Papers

Multi-step revealing can make off-policy evaluation tractable under memoryless logging. With history-dependent logging, state decodability and target-relevant evidence can separate. For every horizon $H\ge3$, we construct two exactly realizable POMDPs with four actions, at most four states per layer, a known logger, and a memoryless target. Action overlap, history coverage, and observation-only revealing remain bounded independently of $H$, yet the target values differ by $1/2$ and the KL divergence between the logged laws is $\Theta(4^{-(H-1)})$, forcing exponential sample complexity. Logger memory makes states distinguishable, while reset erases the model-distinguishing evidence preserved by the target. A separate construction retains this barrier with common, known observation-only revealing operators. Under action and history coverage, we give a finite-class OPE guarantee using common observable value representations that remain valid at every history. The sample bound depends polynomially on their second-moment cost. In the common-operator construction, the same value direction has constant marginal decoding cost but exponential history-conditioned cost. Finally, on a fixed four-action continuum, we derive matching passive and budgeted readout rates. With one known channel and unit read cost, early reads are optimal. With unknown sensor bias, early reads alone remain exponentially costly. Combining them with post-reset calibration gives sample complexity independent of $H$ when both read types receive fixed positive expected budgets per trajectory.

Vision-language-action (VLA) models translate multimodal observations into low-level robot actions. During robot operation, each control period sets an inference deadline, and overruns leave the robot acting on stale observations, reducing task success. Meeting this deadline motivates on-device or nearby edge execution, where a single robot requires batch-1 inference outside the design point of LLM serving systems. Although VLA architectures combine familiar vision-language, autoregressive, and diffusion-style components, their runtime behavior in this batch-1 control setting remains uncharacterized. We characterize four representative VLA models on an edge GPU server and two onboard SoCs, using single-inference profiling and 43,200 closed-loop episodes. Action tensor dimensionality determines whether a stage is memory- or compute-bound, platform balance can shift that bottleneck, and GPU frequency scaling yields a platform-dependent energy-latency sweet spot. In closed-loop operation, overlapping inference with action execution creates an accuracy-speed-energy tradeoff, and no configuration is Pareto-dominant across deployment SLOs. These results guide joint design of VLA model architectures, hardware, and runtime policies.

SQL queries that large language models write from natural language questions can execute successfully yet produce incorrect results, so execution alone does not reveal what to fix. An error taxonomy says why the query is wrong, but not where to look or how to change it. Existing methods can guide SQL correction through feedback, error reports, or generated plans alongside an unmasked query. We introduce TEG(Taxonomy-guided Error Grounding), which turns a supplied diagnosis into a structured correction input for natural language-to-SQL (NL2SQL) correction. Type-specific rules map each error type to construct classes to reconsider and an edit operation to request. TEG masks the selected constructs in the query when applicable and states that operation in an edit instruction. TEG generates candidate corrections from this input, uses execution feedback to guide candidate selection, and repeats the process one annotation at a time for queries with several errors. On NL2SQL-BUGs, TEG reaches 47.3 single-error execution accuracy and 37.0 overall with Qwen2.5-7B-Instruct. Across the model sizes and thinking modes evaluated in the main comparison, TEG outperforms all evaluated baselines on single-error queries, even when the baselines receive the same error-type annotations. With predicted types, TEG stays above direct LLM correction and ErrorLLM on single-error queries.

This work proposes OzII-RescaleBE, a method that enables persistent execution of chained tensor mode products in Ozaki scheme II, keeping the intermediate tensors in residue form. By performing rescaling and base extension directly on the residue representation, it requires conversion to residues only at the beginning of the chain and reconstruction only at the end. An implementation using CuTe DSL and INT8 Tensor Cores is provided for verification and evaluation. The method is compared with per-mode composition of Ozaki scheme~II (GEMMul8-Composed) and a dense Kronecker-product formulation (GEMMul8-KRON), both implemented using the GEMMul8 library. Across three datasets with different input distributions, OzII-RescaleBE achieves normwise relative errors ranging from $2.5\times10^{-16}$ to $2.6\times10^{-15}$ for chain depths $d=3$ through $7$. The corresponding errors range from $10^{-16}$ to $10^{-15}$ for GEMMul8-KRON and from $1\times10^{-16}$ to $3\times10^{-16}$ for GEMMul8-Composed and the FP64 chain. At $d=8$, the errors of OzII-RescaleBE increase to between $7\times10^{-14}$ and $6\times10^{-13}$. For mode sizes $n=8$ to $256$, OzII-RescaleBE achieves throughputs ranging from 1.47 to 4.42\,GDoF/s. Its throughput is within 12\,% of GEMMul8-KRON at $n=8$ and $12$ and exceeds it at larger tested sizes. Compared with GEMMul8-Composed, OzII-RescaleBE achieves $2.1$–$60\times$ the throughput for $n\leq128$, but has 6–12\,% lower throughput at $n=256$. It also uses less device memory than the GEMMul8 baselines in the measured memory comparisons. These results demonstrate that rescaling and base extension enable accurate residue-domain tensor chains while avoiding repeated intermediate conversions to floating point.

