Papers

Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorrect behavioral targets; when the same trajectory writes both the patch and the test, their errors can agree and create false confidence. We introduce ExecCritic, combining a test–verify–revise scaffold with a role-specific reinforcement learning recipe for training agents within it. The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests. Both roles use Qwen-3.5-35B-A3B as the backbone and are trained separately. In Learn to Test, the Test agent learns to produce behaviorally valid tests that distinguish correct from incorrect patches. In Test to Improve, the Repair agent learns both direct task resolution and feedback-guided revision. On SWE-bench Verified, test quality determines whether feedback helps: holding the base Repair agent fixed, tests from the base Test agent reduce resolved rate from a no-test baseline of 61.2% to 57.3%, whereas tests from GPT-5.6-sol raise it to 65.3%. Role-specific post-training raises the Qwen Test agent's Base-to-Gold success from 22.2% to 62.2%; composing the two post-trained Qwen agents reaches 72.6%, an 11.4-point gain over the original no-test baseline without stronger-model or Oracle feedback at evaluation time. Code is publicly available at https://github.com/MSR-Orchard/execcritic.

An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the one-hidden-layer ReLU model of Awasthi et al. (COLT 2024). For width $s$, at most $k$ active units per input, and effective weight and bias bounds $W,B$, every size-$m$ sample in the class's fixed radius-$R$ input domain satisfies $\mathcal{R}(S)\le CWR\min\{k,\sqrt{sk/m}\log^{3/2}(2m)\}+kB/\sqrt m$. A support-preserving cover and a single normalized chaining argument remove the previous explicit dimension factor, up to logarithms. Lower bounds on appropriate i.i.d. marginals match up to those logarithms, showing how changing active units across inputs retains a width dependence. The input domain matters: zero-bias networks sparse on the entire ball have at most $2k$ nonzero units and complexity $O(kWR/\sqrt m)$, whereas bias bounds comparable to $WR$ restore the worst-case rate on that same domain in only logarithmic dimension. A spherical-cap construction proves the latter claim without assuming sparsity merely on the sampling support. For a specified normalized bounded loss and biases comparable to $WR$, we also obtain agnostic minimax excess-risk bounds of order $\min\{1,\sqrt{s/(km)}\}$ up to logarithms.

Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes' rule. Using this connection, we present a generalization of Amari's Bayesian duality and discuss its relevance for modern artificial intelligence.

Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representation contain? We use canonical color as a controlled test case to ask whether vision encoders make canonical-color information linearly accessible, even when color is removed from the input image. We construct a dataset of objects with canonical colors, and probe vision encoders for both color and object identity using color and grayscale images. We find that canonical color remains decodable from grayscale images, and is tied to predicted object identity, indicating a conceptual link. Extending this analysis to full VLMs, we find that VLM post-training can have a surprisingly large effect on color decodability in the vision encoder. Overall, canonical color provides a usefully controllable lens for tracing object-level conceptual semantic information in vision encoders and VLMs.

Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods distill pretrained bidirectional video diffusion models into causal AR students through Distribution Matching Distillation (DMD), but the generated videos often suffer from over-saturation and over-smoothing issues, resulting in limited visual quality and realism. The key contributing factor is the mode-seeking behavior of the reverse KL objective in DMD, which can cause the student distribution to collapse onto only a few modes of the teacher distribution. To address this, we propose Mask Forcing, a Dual-Noise Masking Rollout strategy that perturbs the AR student self-rollout to mitigate mode collapse induced by reverse-KL mode seeking. The core idea is to inject cleaner signals into noisy rollout inputs via random masks along spatial and temporal axes during the self-rollout process of AR diffusion distillation. Such perturbations encourage the student rollouts to explore more regions of the teacher distribution, allowing DMD to provide learning signals beyond the modes already covered by the student. Moreover, the cleaner tokens act as denoising guidance for other noisier tokens, improving the intermediate rollout predictions and reducing error accumulation. Extensive experiments demonstrate that our method improves multiple AR video diffusion distillation methods with higher visual quality efficiently, without incorporating real video data or additional post-training stages.

