Papers

In Human-Interactive Robot Learning (HIRL), human teachers assess learning progress by observing agent behavior. However, Reinforcement Learning (RL) agents often fail to express learning progress in human-interpretable ways, leading to suboptimal or counterproductive teaching. This work proposes "Insight": a human-interpretable affective signal grounded in the RL process. It is specifically designed to address the "Absence of learning" human teacher mental model misalignment - the misconception that a failing or exploring agent is broken, underpowered or not learning at all - by signaling an agent's "Aha!" Insight moment. The signal is derived from the absolute Temporal Difference (TD) error making it easily implementable in other RL agents. To ground this signal, five design criteria were formulated: Relevance, Interpretability, Faithfulness, Scalability, Generalizability. The structural construct validity was assessed through simulation, examining micro and macro dynamics and event-related sensitivity. Micro dynamics reveal that Insight captures meaningful learning events at the appropriate time and magnitude. Macro dynamics demonstrate that the signal follows the agent's learning phases and reflects overall progress. Event-related sensitivity shows, the signal distinguishes the saliency of environment interactions, such as positive rewards versus "trauma-like" negative events. These results demonstrate that technical RL dynamics can be effectively packaged into human-like affective substrates to close the teacher-learner loop.

National aviation-investigation databases are deep but territorial; global compilations such as the Aviation Safety Network and the Bureau of Aircraft Accidents Archives are hand-curated, apply their own inclusion thresholds, and publish no per-record lineage. The FlightFinder Occurrence Corpus harmonizes 279,485 occurrences and 131,882 attached narratives from 128 source codes – national accident-investigation authorities, occurrence-reporting systems and four global compilations. Records are mapped into one schema; each normalized record reduces to exactly one key from an ordered ladder – event signature, registration and date, rounded position and date, or source and native identifier – so a missing field never creates a link, and the key is the occurrence identifier. Records the ladder cannot reach are scored in a blocked pass into an explicit merge table and applied only within an automatically approved score band or after a person confirms them. Field conflicts follow a documented source ranking; one provenance row per contributing source – its native identifier and URL – is retained, with attribution and licence terms per source code. Linkage error is measured on five adjudicated samples totalling 200 pairs. A recorded uniform random draw of 60 from the 3,441 merges the automatic band applies as it ships found no error; the exact two-sided 95% Clopper-Pearson upper bound on its false-merge rate is 6.0%, or 205 pairs. The measured error covers the scored band only; the ladder's deterministic joins are not adjudicated. The corpus has no exposure denominators and inherits the under-reporting of its sources. It is offered as a base for cross-national safety statistics, source-disagreement studies and narrative text mining; a frozen, DOI-referenced snapshot accompanies the live API.

Humans express uncertainty verbally via markers (e.g., "possible," "likely"), yet most LLM uncertainty quantification (UQ) relies on costing likelihood- or consistency-based signals. From a cognitive perspective, accurate verbal uncertainty reflects metacognitive monitoring, representing knowledge boundaries ("knowing that you don't know") to support regulation and information seeking. In this paper, we investigate how LLMs diverge from humans in verbal uncertainty quantification and whether verbal markers can reliably quantify LLM uncertainty. We curate a corpus of human uncertainty markers from psychology and decision-science literature and benchmark LLMs against it. We observe that LLMs encode verbal uncertainty with numerical levels that differ substantially from those of humans. We then introduce METHODNAME, a novel optimization-based algorithm that learns an optimal uncertainty profile over uncertainty markers directly from LLM outputs. By fitting a marker-uncertainty mapping to best explain empirical correctness, METHODNAME discovers how much probability mass each verbal marker should convey, rather than estimating uncertainty via repeated sampling. METHODNAME enables a direct, marker-level comparison of confidence semantics between humans and LLMs, disentangling mismatch and revealing systematic confidence disparities in verbal expressions.