Pointwise Mutual Information (PMI) is a core measure of testing word association, and Skip-gram with Negative Sampling (SGNS) is essentially a method that implicitly factorizes a shifted PMI matrix. However, a systematic and well-rounded characterization of finite-sample uncertainty in PMI estimation remains absent and imperative to venture into. We provide a statistical framework for PMI estimation and its connection to SGNS. We prove consistency, asymptotic unbiasedness, and asymptotic normality of the empirical PMI estimator, derive its variance via the Delta method, and, applying stochastic approximation theory, obtain a variance decomposition for SGNS-based PMI estimation that separates data variance from optimization variance. Simulation experiments validate the Delta method approximation. Real-data experiments on the Brown Corpus (d = 100) reveal that SGNS systematically deviates from the theoretical relationship PMI + log K. The empirical relationship shows an attenuated PMI coefficient, an amplified log K effect, and a positive intercept, indicating systematic bias. Word analogy validation confirms the models are effective. The failure to validate the variance decomposition under low-dimensional conditions does not diminish its theoretical value; rather, it identifies the unbiasedness assumption as the key bottleneck and clarifies the gap between asymptotic theory and practice, providing implications for both practice and theory.

As enterprise blockchains become increasingly interconnected, access control must extend beyond the boundaries of a single network. Existing approaches mainly focus on controlling access within one blockchain, while cross-chain interactions involve multiple networks that may follow different access-control policies and administrative rules. In this paper, we propose InterAcct, an end-to-end access-control framework for secure interactions across permissioned blockchain networks. To avoid exposing sensitive internal information, InterAcct converts outgoing requests into a consortium-level representation before they are shared with another network. When a response is returned, the framework securely maps it back to the original requester within the source consortium, preserving confidentiality throughout the interaction. Our experimental results show that InterAcct can enforce end-to-end access control for cross-chain request-response interactions with low additional overhead and can continue to operate effectively as the workload increases.

Domain Generalization (DG) for medical image segmentation is both highly challenging and critically important. However, existing medical DG methods largely overlook the issue of Catastrophic Forgetting (CF): Models often sacrifice their ability to retain source-domain knowledge while pursuing cross-domain robustness. This can directly threaten diagnostic safety in already-deployed clinical scenarios. To address this, we investigate data augmentation strategies and catastrophic forgetting for medical image DG segmentation. First, we propose a structure-guided style diffusion augmentation method. Constrained by anatomical structure consistency in the frequency domain, this method performs cross-domain diffusion on the amplitude spectrum, generating samples with more diverse and broader style coverage to better support domain generalization. Then, we design a collaborative learning network with a dual-branch interactive architecture (CoDG-Net), together with a novel learning bias-guided strategy that adaptively regulates knowledge transfer at both the layer level and the task level, thereby effectively mitigating catastrophic forgetting on the source domain. Experiments and ablation studies on single-source and multi-source medical DG benchmark datasets demonstrate that CoDG-Net not only outperforms existing state-of-the-art methods in target-domain segmentation performance, but also achieves a lower forgetting rate on the source-domain data. The code is available at: https://github.com/wangprocess/CoDG-Net.