Dexterous manipulation involves contact-rich and fine-grained interactions with the physical world, posing significant challenges for existing vision-language-action (VLA) models due to severe visual occlusions and complex contact dynamics. While recent works have incorporated tactile sensing into robotic manipulation, most approaches still rely on homogeneous multimodal fusion, lacking adaptive tactile integration and explicit modeling of physical dynamics. In this work, we present DeCAL, a physically-grounded dexterous vision-language-action model that unifies understanding, imagination and action generation for contact-rich dexterous manipulation. Built upon a Mixture-of-Transformers (MoT) architecture, DeCAL leverages specialized experts for each capability while enabling efficient information flow among them. To effectively leverage tactile information, we introduce Adaptive Visuo-Tactile Fusion that dynamically regulates tactile interactions via a contact-aware gating strategy. Furthermore, we propose Visuo-Tactile Latent Co-Imagination to jointly model visual and tactile dynamics, equipping the policy with implicit physical world knowledge. Experimental results show that DeCAL consistently achieves state-of-the-art performance across all tasks, attaining a 71% average success rate and an 83.4% progress success rate, while also demonstrating strong generalization to unseen scenarios. The website is available at https://aureleopku.github.io/DeCAL.

Normalization renders large parts of neural networks effectively scale invariant, inducing a hidden feedback loop in which learning-rate schedules and weight decay interact through the parameter norm to control the effective step taken by the optimizer. We show that this interaction is governed by an exact discrete-time law: a single scalar quantity captures all schedule and decay forcing, while norm growth induces an opposing geometric self-quenching effect. This yields a sharp boundary that cleanly separates contraction- and expansion-dominated effective learning rate regimes. To understand the underlying mechanism, we provide exact analysis of a fully solved normalized regression model where the dynamics reduce to two dimensions and show that the balance point is intrinsically unstable, implying that constant learning rate with weight decay cannot stably maintain an interior equilibrium and instead produces recurrent behavior driven by discrete-time Jacobian structure. We further extend this perspective across optimizers through unified homogeneous-optimizer framework that reveals a structural dichotomy in self-quenching strength, providing a first-principles explanation for why adaptive methods exhibit systematically weaker stabilization under normalization. Across dynamical systems and neural networks (MLP, CNN, GPT2 / MNIST, CIFAR, wikiText, OpenWebText), the predicted law holds with high precision and enables direct control of training via the identified scalar, with performance peaking sharply at the predicted boundary. Together, these results isolate a single governing quantity for scale-invariant optimization, providing a precise and actionable lens on training dynamics, optimizer behavior, and schedule design in modern deep learning. Code is available in https://github.com/shasanamin/normalized-optimization-dynamics.

Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories featuring negative downstream utility through cooperative attribution and selectively suppresses them from agent execution. MeClear combines Leave One Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, effectively resolving redundant conflict masking where single removal evaluations fail. Utilizing attribution rankings, MeClear executes a query scoped minimal clearance strategy over a nested filtration, verifying task recovery on the cleared context without permanently altering the persistent memory bank. Comprehensive experimental evaluations across ten long dialogue memory pools demonstrate that MeClear achieves a target recall of 85.9% and an overall task recovery rate of 82.3%, representing a 25.5 percentage point improvement over Leave One Out (LOO) baselines.

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing to understand what models learn and ensure safe alignment. Mechanistic interpretability tools are essential to bridge this gap, among which Sparse Autoencoders (SAEs) serve as a cornerstone by isolating interpretable features for model inspection and steering. In this paper, we introduce SAEScientist-Bench to evaluate whether AI agents can act as scientists utilizing SAE tools for autonomous mechanistic discovery. Given a target concept, an agent designs contrastive probes and navigates a Gemma Scope dictionary of 131K+ features in Gemma-2-9B-IT to discover the optimal feature, evaluated against curated expert reference features anchored on Neuronpedia across activation rank, concept selectivity on contrastive texts, and causal steering. Across 10 agent configurations and 20 tasks, frontier agents demonstrate genuine discovery capabilities and lead different evaluation dimensions, but remain well behind the expert baseline, approaching expert levels on separating target concepts from contrastive controls while lagging substantially in causal generation steering. Further analysis reveals that although agents can design contrasts to rule out spurious candidates, they frequently misinterpret experimental measurements. These results establish experimental model understanding as a measurable capability for closed-loop autonomous AI R&D. Our code is available at https://github.com/Trae1ounG/SAEScientist.

