuses training-set normalization statistics, and reports three model seeds, learned tokenizers are more accurate than APP-Transformer, and a persistence baseline has lower one-step MAE on all three ShipBench hulls. The supported benefit of APP is therefore computational rather than universal predictive superiority: on a representative DTC input, APP-Transformer requires 1.815 GFLOPs and 1.309 ms per model forward, while a matched ablation shows that adaptive partitioning reduces MAE by 16.4-24.9% relative to a uniform partition augmented with learned slicing. Condition encoders provide setting-dependent gains in leave-one-hull-out evaluation, but the current absolute next-state objective does not establish accurate long-horizon dynamics. These results characterize APP as a compact spatial representation with an explicit accuracy–efficiency trade-off. Code is available at https://github.com/wenhuahuo/APPSolver .

Large Language Models (LLMs) still exhibit limited capability in following complex instructions. While existing approaches often rely on preference learning to enhance this ability, they typically overlook the relationships between the permissible response spaces of different instructions, which restricts a model to align with subtle and diverse constraint variations. To address this, we propose Cross-Relational Preference Learning (CRPL), a novel framework for constructing preference data that explicitly models inter-instruction relationships through two key techniques: Cross-Relationship Perturbation and Cross-Region Pair Sampling. This enables the generation of more diverse preference data that captures a wide spectrum of constraint variations. Additionally, we introduce an atomic constraint-based verification mechanism to rigorously assess response satisfaction, ensuring high-quality preference pair construction. Extensive experiments across multiple preference learning methods (e.g., DPO, KTO), LLM backbones and four instruction-following benchmarks demonstrate that our approach achieves substantial improvements over prior baselines and exhibits strong generalization.

Background: Patient details and acquisition metadata are important for clinical decisions, image quality control, and automated research pipelines, but may be missing or unreliable in imaging archives. Purpose: To develop and evaluate a fast open-source model that predicts patient and acquisition characteristics directly from CT and MR images. Materials and Methods: Separate 3D ResNet-10 ensembles for CT and MR were trained on 57,291 and 43,200 clinical examinations acquired from 2011 to 2025. Both predicted weight, height, age, sex, contrast presence, vertebral coverage, and image noise. The CT model additionally predicted scanner manufacturer, tube voltage, tube current, convolution kernel, and post-injection time; the MR model predicted sequence class. Performance was evaluated on internal CT (n=501) and MR (n=636) test sets and an external CT dataset (n=54). Results: Internal CT MAEs were 3.90 kg, 3.68 cm, and 4.42 years for weight, height, and age, with sex F1=0.990; corresponding MR results were 4.34 kg, 4.62 cm, 7.13 years, and F1=0.970. The CNN outperformed a segmentation-derived XGBoost baseline for all four core targets in both modalities (adjusted P<=.042). F1 scores were 0.963 for CT contrast, 0.953 for MR sequence, and 0.823 for MR contrast. External CT MAEs were 4.45 kg, 4.05 cm, and 5.17 years, with sex F1=0.971. CPU inference required 20 seconds for CT and 12 seconds for MR. Conclusion: One 3D multitask model per modality can rapidly recover patient and acquisition characteristics from heterogeneous CT and MR examinations. Models are available in TotalSegmentator: https://github.com/wasserth/TotalSegmentator

While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user queries implicitly rely on domain-specific knowledge, such as business logic, data conventions, and analytical practices, that is neither captured by the schema nor explicitly stated in the natural language question. Historical SQL query logs offer a valuable source of such knowledge, yet existing benchmarks do not adequately support evaluation of history-driven approaches. To address this gap, we introduce BIRD-History, a benchmark consisting of 1,393 tasks across 11 databases, designed to evaluate text-to-SQL systems' ability to ground underspecified natural language questions using historical SQL scripts. Each task is annotated with ground-truth labels specifying which historical queries contain relevant knowledge and which SQL clauses encode it, enabling systematic evaluation of both retrieval effectiveness and knowledge utilization. Alongside the benchmark, we propose a plug-in retriever that extracts five types of external knowledge from historical SQL scripts, then retrieves and reranks relevant fragments for query generation. The retriever integrates seamlessly into existing few-shot text-to-SQL pipelines without requiring prompt modifications. Experiments demonstrate consistent improvements across four text-to-SQL systems, highlighting the value of leveraging historical query logs for handling underspecified queries. Dataset and code are open-sourced on https://github.com/zjuidg/BIRD-History.