Time-series data are often sampled irregularly at high frequencies and exhibit long-range dependencies, which makes long-horizon modelling difficult. Continuous-time models such as neural controlled differential equations (NCDEs) and neural rough differential equations (NRDEs) can handle irregular sampling, but they scale poorly to long sequences. Selective state-space models (SSMs) such as Mamba scale linearly with sequence length, but they provide limited recurrent mixing across hidden dimensions within a single block. We propose LogSig-SSM (Log-Signature Compression for State-Space Models), which first compresses long multivariate time series into a shorter sequence of tokens using multi-scale windowed log-signatures, and then processes these tokens with a selective SSM backbone. LogSig-SSM is scalable and robust to irregular sampling, combining log-signature tokens that capture higher-order cross-channel interactions with a selective SSM that models long-range dependencies. The model also admits a continuous-time interpretation as an NCDE/NRDE-style system driven by a log-signature-based input, in which selectivity induces an input-dependent rescaling of the latent dynamics. Across four benchmarks, namely long-sequence classification on UEA, high-frequency physiological regression on PPG-DaLiA, multivariate weather forecasting, and irregularly sampled clinical prediction on PhysioNet Sepsis, LogSig-SSM outperforms or matches strong SSM and continuous-time baselines while training up to $30\times$ faster and using up to $37\times$ less GPU memory than Mamba on the longest sequences.

The synchronization of large-scale kinetic swarms with digital twin networks can generate substantial signaling overhead when predictable motion is repeatedly reported. To reduce such redundancy, we propose the thermodynamic digital twin (TDT), a physics-guided synchronization framework that combines field-based state extrapolation with event-triggered correction. For a closed domain with vanishing boundary flux, the divergence–entropy relation is used as a physical motivation for identifying structural changes in the reconstructed swarm field. Based on Reynolds decomposition, the hierarchical thermodynamic synchronization (HTS) protocol separates low-dimensional macroscopic drift updates from full-state microscopic corrections. A locally measurable smoothed-particle-hydrodynamics descriptor, combining velocity divergence and acceleration, provides an implementation-oriented early-warning trigger, while a transport-error analysis provides a short-interval rule for limiting silent extrapolation. The same extrapolation mechanism is further used as a predictor-like delay compensator in the closed-loop digital twin. Across the evaluated numerical settings, TDT reduces the generated edge-to-cloud synchronization payload relative to the considered baselines and exhibits a favorable empirical trade-off between tracking error and communication cost. The results also indicate improved delay tolerance in the evaluated control loop.

On-policy self-distillation (OPSD) provides dense token-level supervision without a second model: one network acts as teacher with the reference solution and as student with only the problem. We identify a specific failure mode of this recipe. During training, student token entropy rises past the teacher's and remains elevated, a pattern we call entropy overshoot. We trace it to both sides of distillation. The reference-conditioned teacher is confident along its answer-directed reasoning path, but this confidence transfers poorly to student-generated prefixes, making its supervision overly tied to answer-specific cues rather than reusable reasoning patterns; meanwhile, the forward KL used by OPSD continually diffuses the student's predictive distribution without pulling it back. We introduce E$^2$-OPSD to address both causes. Exemplar-guided teaching replaces the current answer with a retrieved solved neighboring problem, providing transferable reasoning guidance without revealing the destination and better matching student-reachable states. Entropy-aware distillation uses the student-teacher entropy gap to determine the direction and strength of each token's correction. E$^2$-OPSD improves math reasoning by up to 4.3 points in mean@16 over OPSD, while out-of-domain evaluations show gains over the corresponding base models of up to 4.9 points in mean@16 and 5.5 points in pass@8. Despite these gains, E$^2$-OPSD remains simple, requiring no additional forward passes or networks. Code repo: https://github.com/orionfei/E2-OPSD.

Large language models (LLMs) are increasingly used through terminal user interfaces (TUIs), yet task completion alone does not capture how difficult an interface is to understand and operate. Existing human assessments and LLM-generated ratings or reports do not provide repeatable measurements of interaction effort grounded in verified task execution. We propose Agent-as-a-User, an evaluation paradigm that places an LLM agent in the user role. Agent-KLM separates agent-side interpretation and operation costs and relates them structurally to human interaction. TUINaut operationalizes the paradigm by recording interaction trajectories and verifying outcomes with actor-independent oracles. Using TUINaut-Bench, we study 84 tasks across 15 real-world TUIs with six human participants and five observation-evaluator configurations, and evaluate 45 TUIs generated by three leading stacks. Similar aggregate success rates mask differences in which tasks humans and agents complete, whereas interpretation and operation costs follow correlated task rankings, especially for operation. This pattern persists across configurations. Generated TUIs can implement correct functionality while still requiring usability improvements. These results position Agent-as-a-User as a repeatable, execution-grounded paradigm for measuring task-based usability.