These days we are witnessing many mobile applications based on the recommended systems, which have become a great technology which is been used by the various mobile applications according to the situation. Recommendation provided by the mobile application is a key element for the person who is traveling to several places. For any tourist information application contextual information is much needed to guide the user on his interests this can be achieved by the Context-aware computing. Which provides the user most interactive system with the suggestions provided by it based on the input from the user in a certain location, here context includes the user's mental, social, physical environments. To achieve this contextual information, we will design and implement the context-aware user interface based on the user for which we have to study the user and design a rich user interface. The final outcome for which users have the satisfaction when using context-aware functionality will be much better than non-context-aware application.

Large linear programs can exceed the memory of a single compute node. Although first-order methods replace sparse factorizations with GPU-suited matrix-vector products, other solver phases can reintroduce a single-node memory limit. We present SHARDLP, a distributed GPU LP solver that keeps the matrix and primal-dual state partitioned from sharded input through solution output. On the Google PDLP benchmark, SHARDLP solves ten of eleven instances, compared with eight in the published CPU PDLP study. On the largest benchmark, eight H200 GPUs solve a 1.185-billion-variable, 6.338-billion-nonzero LP in 9.9 minutes; the published CPU experiment reports 21.06 hours on different hardware. Beyond this benchmark, separately checked multi-node solves reach up to 13.604 billion variables and 40.807 billion nonzeros, while validated executions span up to 76 GPUs across 29 compute nodes. For column-partitioned solves, support-aware communication skips GPUs that store no coefficients for a row; on an LP with 2.76 billion nonzeros, it cuts modelled communication by 92.97% and improves solver time by 1.27x-1.52x. The code for SHARDLP is available at https://github.com/ArnaudDeza/ShardLP.

Curriculum learning is governed by several coupled design choices—how difficulty is defined, how examples are ordered, how much exposure each level receives, and how quickly training moves across levels—making it hard to isolate what actually helps. We present Wasserstein curriculum paths, a simple transport-based framework that decouples these factors by representing curricula as trajectories of training distributions over discrete difficulty levels. Across a calibrated synthetic suite with 12 tasks and 33 difficulty axes, we use this framework to isolate the effects of ordering, matched exposure, endpoint smoothness, and pacing under fixed training budgets. We find that curriculum effects are strongly context-dependent: no single strategy dominates across tasks, difficulty axes, and budgets, and curricula mainly change where a fixed budget is spent most effectively. Within this framework, easy-to-hard ordering improves hard-level performance relative to exposure-matched static sampling, showing that the benefit is not explained by cumulative exposure alone. We further show that endpoint smoothness and pacing substantially affect where along the difficulty spectrum a curriculum is effective. Finally, we show that the same transport view naturally supports extensions to learned pacing through geometry and to structured difficulty spaces beyond one-dimensional orderings.

FP8 Ozaki II emulates FP64 matrix multiplication by tensor-core products over a CRT residue system; converting the operands into residue planes (the deconstruction term in the Tensor-Memory Equilibrium model of the companion paper "FP8 is All You Need, Part 1") costs integer-pipe and memory resources before tensor instructions issue. This paper engineers that path; every result is a model projection pending measurement. First, a deconstruction-aware model: on the NVIDIA Rubin GPU the emulated rate reaches the arithmetic roof $P_{\rm FP8}/(3r+1)$ ($\approx 473$ TFLOPS at $r=12$) only within one thread-block cluster; larger outputs are re-split on the fly and held at a floor of $\approx 235$ TFLOPS (half the roof, a ratio of three design integers, not a fit), while real solvers' tall/skinny shapes stay near the crossover, $1.6$-$1.9\times$ over simple deconstruction today. Second, the method: convert-once residue workspaces, an exact two-limb constant-reduction GEMM on integer tensor pipes (or pure-SIMT dp4a), and conversion pipelined behind the MMAs, moving the crossover from $\approx 1211$ to $\approx 480$-$730$. Third, modulus co-design: all-byte and hybrid sets, two supply bounds and a carry-corrected E4M3 split of tail moduli. Fourth and central, the closed-form floor names its hardware escape, and the prize is Rubin's: a stream-side residue-conversion mode on the asynchronous copy path (Option C), a narrow fixed-function block sized as a bill of materials, takes plane formation off the arithmetic pipes and lifts the floor from 235 TFLOPS to the full 473-TFLOPS roof at unchanged cluster reach, about doubling HPL-class FP64 per Rubin GPU, and unbinds conversion-bound sparse kernels. The NVIDIA GB300 GPU, whose 135-TFLOPS roof sits at its own floor, gains little; floor and remedy are Rubin-scale. Application traces ground the analysis; constants are script-checked.