A Boolean Holant problem evaluates a graph partition function specified by local signatures at its vertices. We prove a complexity dichotomy for arbitrary finite sets of algebraic complex-valued signatures on general graphs: an explicit, decidable criterion characterizes the polynomial-time cases, and every remaining case is $\#\mathsf{P}$-hard under polynomial-time Turing reductions. The proof resolves the all-even case by constructing signatures with nonzero endpoints and all remaining support on the central layer, then classifying them according to half their arity. Binary transfer groups and matching-product reconstruction provide the main tools in the small- and large-height cases, respectively.

Holographic algorithms solve planar counting problems by encoding each value of a finite domain into several Boolean matchgate wires. Base collapse asks whether every exact representation can be compressed to a number of wires per edge bounded only by the domain size. Chen (STOC 2016) and Xia (STOC 2016) established broad positive collapse theorems under full-rank and related structural hypotheses. Together, these works left open whether a domain-only collapse bound survives when several locally deficient signatures must share one encoding. We resolve this open problem negatively, already on a three-state (qutrit) domain. For every $a\ge4$, we construct a five-label integer-valued qutrit language of maximum arity $a$ with an exact rational matchgate presentation, yet every exactly equivalent label-preserving presentation requires common width $\Omega(2^{a/2}/a)$, even if its domain, base, tensors, and complex weights may all change. The construction avoids the usual local degeneracies, so the obstruction is genuinely simultaneous. Algebraic geometry then drives an exhaustive trichotomy explaining the boundary of collapse: the gadget closure either separates into rays, is Gaussian-mobile and collapses to width at most three, or is confined to a rigid plane-plus-ray flag containing our unbounded family. Pure-spinor geometry forces compression in the mobile case, while dimension bounds for matchgate varieties and Zariski avoidance place exact integer data outside every low-width algebraic image. Thus one geometric framework explains both why collapse occurs and why it can fail without bound.

Observation consistency (OC) and modified observation consistency (MOC) are structural conditions used in hierarchical and modular supervisory control under partial observation. Their verification for languages generated by deterministic finite automata is PSPACE-hard, whereas decidability was open. We answer this question by showing that both problems are undecidable, that is, there are no algorithms verifying OC or MOC. On the positive side, we identify a decidable class defined by a restriction on the plant: if every cycle of the automaton contains a transition labeled by an observable high-level event, then verification of both conditions is PSPACE-complete.

"An agent that writes its conclusions into a store it later retrieves from closes a loop usually reported as one-way contamination. Taking the loop to the infinite-tenure limit against an append-only store gives a different picture: because writing never deletes, the reachable state space has a hard upper edge at (n-1)/n, so the outcome is a choice between two edges rather than a decay. At f_0 = 0.9 the interval between the two modes holds 3.6% of 220 runs where a uniform spread would put 20.6%, and is strictly empty on the first 15; the pooled mean describes 8.2% of the runs it summarises, the median 68.2%. Everything the model contributes is carried by one measured primitive with no fitted parameter, the copy function \gamma(\phi): on 36 Wikidata facts, sign(\hat{\gamma} - \gamma_{crit}), with \gamma_{crit} = 1/k at r = 0, w = 1, predicts the direction of drift on 353 of 360 real-fact runs (39 of 40 synthetic in the same batch). Scale does not rescue the store: pooled frontier capture is 0.850, with claude-sonnet-4.5 captured on 20 of 20 seeds against our registered prediction of <0.5. What the interval tests is distinguishability rather than count: on the real facts, multi-valued runs have 6.4x its occupancy of the rest. It survives at f_0 in {0.1, 0.3, 0.5}, capture peaks at f_0 = 0.5, and of four interventions with criteria frozen first, timing dominates fraction at matched budget while a consistency gate drives every model to 0.993. The resampling unit is the seed, at a design effect of 3.75 on a pooled level: under a 44-seed control the ordering supporting claim 4 collapses from Spearman +0.98 at three seeds to +0.31-0.80 at forty-four, while claim 2's ordering is exact there (+1.00, p = 0.017). All 87 graded rows are in Appendix W, 37 of them graded withdrawn, failed, self-correcting, undecidable or an acknowledged limit, against 50 that are not."