A second-order exponential low-regularity integrator is proposed for the incompressible Navier–Stokes equations. The method requires only linear solves and satisfies a discrete energy-decay property. Second-order temporal convergence is established under a uniform $H^4$ solution bound, with an error constant that remains bounded as the viscosity tends to zero. For the Fourier–Galerkin discretization, the optimal spatial convergence rate is established for fixed viscosity. The method can also be extended to conforming finite element methods while retaining the discrete energy-decay structure. Numerical results confirm the convergence orders and robustness with respect to the viscosity.

State-of-the-art ASR systems primarily target native adult speech, leading to substantial performance gaps for children, adolescents, and L2 speakers. We introduce AraYoungVoices, a 151.72-hour Arabic read-speech corpus from 286 speakers aged 7–18, comprising AraKids (7–12) and AraTeens (13–18). The corpus includes 146 native Arabic (L1) and 140 second-language (L2) speakers, with native speakers spanning Egyptian, Gulf, Levantine, and North African dialectal backgrounds and L2 speakers representing diverse linguistic backgrounds across the Americas, Asia, Africa, and Europe. We benchmark four pretrained ASR models under zero-shot and fine-tuned settings using unseen-speaker-$\&$-unseen-prompt (USUP) and unseen-speaker-$\&$-seen-prompt (USSP) evaluations. Results show that L2 speech remains substantially more challenging than L1 speech, with the largest errors observed mainly for younger L2 speakers. Age-specific fine-tuning improves the matched age group, while joint fine-tuning provides a stronger balance across populations. ASR hypotheses are also consistently closer to the standard reading prompt than to the verbatim transcription, particularly for L2 speech, suggesting partial normalization of reading deviations.

Self-supervised visual representation learning learns useful features without manual annotations during representation training. The image-based joint-embedding predictive architecture (I-JEPA) predicts latent representations of masked image regions, but its objective does not explicitly model responses to specified visual interventions. We introduce CI-JEPA, a counterfactual intervention-aware extension that learns to predict the representation change $\Delta Z = Z_{\mathrm{CF}} - Z$ between an original image and a modified counterpart. We assess representation robustness through selective sensitivity: stronger responses to task-relevant semantic changes than to nuisance changes. Experiments on Flowers102 use flower-center occlusion as a candidate semantic intervention and background blur and tint as candidate nuisance interventions. With frozen-encoder linear probing, CI-JEPA achieves a best validation accuracy of 78.14%, compared with 77.55% for both the pretrained ViT-B/16 and the I-JEPA baseline, a gain of 0.59 percentage points. The reported mean $L_2$ representation changes are 4.42 for center occlusion, 3.48 for background tint, and 2.83 for background blur. This ordering is consistent with relative semantic selectivity for the evaluated interventions, rather than complete nuisance invariance. The accuracy comparison is complementary and does not establish improved robustness over the baselines. These controlled image modifications provide a framework for studying intervention-induced changes in JEPA representations; they do not establish causal feature discovery or robustness to all visual changes.

When does communication help a group identify hidden adversaries, and how does its value change as the group adapts? In Mafia, an informed minority hides inside an uninformed majority whose only evidence is open play. The zero-information game, where each day's vote eliminates a random player, is exactly solved and scores every society; matched-casting comparisons between protocols identify the effect of communication. Societies of 8-100 claude-haiku-4-5 agents (7,416 analyzed games, 1.9M model calls) adapt by rewriting and inheriting private strategy notes. Simultaneous broadcast improves adversary identification over silence in all nine compositions tested (8-46 players). Turn-taking removes most of this advantage; its voting landslides are as frequent as broadcast's but land on mafia near chance (1.08x versus 2.53x). At 70 players, agents reading eight statements per day identify adversaries worse than silent ones, and limited talk is worth less than at 46 players. Adaptation is fast but need not help. In their first broadcast games, citizens announce their role far more often than mafia (91% vs. 30%) and first-day votes find mafia at three times chance; within two generations citizens stop announcing and the cue fades, a change the inherited notes carry. In controlled redeployments at 16 players, societies carrying sixty generations of their own notes score below societies with none. Communication shapes both collective inference and the signals it depends on, so a protocol's value must be measured together with the adaptation that changes those signals.