Combining search with function approximation has driven major advances in game-playing programs, making self-play algorithms more competitive than ever. Still, the computational overhead of the most popular methods, based on Monte Carlo Tree Search (MCTS), can be substantial. In this work, we investigate whether simpler methods remain competitive in non-trivial, moderately sized games such as Connect Four, Hex(7x7) and synthetic games. We train a minimal self-play implementation of Approximate Value Iteration (AVI) and use ground-truth oracles for exact evaluation. Contrary to expectations, our results demonstrate the surprising effectiveness of AVI: it learns more accurate value functions than those learned by AlphaZero, while its one-step-lookahead greedy policies remain competitive with MCTS-based policies at substantially lower training and inference costs. Preliminary experiments on Othello and Go(9x9) show that AVI trains stably on larger games and learns effective value functions. These findings suggest that the success of MCTS-based methods may have eclipsed simpler approaches that have become increasingly practical with modern deep-learning tools.

We show that one-way one-round quantum-LOCAL algorithms cannot $4$-color directed cycles with high probability. This is the first lower bound in the high-probability quantum LOCAL setting that goes beyond the non-signaling and bounded-dependence models, exploiting the structure of distributed quantum algorithms. Our proof establishes a bidirectional connection between distributed quantum computing and extremal combinatorics. We obtain our lower bound by proving a Mantel-type stability theorem for weighted matrix spaces.

Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations typically use short, prespecified conversations and may therefore miss failures that emerge under sustained, adaptive disagreement. We introduce SPINE, a benchmark in which an LLM proxy plays a persistent but mistaken user and adaptively challenges a target model for up to 25 turns. We evaluate four commercial models (Claude Sonnet 5, GPT-5.6 Terra, Gemini 3.1 Pro, and DeepSeek V4 Pro) and three Olmo3-7b models on 100 false presuppositions and 100 unethical queries. We define collapse as a target model abandoning the correct position and yielding to user pressure. Our experimental results show that collapse rates increase with conversation length across post-trained models, with the overall rate rising from 0%-57% within 5 turns to 20%-97% within 25 turns depending on model and scenario. These results show that evaluations limited to a few conversational turns underestimate sycophancy and resistance under sustained pressure remains unreliable across current models. By analyzing models with accessible reasoning traces, we surprisingly found that the correct position often remains represented in the trace in 50%-89% of analyzed collapse turns, suggesting that the model chooses to please a user and sycophancy is not due to ignorance or the correct knowledge being overridden. Ablations show that the SPINE protocol substantially increases the sycophantic collapse rate compared to pre-generated scripts. Among all tactics, emotional appeals are most associated with inducing LLM sycophantic behavior, with position weakening in 44.3% of turns using this tactic. Code, data, and transcripts will be released upon publication.

As Large Language Model (LLM) agents increasingly automate offensive operations across the cyber kill chain, their efficacy in complex local post-exploitation tasks remains inadequately quantified. Among these, Linux privilege escalation is a key step between initial access and full system compromise. However, existing evaluations for this task are limited by small sample sizes (fewer than 15 scenarios), lacking the scale to compare model capabilities under executable verification. To address this, we present PrivEscalate, a large-scale benchmark for Linux privilege escalation, comprising 531 Dockerized scenarios spanning 14 sub-categories. We additionally derive 329 parameterized variants to measure sensitivity to environmental distractors. Evaluating six LLMs across three agent architectures reveals: (i) model capability is heterogeneous across vulnerability classes, with no single model dominating across the high-prevalence classes, motivating multi-dimensional risk assessments; (ii) LLM successes are sensitive to environmental perturbation, so configuration rotation can disrupt some exploit attempts but does not eliminate the measured risk; and (iii) agent architectures can materially change success rates and reorder model rankings, though the magnitude is model-dependent. Leveraging these insights, we develop PrivEscAgent, a domain-specialized wrapper that augments a generic ReAct agent with deterministic enumeration, category matching, and step planning. PrivEscAgent improves over prior Linux privilege-escalation agent baselines without underlying LLM modifications. We release PrivEscalate as an open-source, Dockerized measurement instrument supporting LLM agent evaluation, defensive tool validation, and red-team training.