Dual-source encrypted points of interest (DSEP), POIs from two encrypted coordinate systems, suffer from intertwined location and attribute uncertainties, including nonlinear systematic misalignment and naming inconsistency, hindering land-use/land-cover (LULC) mapping. To the best of our knowledge, this paper is the first to propose an LLM-driven, training-free location-attribute synergic closed-loop optimization paradigm for DSEP fusion. The paradigm jointly refines location transformation and attribute correspondences through iterative feedback. Attribute-synergic location fusion uses an LLM-driven attribute matching method to establish DSEP correspondences, reducing matching complexity from O(N^2) to O(N), and refines transformation coefficients using an improved particle swarm optimization algorithm within ISODATA-clustered local subregions. Location-synergic attribute fusion then reassesses attribute confidence from updated geometric residuals through an LLM-fuzzy method. The refined correspondences feed back into location optimization, forming a bidirectional closed loop. Sample purification and adaptive radius contraction enable convergence in essentially two iterations. We further propose a training-free LULC mapping method that inherits land-use classes from encrypted maps through location fusion, producing vector-raster integrated LULC maps. A reference-free POI fusion evaluation method is applied across 31 provincial capitals and municipalities in mainland China. Experiments show that our method achieves an average DSEP location fusion residual of 4.58 m and attribute fusion accuracy of 95.12%, improving upon the open-source baseline and state-of-the-art method by 1.77 m and 14.87%, respectively. Overall, the method provides a training-free solution for DSEP fusion and enables georeferencing of encrypted vector data to WGS-84 without field-surveyed ground control points.

We introduce FrontierMath Erdős (FME), a benchmark of 68 Erdős problems that are open as of August 2026. To solve a task in FME, AI systems must resolve (prove or disprove) one of the 68 conjectures in the proof assistant Lean. Our 68 problems were selected by the second author among 652 open problems on erdosproblems.com for their mathematical interest and difficulty. AIs have recently resolved several open problems in mathematics, but these demonstrations fall short of a systematic study of AI capabilities. FME evaluates every AI model on the same fixed problems, autonomously and under the same budget. We evaluated five AIs with a budget of \$300 per problem. One (GPT-6 Astra) scored 3%, and all others scored 0%.

Large language models (LLMs) aligned for safety often suffer from over-refusal, incorrectly rejecting benign yet safety-related instructions. Prior studies primarily attribute this to static representation overlap, largely overlooking the underlying dynamic mechanisms. In this paper, we present the mechanistic analysis of over-refusal through the lens of internal routing conflicts within transformer attention. We discover that a sparse subset of Hypersensitive Safety Heads misfires on Hard-Safe prompts, exhibiting abnormal attention entanglement that forcefully binds harmless target entities to refusal semantics. This triggers a severe, high-entropy routing conflict that deprives target entities of necessary attention. To counteract this, we propose Semantic Routing Calibration (SRC), a lightweight, training-free inference framework. SRC precisely localizes and dynamically suppresses these hypersensitive safety heads at the inference stage. Coupled with a dual-branch logits fusion that acts as a safety regularizer during subsequent decoding, SRC seamlessly restores trustworthy reasoning. Extensive experiments demonstrate that SRC alleviates over-refusal, with intrinsic safety performance preserved as much as feasible.

In on-policy distillation (OPD), the student determines which states receive teacher supervision. As its policy evolves, earlier response prefixes become less likely even though teacher-student disagreement on them persists. Under matched trajectory and optimization budgets, neither more queries nor more frequent rollout resampling is uniformly beneficial. Current-policy rollouts outperform initial-policy rollouts at shorter response budgets, but this ranking reverses at longer budgets. Replaying initial-policy rollouts after current-policy training improves accuracy, whereas replaying fixed recent rollouts does not reproduce the gain. We propose R-OPD, a gradient-triggered curriculum that adaptively selects when to revisit initial-student trajectories. When changes in mean gradients fall within minibatch-level variation for two consecutive comparisons, training switches from the next iteration onward to initial-policy replay. Across eight mathematics benchmarks and three training-data orders, R-OPD improves average accuracy over continued current-policy sampling by 2.25/4.44 percentage points at 16K/32K for a 0.6B student and 2.81/6.15 points for a 1.7B student. With a 30B-A3B teacher, it improves 8B accuracy by 4.05 points at 32K. At 32K, R-OPD exceeds a fixed schedule of 40 current-policy updates followed by 20 replay updates by 1.39/1.66/1.85 points for 0.6B/1.7B/8B. At the same generation cap, R-OPD also produces longer responses, suggesting that well-timed revisits help students use more of their reasoning capacity.

Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line of such agents frames model building as a code search problem and solves it by tree search, in which each node is a candidate program and the tree grows by generating a child program from a parent, and these agents now approach the capability of experienced AI engineers on realistic benchmarks. However, these agents have three weaknesses in efficiency that have not been fully addressed. First, only a small number of candidates can be executed within a realistic budget, so search rules that rank nodes by executed rewards, such as Monte Carlo-style tree search, rely on few and noisy scores and select the next node to explore less effectively. Second, no resource-aware strategy is used to schedule training jobs, which can lower hardware utilization and training efficiency. Third, every agent call is served by a single powerful model, which inflates inference cost. Here we introduce AIBuildAI-2.5, an agentic system that carries out the tree search with LLM agents and addresses each of the three issues. AIBuildAI-2.5 proposes a novel LLM-guided tree search, in which a judge scores each candidate on its expected improvement, grounding, and feasibility, and a selector ranks the pool of candidates from these scores and the state of the search. In addition, AIBuildAI-2.5 comprises a scheduler that launches training jobs with the current hardware resource status taken into account and a router that assigns lower-cost LLMs to less demanding tasks while reserving the most capable LLM for the most challenging sub-tasks in the AI model building workflow. AIBuildAI-2.5 ranks first on MLE-Bench with a medal rate of 73.3%, and outperforms a strong baseline on six autonomous AI research tasks from AIRS-Bench.

Lexicon-driven misogyny detectors cannot, by construction, distinguish a slur used against a woman from the same slur mentioned in counter-speech ("don't call her that") – yet exactly this distinction governs whether moderation protects or silences the people discussing abuse. We study this problem in code-mixed Hinglish and make three contributions. First, we diagnose two evaluation artifacts on a publicly available redacted corpus: category-encoding anonymization placeholders leak the label (a no-learning rule scores 1.000), and even after they are neutralized misogynistic and benign comments occupy lexically disjoint registers, so bag-of-words reaches macro-F1 approximately 1.00 under random cross-validation but collapses under template-disjoint evaluation. Second, we release Hinglish-MGY-Diag, a deterministic generator and a 416-item / 163-minimal-pair contrast-set diagnostic across five linguistically motivated categories in which slur presence and gendered register are decorrelated from the label by construction. Third, we introduce a strict pair-consistency metric that credits a model only when both members of a minimal pair are correctly labelled. Five from-scratch classical baselines evaluated under construction-disjoint five-fold cross-validation reveal that the strongest model reaches 0.93 accuracy on the cleanest use-mention subset but only 0.82 consistency – it still mislabels roughly one counter-speech pair in five. A frontier LLM used as an author-model ceiling attains 1.000 on all metrics, doubling as independent label validation and confirming the benchmark is a capability gradient rather than an adversarial wall. We release all code, data, the generator, and an arms-length LLM harness for reproducing every number.

A large audio language model (LALM) attaches a speech front end to a text language model (LM) that is already safety-aligned. When such a model refuses a harmful spoken request, is the refusal carried by the front end, or inherited from the text LM? We test this with causal interventions. At each model's audio-to-LM interface and at tested LM residual layers, we fit a direction separating harmful from benign prompts, ablate its component, and measure the resulting change in the model's first-token refusal margin. Four of the five models are evaluated under held-out category shift. Across five LALMs spanning three backbone families, with three models passing a baseline safety gate, the largest tested effects occur in a mid-to-late LM band, while ablations of the tested interface directions have little effect. On Qwen2.5-Omni, ablating the L16 direction changes the margin by -7.10, versus -0.013 at the projector. The audio pathway is still in use: zeroing the encoder output changes the margin by -4.7. In the same model, the contrast is linearly decodable at an early layer where single-layer ablation has little effect, and a direction fitted on the LM backbone alone transfers to the full audio model. Because harmful and benign prompts also differ in form, we interpret the direction as refusal-linked rather than harmfulness-specific. These interventions localize dependence of the refusal margin, not where refusal is computed. Moving the margin also does not always change what the model writes. Safety audits of these models should use interventions rather than rely on probes alone, and should examine the inherited text LM alongside the audio interface.

Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/without comparison cannot say which part of the layer does the work: the semantic content, the retrieval scaffolding that delivers it, or the pre-computed views that usually accompany it. We report a four-arm ablation on DABStep on four models that separates the three. The instrument is a data contract: a YAML artifact that carries a domain's semantics and the rules an agent's tools enforce. One arm empties every field of prose in the frozen contract while holding the tool surface, retrieval instruction, table allow-list and operation rules byte-for-byte fixed. Compiling the contract's own SQL expressions into views gives the ceiling a pre-computed layer would reach: gold on all 176 tasks it covers. Content dominates. It raises hard-task accuracy from 13.9% to 55.1%, 22.6% to 56.6%, 22.9% to 68.4% and 37.0% to 77.4%, beating the same knowledge pasted into the prompt on every model. Scaffolding without content is worth 0 to 5 points on two flash models and 14 to 15 on two frontier models. Against the compiled ceiling the contract arm's shortfall is a failure to derive, and it falls from 39 points to 5 with model capability. The contract beats the prompt because the rule it needs is one lookup away rather than buried in a long prompt: its SQL carries the fee semantics up to 98% of the time against the prompt arm's 4%, and at the lowest cost per correct answer on three of four models. For practitioners: semantics first, scaffolding second, pre-computed macros only where an agent demonstrably fails to derive. Ungoverned arms submitted 166 mutating statements; governed arms none. The gain is confined to the contract's domain. On one model the benchmark's own withheld golds grade the contract arm at 51.9% against 18.8% for the prompt baseline.

Large language model-driven remote sensing (RS) agents offer a promising approach to automating geospatial analysis. However, lightweight RS agents based on compact language models struggle with multi-step interactive tasks due to loss of long-horizon states, inefficient environmental feedback utilization, and sparse optimization signals. We propose RS-Claw-Evolution, an environment-feedback-driven framework that progressively improves lightweight agents through three stages. Interaction evolution uses executable code to control observations, maintain intermediate states, and reduce context redundancy. Experience evolution combines failure-aware trajectory generation with error-turn masking to learn from informative failure-recovery experiences without imitating faulty actions. Decision evolution uses reinforcement learning with multi-dimensional environment rewards and turn-level advantage protection to optimize tool-use behaviors and improve credit assignment in long sequences. On Earth-Bench, the optimized Qwen3-4B-based agent achieves 65.9% accuracy in Autonomous Planning mode, outperforming the untrained Qwen3-32B baseline (43.8%) and DeepSeek-V3.1 (60.8%), while approaching GPT-5 (71.6%). These results demonstrate that learning from environmental feedback can improve lightweight agents and narrow their performance gap with larger models in long-horizon RS tasks.

Producing task-specific large language models requires discovering effective training strategies through experimentation. Automated fine-tuning systems have made this experimentation feasible with far less manual effort. However, these systems are stateless: each search discards its discovered strategies, dataset insights, and hyperparameter findings once it ends. Every new task must then repeat this costly search from a cold start. To address this, we propose Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning search cumulative. In the first stage, a multi-agent pipeline performs Monte Carlo Tree Search-based exploration. A parallel Distillation Agent extracts task-specific exploration records and confidence-scored cross-task insights, which together constitute a structured experience repository. In the second stage, SAGE retrieves relevant experience from this repository and selects what applies to guide training on the new task. We evaluate SAGE on nine unseen tasks spanning both single- and cross-category settings. In single-round execution, SAGE's accumulated experience raises the average relative improvement over baseline from 3.2% to 15.6%, a 12.4-percentage-point gain over the same pipeline without it. These results show that persistent strategy experience provides effective guidance for automated fine-tuning on unseen tasks.

Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present DIPLOMAT, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce PROWESS, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched withnegotiation strategies, politeness levels, persuasive strategies. DIPLOMAT is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables DIPLOMAT to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluation on PROWESS confirm that DIPLOMAT consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.

Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes personas into hierarchical levels of observable expression, latent beliefs, and core motivational drives, for constructing highly convincing role-playing agents. Governed by the principles of scripted determinism and bounded agency, the architecture restricts the model to a reactive engine guided by a structured internal script. We further propose a reference-free evaluation framework that benchmarks dialogue naturalness against empirical human distributions using established psychological clinical instruments and adversarial stress-tests. Empirical evaluation reveals that while LLMs achieve high pragmatic fluency, they exhibit systematic limitations in emotional expression and joint attention. In addition, we present a case study of two Deep Personas and evaluate them using the proposed framework, demonstrating that structured personas can produce interactions that more closely align with human conversational behavior.

On-policy distillation (OPD) is a promising approach for transferring knowledge between language models, where a student receives dense token-level supervision along its own generated trajectories. However, teacher supervision can be unreliable when conditioned on incomplete or low-quality student prefixes. We identify Teacher Uncertainty Contraction (TUC), a systematic phenomenon whereby the teacher's predictive uncertainty decreases as it continues from a student-generated prefix. We theoretically characterize this trade-off through a variance-bias decomposition of teacher-branch gradients, showing that uncertainty contraction reduces variance while teacher-student path divergence increases bias, thereby favoring a finite continuation. Guided by this insight, we propose Adaptive-Continuations On-Policy Distillation (AC-OPD), which augments informative states along student rollouts with teacher continuations and adaptively selects their effective supervision horizons. Experiments on mathematical reasoning and code generation across model scales demonstrate that AC-OPD consistently improves over standard OPD. Controlled-continuations and matched-budget analyses further validate the adaptive-continuations design, highlighting adaptive teacher continuations as an effective principle for reliable on-policy distillation.The code will be made publicly available upon publication.

Model merging has emerged as a promising paradigm for integrating multiple task-specific capabilities into a single large language model. However, existing methods predominantly focus on post-hoc processing of independently fine-tuned models, overlooking how the training phase itself impacts cross-task compatibility. Resolving parameter conflicts after fine-tuning is inherently sub-optimal. To address this, we propose CAMFT, a Conflict-Aware Mergeable Fine-Tuning method that makes task adaptation both efficient and mergeaware. CAMFT treats mergeability as a property shaped during fine-tuning, rather than only a problem to be solved after fine-tuning. By guiding each task to update sparse coordinates with lower cross-task conflict, CAMFT produces task updates that are efficient to train and more compatible for downstream model merging. Extensive experiments demonstrate that CAMFT outperforms standard finetuning baselines in multi-task merging scenarios. Codes are available at https://github.com/gyanchow/CAMFT-LLM.

We present CALM, a reproducible hybrid framework that integrates an optional large language model (LLM) activity planner with calibrated stochastic choice, shared network feedback, memory and habit, typed feasibility checks, and deterministic offline replay. Unlike trip-mode classifiers or diary-only generators, CALM executes a closed traveler-day loop and evaluates each generative module against an empirical, reproducible baseline. On the 2024 New York City Citywide Mobility Survey (CMS), 110,691 seven-mode trips are split by respondent into 78,487 training and 32,204 holdout trips. Training-only alternative-specific constant calibration reduces mean holdout mode Jensen-Shannon divergence from 0.15599 to 0.00394 across ten seeds. A matched live-LLM ablation then quantifies trade-offs among aggregate fit, temporal fit, behavioral persistence, and feasibility, while frozen prompt-response pairs support deterministic replay of downstream simulation. Controlled weather, delay, fare, and parking ladders further demonstrate consistent and interpretable responses under intervention. CALM contributes a reproducible protocol for integrating and evaluating generative planners in traveler simulation through person-disjoint calibration, matched module ablation, controlled stress testing, and end-to-end traceability.