Mapping post-harvest burned cropland is difficult when fires are small and fragmented and reliable labels are scarce. We developed a calibrated weak-supervision framework for Punjab, India, using Sentinel-2 spectral change, VIIRS active-fire context, and MODIS MCD64A1 as a coarse external calibration and agreement reference. Three pseudo-label recipes, five feature representations, and linear, tree-based, boosted, and neural classifiers were evaluated using nested district-held-out cross-validation over three seeds and five folds. NBR and dNBR were excluded from classifier inputs. The best configuration used the very-strict recipe, a multilayer perceptron, and the full optical feature set (mean Cohen's kappa 0.395, AUROC 0.753, F1 0.747, balanced accuracy 0.703); Random Forest, XGBoost, and LightGBM were practically tied. Higher agreement with held-out pseudo-labels did not establish improved label correctness or independent burned-area accuracy. For deployment, a Random Forest with the very-strict recipe and full optical features was retained. An externally calibrated threshold of 0.60 yielded district-level MODIS agreement of R-squared 0.636, a mapped-to-MODIS burned-area ratio of 1.005, and Spearman correlation of 0.779 with district fire counts. Pixel-level MODIS agreement remained modest (F1 0.205, kappa 0.093). Zero-shot transfer to Haryana was promising (mean kappa 0.641), but Punjab cross-year stability was weak, and Sentinel-1/Sentinel-2 feature concatenation did not improve the optical baseline. Optical observations ended before the seasonal fire context, limiting coverage of late burns. The framework supports district-scale burden assessment and hotspot screening, with limited support for exact scar boundaries or temporally stable annual mapping.

Agentic Harness is the runtime that constructs task context and controls execution flow, thereby shaping overall agent performance. Given a fixed model and external evaluation, automated Harness optimization seeks to improve this runtime through an iterative proposal–evaluation loop to better solve target tasks. Existing meta-harness methods mainly adopt proposer-centric discovery, in which an LLM-based proposer integrates accumulated experimental findings to determine subsequent Harness revisions. This places the burden of maintaining the evolving improvement state on the proposer as history expands and its underlying experimental logic becomes harder to discern. In this paper, we introduce the Causal Improvement Graph (CIG), a graph-governed meta-harness framework that externalizes the evolving improvement state in a persistent graph, allowing prior findings to directly govern subsequent Harness optimization through local proposer operations. CIG grows and links Evidence, Hypothesis, Intervention, and Outcome nodes to represent what was observed, how it may be explained, how to test that explanation, and what the evaluation reveals. Their structural relations preserve how the improvement state changes across iterations, allowing local proposers to build directly on relations among prior findings rather than recover them from raw history. Across various agent tasks, CIG discovers stronger Harnesses than previous meta-harness baselines and remains robust to the choice of task solver and proposer. Structural ablations further support the design of an explicit improvement state with graph-governed evolution.

We present an oracle-optimal method for finite-sum monotone inclusions under mean-square Lipschitz continuity. Our switching regularization method finds a point $y$ and a certificate $g\in G(y)$ with $(\mathbb{E}\|F(y)+g\|^2)^{1/2}\le\varepsilon$ using $\mathcal{O}(n+\sqrt{n}LR/\varepsilon)$ expected component evaluations and resolvent evaluations. It removes the additive $n\log n$ cost of restarting a variance-reduced solver at every regularization stage by switching to a centered stochastic proximal iteration at regularization strength $L/\sqrt{n}$. Carrying an operator estimate between the remaining stages limits their total cost to $\mathcal{O}(n)$. A matching $\Omega(n+\sqrt{n}LR/\varepsilon)$ lower bound holds for randomized linear-span component-oracle algorithms with adaptive stopping and expected query budgets. Thus, for $0<\varepsilon\le LR/2$, our method attains the optimal worst-case expected component complexity in this oracle model, up to universal constants.

Sparse-accelerator design spaces are usually searched against analytical models, so a design point is admitted on what a model predicts rather than on what the hardware does. SparseCraft closes that gap with a language model inside a closed CHIA loop. In each of 15 iterations the model reads the measured outcome of the previous one and edits the Chisel RTL, the memory configuration and the sparse-kernel schedule of a Gemmini accelerator through MCP tool servers, and no candidate counts until it has been checked for legality, elaborated, simulated cycle-accurately, checked bit-for-bit on every output against a golden reference, and synthesised. The harness turns each measurement into the next work order, a diagnosed bottleneck with matching strategy guidance, the history of tried designs and a score of the model's own prediction, and a second model repairs changes that fail a gate. On a $512 \times 512$ GraphChallenge sparse-DNN layer the loop reaches 2.1x fewer cycles, 9.8x less off-chip traffic and 22.8% less area than the block-sparse Gemmini baseline, with 5.61x higher modelled perf/W and 11.8x lower EDP. The levers span three layers: a schedule that keeps the dense operand resident removes 9.8x of the traffic, a zero-gated MAC and a zero-row skip unit that the model wrote in Chisel cut energy, and resizing the memories cuts area.