Large Language Models (LLMs) often exhibit "Attention Sink" (AS) and the accompanying "Massive Activations" (MAs) at the initial position of a sequence. These phenomena frequently co-occur, and MAs can pose challenges for low-bit quantization. In this study, we analyze the factors underlying AS and MAs that emerge at the initial position regardless of the token occupying it. Our experiments suggest that self-concentration of attention, resulting from the causal mask, and the subsequent Value-non-mixing in attention outputs contribute to AS and MAs. These findings provide new empirical evidence on the internal dynamics of LLMs, offering insights that may inform future quantization strategies and advance our understanding of the internal mechanisms of attention layers.

Open vocabulary 3D semantic segmentation methods typically lift CLIP features into 3D. This embeds points in a joint vision-language space known to behave like a bag-of-words on compositional tasks. Furthermore, even annotation free variants often require a large 3D training corpus and a dedicated 3D encoder per domain. Instead we use a vision-language model purely as a translator. It produces structured, entity-level descriptions of each posed image. These descriptions are grounded, projected, and aggregated directly in a general-purpose, language-only embedding space, with no 3D training corpus or encoder required. On ScanNet++, our pipeline is competitive with strong annotation free baselines trained on ScanNet. On a 5-building cultural heritage benchmark, raw scores initially favor a CLIP-based variant, but a single systematic vocabulary correction reverses this ranking. An effect confirmed by a second, independent correction on a different class, indicating that language-space embeddings track physical content more faithfully. This fidelity extends to genuinely out-of-vocabulary (OOV) objects on ScanNet++ proving that language-space embeddings separate presence from absence objects far more sharply than CLIP-based embeddings do. GoDeep also localize these OOV objects within the scene, all without any 2D-3D annotation. Because every representation remains discrete text, predictions are also explainable at the point level. Finally, exploiting both a heuristic weighting, that favors precise over merely frequent observations and GoDeep's explainability property, we propose an aggregation strategy, as a proof of concept, that favors finer elements localization.

Mid-training, the stage between pre-training and alignment, is where a model's per-domain data composition is typically set by data availability rather than principled design. We ask what that decision buys, and whether a later alignment pass can undo it. In a controlled logical-reasoning setting (Qwen3-8B-Base, with a 4B replication; five semantically rule-disjoint KOR-Bench domains) we train 30 allocations spanning the five-domain simplex, 24 sweep configurations plus six withheld from the fit, at five seeds each. Three findings emerge. First, every domain has an interior coverage optimum: the moderate band ($10\%$-$40\%$) is best for all five domains, and a calibrated permutation test for quadratic interiority gives $P\approx0.010$; the fitted mid-training-only curves, with 8B peaks between $9.9\%$ and $35.1\%$, reproduce for curve shape but not peak location. Second, the gaps survive a fixed-budget alignment pass: compensatory SFT raises 116/120 cells (mean $+4.32\%$) yet bridges $0/240$ pairs at a $5\%$ threshold and $30/240$ at a $10\%$ ratio, an equal-budget uniform control behaves almost identically, and a permutation null would bridge $13.8\pm3.3$ and $77.9\pm8.5$ pairs ($P<0.001$). Third, zero coverage collapses mid-training-only accuracy, though a FineWeb-Edu-only control shows the collapse is commingled with generic drift. An exploratory $\theta^*$ allocation attains the largest full-pipeline gain ($+4.36\%$ vs. $+0.80\%$/$+0.64\%$\,pp) but is marginal under Welch test.

As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revisions. We study this as Actionable Peer-review Generation and decompose it into two subtasks: diagnostic claim generation and revision suggestion generation. We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans. Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback. From real review-rebuttal threads on OpenReview, we construct ActReview-40K by aligning reviewer weaknesses with author responses and grounding the resulting feedback in localized paper evidence. We post-train Qwen3-8B-Base with multi-task supervised fine-tuning followed by GRPO using candidate-aware, weakness-specific rubric rewards. We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness. Experiments show that ActReview outperforms prior specialized review-generation models on actionability and grounding while remaining competitive with strong prompt-based LLMs. Human evaluation confirms improved revision usefulness while revealing a remaining gap in technical accuracy, and additional analyses support generalization to held-out papers and robustness across independent judges.