Forecasting karst aquifer dynamics is difficult because recharge responses are nonlinear, event-driven, and governed by strongly heterogeneous flow paths. This study develops and evaluates a deployment-aware framework for 1-12-week-ahead prediction of spring discharge and groundwater level using approximately 79 years of hydroclimatic observations from the Edwards Aquifer, Texas. Five model families were compared under a common temporal evaluation design: extreme gradient boosting, extremely randomized trees, long short-term memory, convolutional neural networks, and Transformers. Predictions were evaluated using coefficient of determination, Kling-Gupta efficiency, root-mean-square error, and agreement with operational drought thresholds. Extreme gradient boosting was consistently most reliable, with R2 at least 0.97, 0.96, and 0.94 across 1-4-, 5-8-, and 9-12-week horizons, respectively, and greater than 90% critical-stage agreement at the first three drought stages across all horizons. Deep models were competitive at short horizons but degraded progressively and exhibited isolated failures at longer lead times. We attribute this contrast to an alignment between tree partitioning and low-dimensional, axis-aligned hydroclimatic predictors, together with the tendency of neural models to smooth irregular extremes. The validated models were embedded in a five-agent operational architecture that automates data acquisition, model assignment, deterministic prediction, threshold monitoring, prospective verification, literature retrieval, and reporting. The contribution is therefore a transferable framework joining parsimonious model selection, leakage-aware multi-horizon evaluation, decision-relevant threshold skill, and auditable agentic automation.

3D Gaussian Splatting achieves photorealistic reconstruction within training view distribution, yet it degrades on out-of-distribution novel views, exhibiting holes in unobserved regions and artifacts in observable areas. Recent works formulate this task as extrapolation and interpolation and try to address it with generative models, but remain limited in extrapolation scale and quality. They repeat a generate-reconstruct-shift cycle to progressively build a scene, which introduces accumulated errors with every step conditioning on previous outcomes. In this work, we propose a holistic framework for extrapolation and interpolation. We devise an independent camera view detection mechanism to enable parallel conflict-free extrapolation, circumventing the reliance on the aforementioned error-prone cycle. Building upon this, we design a hierarchical pipeline that extrapolates independent and dependent camera views separately. Additionally, previous methods overlook inconsistency between generated and original images, resulting in compromising well-reconstructed areas. We propose a plug-and-play Quality-Aware Mask (QA-Mask) module, enabling selective utilization of generated data. By calibrating learning weights with pixel-wise rendering quality, it prevents generation-induced degradations on well-constructed areas. Extensive experiments demonstrate the superior performance of our framework, with QA-Mask generalizing to multiple generative reconstruction models.

LLM agents are increasingly used for collaborative problem solving and human-group simulation. This makes outcome-only evaluation insufficient: if LLM groups are used as models of human groups, we need to know whether they succeed or fail through human-like deliberative mechanisms. We compare human group chats with matched LLM deliberation traces on Wason-style deductive reasoning, then test whether the same process signatures generalize to analogical, abductive, and analytical tasks. Humans and LLMs show the same assembly bonus asymmetry: discussion improves the average member more often than the best initial member. Initial-answer diversity accounts for the effect of model heterogeneity, increasing movement in both corrective and destructive directions. The main differences are process-level. Compared with humans, LLM groups follow majorities more often, surface less unique information, and converge earlier; correct minority signals succeed mainly when re-expressed early. Interventions motivated by human group-decision research yield modest improvements in collective outcomes, but do not remove the coordination bottleneck. Together, these results suggest that LLM groups can reproduce some outcome-level patterns of human deliberation while diverging in the mechanisms that generate assembly bonus and process loss, with implications for group simulation and human-AI collaboration.

This paper proposes SpecAugment-Patch Merging, a simple yet effective method to accelerate Audio Spectrogram Transformer (AST) training. We first apply SpecAugment to mask input spectrograms at the patch level, and after positional embeddings are added, the method selects r pairs of masked patches and merges them, reducing the number of tokens processed by the Transformer. Increasing the number of merged pairs r from 0 to 100 keeps mAP on AudioSet nearly unchanged (34.07 to 34.08) while throughput increases from 43.3 to 49.3 samples/sec, which is a relatively 13.9% improvement. Similar patterns appear on ESC-50 and Speech Commands V2, where throughput steadily improves with only minor accuracy changes, demonstrating that this merging approach provides faster training with minimal performance loss.