Software agents increasingly depend on open-source components when executing tools and interacting with external systems. Security flaws in these dependencies may therefore influence more than the software process in which they occur: their consequences can be carried through tool outputs, agent state, and information subsequently exposed to the model. Determining whether such a consequence is actually realized in a particular execution, and where its influence stops within the agent system, remains challenging. We investigate how known OSS vulnerabilities behave when exercised as part of agent workflows. Our study reveals recurring patterns in the way security-relevant consequences emerge and propagate across runtime layers. Building on these observations, we use vulnerability-aware semantic information, differential executions of vulnerable and corrected software, and runtime provenance spanning multiple layers to determine whether a vulnerability produces an observable security effect and to identify the furthest layer at which that effect remains manifested. Our evaluation shows that this approach can accurately distinguish realized vulnerability effects and determine their manifestation boundaries across a diverse collection of vulnerability scenarios. We additionally apply the analysis to documented workflows in a real-world agent framework and uncover multiple security effects originating from known vulnerabilities in its OSS dependencies. These results highlight the importance of reasoning about vulnerable dependencies in terms of their execution-level consequences rather than vulnerability presence alone.

Evaluation budgets in agentic retrieval-augmented generation span questions, search trajectories, and repeated answers. We measure allocation precision, reading efficiency, and cost boundaries using a retrieval-feedback comparison on HotpotQA and MuSiQue. At 34.14–34.39M model tokens, broader question coverage lowers standard error by 33% versus five reads and 12.6% versus three trajectories. Archived nested and Q-only forecasts predict these allocations within 4.0% and 3.5%, respectively. Depth subsets establish no clear forecasting advantage beyond the two-trajectory audit. One-read variance penalties relative to the fitted optimum at the same token budget are 0–9.9%, with substantial Pro uncertainty. Under recorded model fees, more questions beat more trajectories at search prices of \$0–1 per 1,000 requests; question-versus-read fee rankings remain unresolved. Temperature zero cuts answer disagreement from 14.3% to 3.4% while comparison precision stays similar. \par\medskip\noindentKeywords: Agentic RAG; Evaluation budget; Generalizability theory; Repeated sampling.

Generating a high-quality gaming world from a natural-language game intent requires joint reasoning about scene structure, spatial layout, gameplay objectives, interactive entities, and executable gameplay logic. Existing coding agents can generate individual assets, scenes, or scripts, but often struggle to maintain consistency across these components. We propose Code2Games, an agentic framework that builds a structured gaming world upon a base Blender world generated from the same game intent. Code2Games coordinates scene analysis, gameplay planning, constrained gaming-world generation, and gaming-engine customization through a shared scene-gameplay representation with persistent element correspondence. After world generation, Code2Games adapts the generated world to Unreal Engine 5 and employs an execution-guided reconstruction process that uses compilation diagnostics, runtime feedback, and gameplay test results to resolve inconsistencies arising during engine adaptation. To systematically evaluate gaming-world generation, we introduce the GameCode4D benchmark, which comprises ten fixed game prompts spanning different levels of scene and gameplay complexity. We evaluate the generated results across four dimensions: visual quality, interactive fidelity, multimodal artifact quality, and playable-game quality. Experiments demonstrate that, compared with direct gaming-world generation by coding agents and existing baseline methods, Code2Games consistently improves the visual quality and interactive fidelity of generated gaming worlds, as well as the quality of the resulting games after engine adaptation.