In reinforcement learning with verifiable rewards (RLVR) trained with group relative policy optimization (GRPO), the KL-free reward-advantage term studied here depends on within-group reward variation. If all rollouts in a group are correct or all are wrong, their group-relative advantages are identically zero; these zero-advantage silent groups provide no reward-advantage gradient, yet uniform sampling spends 39% of a run's rollouts on them. History-based prompt selection must first spend target-policy rollouts to estimate difficulty, creating a cold start with rollout waste; ThinkPrior instead uses an external anchor in one offline pass to construct a zero-rollout difficulty prior before the first target-policy rollout. The verifier-scored anchor pass rate supplies an external-anchor initialization for a Beta posterior; ThinkPrior selects by expected learnability and then updates from training outcomes, changing neither the loss nor the optimizer. On Qwen2.5-Math-7B across sixteen seeds, ThinkPrior more than halves early silent groups and cuts wasted rollouts through step 30 by nearly a fifth, while we detect no difference in final accuracy. On this 250-prompt pool the fixed-budget result is a reallocation rather than a net saving. The measured ThinkPrior+DAPO composition reduces generated rollouts by 10.6% while both arms retain the same 3840-rollout update budget. The prior requires no target-policy rollout before the first selection, but the posterior thereafter uses target-policy outcomes.

Sampling-Based Model-Predictive Control (MPC) algorithms are a flexible class of controllers used for navigation on a wide range of robotic systems. Historically, such approaches have lacked hard safety guarantees, a shortcoming which we remedy in this work by computing guaranteed reachable-set overapproximations online with a fast, interval-based pipeline. We show that our method achieves similar performance to a state-of-the-art reachability-based planner without the need for the expensive pre-computation step, and can be scaled to systems that are infeasible using existing approaches. Finally, we demonstrate that our technique reduces safety violations by over 99% in a racing simulation and successfully controls a model racecar on real hardware experiments without crashes.

High-quality tool-use data is critical for training language models to interact effectively with external tools. However, existing synthetic approaches typically follow a generate-then-filter paradigm with static post-hoc verification, often yielding inefficient data with imbalanced feature distributions. We propose ToolLoop, a closed-loop framework that decomposes synthesis into three progressive stages: (1) sampling function name combinations as ground truth; (2) backward derivation of user queries; and (3) forward derivation of tool calls. At each stage, dynamic self-feedback iteratively guides the model toward high-quality generation, realizing a transition from generate-then-filter to generate-verify-refine. On the Berkeley Function Calling Leaderboard (BFCL), a 4B parameter model trained with our 11K synthetic examples achieves 86.40% accuracy in non-reasoning mode, while an Isolate variant that removes BFCL-overlapping candidate functions still reaches 86.07%. Cross-benchmark evaluation on ACEBench further demonstrates strong generalization, with 72.1% overall accuracy using only 18.3% of baseline training data.

Clinical AI evaluation should encompass diagnosis and management after adaptive information gathering. We compared Doctorina, eight physicians and four standalone frontier language models in 150 synthetic Polish-language primary-care consultations. Doctorina achieved 82.0% Top-1 concordance versus 57.0% for physicians (difference, 25.0 percentage points; 95% confidence interval, 17.7-32.7) and 97.3% versus 85.0% primary-or-reference-differential concordance. Across 149 case pairs, normalized workup and treatment scores were 89.4 versus 66.9 and 83.7 versus 61.2. Doctorina had the highest diagnostic point estimates among all six groups; Kimi K3 ranked next, while Claude Opus 5 led the closely spaced management estimates of Opus, Doctorina and Kimi. A second Doctorina execution reproduced the advantages over physicians across all outcomes. Doctorina's advantage over physicians therefore extended from primary-diagnosis selection to higher-rated diagnostic workup and initial treatment after adaptive consultation.