Virtual Try-On (VTON) aims to dress a person with the reference garment, producing visually reasonable results aligned with human preferences. Turning this preference-oriented goal into an actionable objective relies on a scoring function aligned with human taste. However, classic fidelity metrics exhibit weak correlation with human judgments, and generic VLMs fail to provide the discriminative granularity demanded by try-on quality evaluation, which hinges on faithfully preserving garment and person details. This shortcoming is further exacerbated in the reinforcement fine-tuning (RFT) optimization and leads to severe reward hacking. To this end, we present TryOnReward, a fine-grained reward model tailored for VTON. Built on a vision-language backbone, it adopts a foveation calibration objective that grounds each quality dimension in the relevant region to avoid global shortcut learning. Meanwhile, TryOnReward jointly optimizes pairwise preferences and per-dimension quality scores via margin-aware supervision, leveraging both relative and absolute quality signals. For model training and evaluation, we build TryOnReward-100K, a human-annotated per-dimension rating dataset, alongside TryOn-Bench and TryOnRewardBench, two benchmarks covering diverse real scenarios. Extensive experiments confirm that TryOnReward significantly outperforms generic judges in human preference alignment, and when serving as the RFT reward function, it consistently yields human-preferred try-on results across multiple baselines.

We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view. On a calibrated EPIC-KITCHENS subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy, which is higher than the caption baseline by +0.40 (paired p = 1.1 \times 10^{-5}) and direct VLM-only QA by +0.20 (p = 0.0063) on this subset. We further evaluate annotation-source variations, including manual, heuristic, and heuristic+Gemini pipelines, and find that the best structured method stays above the caption baseline across settings. We also include cross-video pair benchmarking and an appendix gallery of glyph outputs for all studied videos. Overall, the results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.

Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for video world models, where a wider sample pool may contain stronger rollouts without improving the output that is ultimately selected. We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and verification. On 192 Physics-IQ scenes, expanding the pool from 4 to 16 candidates increases oracle quality by +9.23 IQ (95% CI [+7.44, +11.14]), but Flow, Cycle, and VideoReward fail to recover this headroom reliably. Across three generators, none of twelve adaptive-depth policies outperforms uniform compute; they recover only 42-69% of the measured entry fee. A matched-60-NFE Predict-and-Perturb intervention on VideoPhy2 is likewise negative across three fresh-seed replicas. These negative results are not universal: anchor-explorer passes all four stages in a sparse PRM800K setting, MMLU-Pro exposes the gap between predictive state and useful action, and a privileged paired future establishes a positive video upper bound. Together, these results show that sampling headroom has deployment value only when it can be converted into a reliable decision whose benefit survives the complete compute charge. Code is available at https://github.com/YuhuaJiang2002/sampling-headroom-is-not-selection-gain.

Facial state analysis plays a crucial role in understanding human expressions, psychological modeling, and human computer interaction. Traditional unimodal vision-based methods are often limited by environmental sensitivity and weak interpretability. Multimodal facial state analysis addresses these issues by integrating complementary cues from visual, audio, textual, physiological, and other related modalities. This survey emphasizes two key aspects: on one hand, multimodal learning enables contextual semantic understanding for improved facial state reasoning and leverages interpretable language generation to enhance model explainability; on the other hand, multi-task learning allows simultaneous analysis of expressions, action units (AUs), and face-based soft biometrics (e.g., age, gender), effectively capturing fine-grained expressions and improving cross-scene generalization. This survey reviews core tasks, representative methods, and datasets in multimodal facial state analysis, focusing on facial expression recognition, AU detection, and face-based soft biometric estimation, and emphasizing the unique value of language in providing contextual semantics, enhancing reasoning, and generating explanations. The survey aims to provide an up-to-date overview of the literature and to highlight future research directions for multimodal, interpretable, and multi-task adaptive facial state analysis.