Large language models are increasingly used as integration layers above specialized tools, but a stronger component does not necessarily produce a stronger combined system. Across five diagnostic datasets (bearing vibration, process monitoring, semiconductor equipment), we study whether an LLM can reliably use external diagnostic information; paired repeat calls separate advice effects from output instability. In all five, conflicting external information overturned initially correct LLM judgments. Among the four datasets with direct integration comparisons, none showed a consistent advantage for implicit LLM integration over the stronger standalone source. On a Tennessee Eastman confirmation set whose protocol was fixed before evaluation, unaided accuracy was 64.67%, implicit LLM-specialist integration 77.43%, and the specialist alone 83.33%. Specialist information improved the LLM by 12.8 points (95% interval 9.7 to 15.9), yet the integrated output stayed 5.9 points below the specialist (95% interval -12.0 to -0.7). A two-source selector oracle reached 92.76%, indicating complementarity that the integrated output did not fully realize. The integrated output missed 140 of 295 specialist corrections (47.5%) but lost 15 of 99 initially correct LLM judgments (15.2%). The deficit remained under prompt and specialist sensitivity analyses. Among CWRU cases solved under both evidence presentations, task-aligned physical evidence yielded lower estimates of susceptibility to incorrect advice in six of seven models (five intervals excluding zero); higher reasoning effort gave no reliable reduction in five models, and a separate four-model TEP analysis gave no clear evidence that it resolves the integration problem. Source quality and integration quality should be evaluated separately: an integration layer should be compared with its stronger standalone component, not only with the unaided LLM.

Continual skill evolution enables LLM agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. Its effectiveness depends on determining not only what to change, but also why a change is justified and when it should become persistent guidance. However, existing experience-driven methods can lose the behavioral evidence and task contexts supporting edits. Moreover, a global validation outcome provides an incomplete judgment of its constituent changes: locally supported corrections may be discarded with a rejected revision, while evidence may require further experience to inform useful updates. To this end, we introduce EVISKILL, an evidence-driven framework that organizes execution observations into Replayable Evidence Cards and synthesizes edits with explicit links to their supporting contexts. Targeted replay verifies these edits through re-execution and provides feedback for correction. Across epochs, EVISKILL preserves evidence and provisionally retains supported edits for further refinement, while global validation governs their incorporation into the final skill. Experiments on three interactive benchmarks across six LLM backbones demonstrate the effectiveness of this approach.

Vision-language foundation models such as CLIP provide strong semantic representations, but their patch tokens are not directly optimized for dense metric geometry. SPACE-CLIP showed that frozen CLIP features can support monocular depth estimation through layer-group feature fusion, yet it leaves open how neighboring CLIP tokens should be combined to recover fine local structure. We present SPACE-CLIPv2, a frozen-backbone depth decoder that aggregates fixed local neighborhoods in CLIP token space. At selected decoder stages, the model samples a fixed token stencil, predicts aggregation weights, and injects the resulting response through a gated residual update. A token-space high-pass branch further preserves shallow local contrast. On NYU Depth V2, SPACE-CLIPv2 improves over a matched SPACE-CLIP baseline, while five-seed experiments consistently favor fixed over learned-offset sampling. Zero-shot iBims-1 evaluation further improves boundary and planar-geometry measures. These results support constrained local token aggregation as a practical mechanism for decoding geometry from frozen CLIP representations.

Geographic information retrieval (GeoIR) tasks require systems to interpret ambiguous toponyms for downstream applications. Traditionally, toponym resolution relies on gazetteers to provide an explicit index of place entities and spatial relationships. Recently, gazetteer-free approaches seek to reduce dependence on handcrafted searches: dense retrieval utilizes text encoders to capture rich context, moving beyond the limitations of lexical search. However, text encoders implicitly assume that learned representations can function as reliable spatial-semantic indexes. In this paper, we evaluate this assumption through a spatial-semantic indexing setup: given a contextualized toponym mention, we retrieve the corresponding gazetteer entity represented by text derived from a gazetteer knowledge graph. We benchmark five frozen text encoders under two retrieval strategies: brute-force nearest-neighbor retrieval over entity representations, and a neuro-symbolic hierarchical beam search that constrains retrieval (i.e. chaining the search with gazetteer hierarchy). Experimental results reveal a distinct coarse-versus-fine trade-off. Unconstrained dense retrieval frequently incurs catastrophic spatial errors. Conversely, hierarchical constraints improve coarse geographic grounding, but still yield limited benefit for fine-grained localization metrics: vanilla text encoders fail to capture the fine-scale spatial fidelity encoded in gazetteers. Our code is publicly available at: https://doi.org/10.25439/rmt.31094269

Vision-language-action (VLA) models encode semantic information from vision-language pretraining, but manipulation also requires precise spatial reasoning. We present GeoBridge-VLA, a two-stage method for learning geometric features from a pretrained VLA's frozen visual encoder and using them for action prediction. Stage I trains a feature bridge and geometry decoder with depth supervision. Stage II freezes these modules and trains a gated residual interface together with the action-side projections and action expert. The residual augments the existing visual tokens without adding a second image encoder or increasing the token count. Deployment requires RGB, robot state, and language, but no depth observations. Under matched evaluation conditions, GeoBridge-VLA achieves 70.9% success on LIBERO, compared with 60.0% for SmolVLA. Disabling the residual in the same trained checkpoint reduces success from 70.90% to 69.85%, with mixed effects across suites. On a physical ROBOTIS OMY robot, GeoBridge-VLA succeeds in 148 of 200 trials (74.0%) across four tasks, compared with 108 of 200 (54.0%) for SmolVLA.