Autonomous 3D active mapping requires a space robot to choose where to sense while building the geometry needed for navigation. Learned occupancy completion extends spatial context beyond the current field of view, but one predicted map often serves two planning roles: it scores expected surface gain and constrains collision-free motion. Unsupported occupancy can therefore distort both where the robot looks and where it believes it can travel. We study this coupled interface in a controlled closed-loop benchmark by holding the active-mapping system fixed and varying only its planner-facing occupancy across observation-only, learned, oracle-corrected, and ground-truth conditions. Improving occupancy accuracy does not monotonically improve closed-loop coverage: across 25 starts, planning with ground-truth occupancy reaches 70% of the learned baseline's final coverage 12.7 steps earlier on average, while increasing final coverage by only 0.031. Guided by this diagnosis, we introduce an observation-gated filter that retains completion in insufficiently observed regions and suppresses predictions only after repeated frustum exposure without nearby RGB-D support. The filter improves both targeted failure-prone starts without retraining or ground truth. These results motivate online revision of planner-facing geometry during autonomous intervals between communication windows. The current study assumes benchmark RGB-D observations and sufficiently accurate pose estimates; planetary sensing conditions and accumulated localization drift remain to be evaluated.

Maritime target tracking over large distances often requires multi-agent teams without centralized coordination, and intermittent communication. Each agent must maintain an independent estimate that can take advantage of opportunistic communications availability when possible. This can lead to overly confident local estimates in the absence of external data. In this work, we propose an augmentation to a classical particle filter implementation that accounts for this potential source of error by forcing particles to spread strategically in the absence of informative updates from other sensor nodes. We demonstrate our method using Unmanned Surface Vessels (USVs) on a lake, and show that our augmentations do not deteriorate nominal performance, and provide an advantage in some specific edge cases.

Consider a permutation of $[n]$ whose values arrive one at a time. We resolve two questions about the space needed to decide natural properties of such input: First, computing the parity of the permutation requires $\Theta(n)$ bits, even with randomization and constant error, and a constant number of passes. Second, every permutation pattern of length three can be detected deterministically in one pass using $O(\log n)$ bits. Together with the 2026 lower bounds of Berendsohn, this completes the classification of fixed permutation patterns; The optimal space complexity is $\Theta(\log n)$ for monotone patterns and patterns of length at most three, and $\Theta(n)$ for every other pattern. As a consequence, we observe that we can verify BST traversals in streaming with logarithmic memory.

We present a real-world case study of multi-task learning (MTL) for temporal process modeling from limited data with temporally sparse labels. Specifically, we investigate multi-task learning for the important agricultural problem of predicting grape cold hardiness, which is the temperature at which lethal freezing occurs. Cold hardiness changes in response to weather and is difficult to measure directly in the field. Thus, growers rely on predictions to decide when to apply costly frost mitigation measures. We apply recurrent neural networks (RNNs) for daily cold-hardiness prediction from time series weather data. A major challenge is that the cold hardiness response varies across plant cultivars and ground-truth data for each cultivar is temporally sparse and limited. To address this challenge, we investigate multi-task learning (MTL) approaches for combining data, where different tasks correspond to different cultivars. We develop a variety of MTL architectures and evaluate them in both MTL and transfer learning settings. Our results show significant differences between architectures and that certain architectures are able to consistently outperform single-task learning and state-of-the-art scientific models. Additionally, we show similar results for the qualitatively different, but related, task of budbreak prediction. Further, improved accuracy for budbreak and cold hardiness is achieved by a single MTL model that simultaneously learns both tasks.

This paper presents a cyber-physical system (CPS) for location-independent programming, supervision, training, and teleoperation of a Robot-Assisted Finishing (RAF) system used to post-process metal additive-manufactured (AM) components. A digital twin (DT) built in Unity is delivered to the operator as a WebGL application that supports both desktop and immersive modes through WebXR-compatible devices. Moreover, it exchanges robot state and pose commands with a collaborative robot through a Message Queuing Telemetry Transport (MQTT) broker. The DT enforces kinematic and collision constraints before a pose is released to the physical robot, and augments the virtual component with a color map of the surface topography that supports operator decisions on part repositioning or process termination. The architecture was validated on a specially designed physical RAF system. A steady-state joint synchronization error of 0.12 deg and a mean round-trip latency of 563 ms were measured, which is adequate for supervisory programming and intermittent teleoperation.