Positive psychology dialogue aims to support emotional distress and positive resource building, requiring models to produce not only empathetic replies but also coherent progression through a multi-turn support process. Existing resources often reduce supervision to turn-level strategies or holistic preference labels, leaving process position, support function, and local repair targets implicit. We introduce StageWell, a process-aligned Chinese corpus for positive psychology dialogue, together with HQS, a structured protocol for data construction and evaluation. StageWell organizes support into a six-stage support process and uses a multi-agent whole-dialogue rewriting workflow to construct 12,445 SFT instances, 1,849 DPO preference pairs, and a GroundTruth subset of 120 expert-revised dialogues and 977 QA pairs. Guided by HQS, DPO pairs are built as process-localized repairs: flawed model outputs are used as rejected responses, and targeted rewrites under the same context and stage constraint are used as chosen responses. Across four 9B-14B open-source LLMs, this supervision yields robust gains in process control, response quality, and safety. Averaged across models, BERTScore improves by 0.037, Q-Overall increases by 1.32 points, S-exact increases by 0.236, and the H-critical rate decreases by 0.167. These results highlight the value of modeling supportive dialogue as a structured multi-turn support process rather than as single-turn response generation.

This work introduces Semantically-Guided Exploration (SGE), a modular exploration framework for ground vehicles that integrates pixel-level semantic segmentation into sampling-based waypoint selection and receding-horizon route optimization. Unlike conventional geometric exploration methods, SGE evaluates candidate exploration goals directly in the image space using a semantic-aware utility function that accounts for terrain traversability, obstacle proximity, objects of interest, and depth-based exploration reward. Sampled waypoints are projected into 3D and ordered through a real-time Traveling Salesman Problem (TSP) formulation, enabling receding-horizon goal selection. To address real-world navigation uncertainty, the framework introduces mechanisms, including temporary taboo regions to handle navigation failures and a graph-based relocation strategy for efficient backtracking across explored areas. We evaluate SGE in standardized simulation benchmarks against state-of-the-art exploration planners and demonstrate competitive performance in volumetric coverage, while enabling semantic task biasing that cannot be achieved by purely geometric methods. The framework is further validated through real-world experiments using multiple robotic platforms in indoor campus buildings and in limestone and coal mines. Results show consistent performance and adaptability across platforms and domains.

CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embeddings and global pooling fail to encode relational structure such as part-whole and parent-child relations. Hyperbolic VLMs address this gap with entailment-based objectives, and text-conditioned variants improve fine-grained alignment through sentence- and phrase-level queries. However, these two lines of work remain separate: hyperbolic VLMs use static image and region features, while query-conditioned methods lack hierarchical geometric structure. We present Hyper3-CLIP, a hierarchy-conditioned hyperbolic VLM that combines global, local, and global-local contrastive learning with query-conditioned visual pooling. To train the model, we construct lightweight query hierarchies from text, comprising full captions, sentence fragments, localized part descriptions, and extracted phrases. Each query conditions the pooling of visual patches, and the resulting representations support image-text, whole-part, and parent-child entailment losses. Query-conditioned pooling is active only during training. Hyper3-CLIP improves R@5 and R@10 retrieval on COCO and Flickr, as well as multi-label classification on VOC and COCO, while remaining competitive on hierarchy metrics. We also audit zero-shot prompt sensitivity under fixed prompt regimes and study the effect of the localized GRIT part budget used during training. Code is available at https://github.com/Hyper3Labs/hyper3-clip.

Classic Formal Concept Analysis (FCA) primarily focuses on the positive relationships between objects and attributes and does not have mechanisms for handling negation.To overcome this limitation, we introduce three types of negation concepts (contradictory negation, opposite negation, intermediary negation) into FCA.Based on the set SCOI and logic LCOI+PLCOI with these three types negation, we define formal context, Galois connection operators, formal concept and concept lattice with three types of negation,this leads to the proposal of a FCACOI: Formal Concept Analysis with contradictory negation, opposite negation and intermediary negation.For the reasoning in FCACOI, this paper focuses on attribute implication reasoning. Based on the logic LCOI+PLCOI and its semantics, we introduce the notion of ICOI-entailment as the semantic implication for attribute implication reasoning in FCACOI. Through ICOI-entailment, a connection is established between attribute implication reasoning in FCACOI and inference in the logic LCOI+PLCOI, it indicate that formally proven inference rules (theorems) in LCOI+PLCOI are valid in the attribute implication reasoning of FCACOI, LCOI+PLCOI provides a logical foundation for attribute implication reasoning in FCACOI. To illustrate the capability of attribute implication reasoning in FCACOI, we discuss its application in a concrete example. Moreover, we explore attribute reduction of the formal context in FCACOI, propose two research frameworks for attribute reduction from different perspectives, and compare their characteristics.We believe that, based on richer logic and semantics, FCACOI elevates FCA from a theory that describes affirmations to one that can describe affirmations and its contradiction(either this or that), opposition(extreme negation) and intermediary (transitional states between oppositions).