Dual-system Vision-Language-Action (VLA) models improve real-time robotic control by pairing a slow, reasoning-capable generalist with a fast specialist action expert. However, existing methods invoke the generalist at a fixed frequency, ignoring the fact that decision-making complexity varies throughout a rollout. This static strategy wastes computation in easy phases and can delay renewed reasoning when the scene changes unexpectedly. We propose TUD (Triggering generalist reasoning via predictive Uncertainty for Dual-system VLA), an adaptive inference framework that selectively skips unnecessary generalist calls. TUD measures the cross-step dispersion of action re-predictions at the upcoming chunk slot under the cached generalist context, as a predictive uncertainty signal. This signal captures how much the future action plan shifts as new observations arrive and is computed from forwards the architecture already runs, requiring neither manual phase labels nor an auxiliary uncertainty model. On VLA-Arena, it achieves a higher success rate at matched call budgets than alternative uncertainty baselines while maintaining low wall-clock overhead, and more consistently separates successful from failed rollouts. Also, TUD finds a more favorable cost-success trade-off than non-adaptive baselines, tracing an entire operating curve as a single threshold is varied, and substantially reduces VLM calls at matched success rate. The same trade-off appears in our real-robot experiments, where TUD cuts generalist calls by 75% relative to the strongest fixed-interval baseline while achieving an even higher success rate. Our results suggest that predictive uncertainty provides a practical criterion for adaptive reasoning in efficient VLA control.

Aerial vision-and-language navigation (VLN) enables unmanned aerial vehicles to execute long-horizon natural-language instructions from visual observations in complex three-dimensional environments. However, recent aerial VLN models often rely on large-scale vision-language backbones and dense visual histories, imposing substantial computation and memory costs that hinder onboard deployment. We propose LightVLN, a lightweight history-aware aerial VLN framework that combines a compact 0.5B language backbone with compact representations of both historical and current observations. LightVLN compresses each historical frame into a single token using visual features already computed by the policy. It further introduces history- and instruction-conditioned local aggregation to reduce the current observation from 256 to 32 visual tokens while preserving navigation-relevant spatial information. With up to 16 historical frames, the policy uses at most 48 observation-derived tokens. On the public OpenFly dataset, LightVLN achieves 50.93% Test-Seen and 36.14% Test-Unseen success rates (SR), outperforming the evaluated 7B language-backbone baselines on most reported metrics. It also achieves 25.83% SR on AerialVLN-S Val-Seen. In a reconstructed unseen campus, we deploy LightVLN on a DJI M350 RTK with an external Jetson Orin NX 16 GB for closed-loop onboard-compute real-to-sim hardware-in-the-loop (HIL) evaluation, achieving 14.61 Hz model inference and 11.13 Hz end-to-end decision updates. These results demonstrate the effectiveness and efficiency of LightVLN for aerial navigation.

We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image regions mentioned in their reasoning. Self-Saliency uses a grounding model to localize the objects mentioned in each reasoning step and treats the resulting areas as supervision for the model's visual attention. Previous work on steering visual attention determines target image regions based solely on the image and question. In contrast, we show that conditioning the target regions on the model's generated reasoning improves downstream performance. For proper evaluation, we build a unified, broad suite of 25 visual reasoning benchmarks, where we reproduce the results of previous methods. We find that Self-Saliency significantly outperforms both prior attention-steering methods and baselines that ground image-level text, achieving both a better average rank and a better mean score. Post-training analysis shows that the model primarily adapts its reasoning text to existing attention patterns, producing shorter steps that refer to larger regions. Nevertheless, when controlling for generated text, attention to grounded regions increases significantly across the relevant layer. Finally, we identify a consistent geometric bias in VLM visual attention toward the image border. However, our ablations show that Self-Saliency's gains cannot be explained by simply aligning attention with the center of the image, highlighting the importance of aligning visual attention with the regions mentioned in the model's reasoning.