Papers

Large language models can produce confident but protocol-invalid answers in domains where procedural compliance is critical. This paper presents Answer Engineering, a deterministic runtime and authoring layer that applies localized rule-guided interventions to the visible reasoning trajectory during standard autoregressive generation, without retraining, modifying model weights, or performing global search. The method is evaluated on a controlled clinical benchmark for sudden sensorineural hearing loss (SSNHL), where correct management depends on protocol-consistent interpretation of symptom timing, Weber/Rinne tuning-fork findings, and otoscopic findings. In the benchmark, step-by-step reasoning shifted rather than eliminated errors: compliant outcomes for SSNHL decreased from 54.5% under unguided generation to 25.1%, while acceptance on the conductive contrast condition increased from 1.6% to 58.9%. Local trajectory editing increased SSNHL compliance to 83.5% and conductive-case adherence to 77.9%, raising balanced accuracy from 42.0% under reasoning-only generation to 80.7%. The results support a systems-level view in which protocol adherence can be improved through auditable runtime control of reasoning trajectories, while also identifying limitations caused by rule coverage, trigger reliability, and persistent diagnosis-first generation dynamics.

Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality mammography datasets for AI development remain limited in both scale and annotation richness, particularly regarding pathological subtype coverage and structured diagnostic reasoning annotations. In this paper, we present MammoExpert, the first mammography dataset with Chain-of-Thought reasoning annotations across three diagnostic phases: (i) primal observation, (ii) factual assessment, and (iii) diagnostic synthesis. Comprising 2,379 mammography images covering 67 WHO-classified histopathology subtypes, each exam provides 42 radiographic features annotated by nine senior radiologists. We evaluate its performance on the breast lesion classification task, demonstrating superior accuracy and reasonability compared to existing classification models. Combining public dataset CBIS-DDSM with MammoExpert yields 7.1% classification accuracy improvement, while the training model to learn CoT reasoning achieves another 4% gain on the MammoExpert test set. Similar improvements are observed on INBreast and Vindr datasets, where the full approach yields accuracy gains of 6.9% and 6.7%, respectively. MammoExpert can serve as a benchmark for interpretable breast lesion diagnosis through explicit CoT reasoning.

Proofreading–correcting segmentation errors in 3D brain reconstructions–is the rate-limiting step in synapse-resolution connectomics. We release ConnectomeBench2, a unified multi-species dataset of over 716,485 expert-labeled proofreading decisions with >4,500,000 associated images spanning four major open connectomes (mouse, human, zebrafish, fly), spanning both split and merge error correction. Trained on this dataset, a single Vision Transformer with shared encoders for mesh geometry and electron microscopy reaches human-level accuracy across species for split error correction and merge error identification, with performance scaling with data size and modality. Beyond accuracy, we show that the model is well-calibrated within distribution, that measures of distribution distance predict where calibration and accuracy will degrade on unseen data, and that connectomics-specific pretraining and active learning-based sample selection show potential to substantially reduce the labeling effort needed to extend to new species and brain regions. The benchmark provides the infrastructure to train and evaluate increasingly capable vision models for connectomic proofreading. Data and code availability. The ConnectomeBench2 dataset is released on Hugging Face at https://huggingface.co/datasets/jeffbbrown2/ConnectomeBench2. The accompanying codebase is available on GitHub at https://github.com/timfarkas/ConnectomeBench2.

Remote photoplethysmography (rPPG) is a camera-based technique for measuring physiological signals, particularly cardiac activity. From the remotely measured signals, heart rate can be estimated, which is crucial for health monitoring. In this study, we investigate a driver health monitoring system based on remote heart rate estimation. However, driving environments represent uncontrolled settings where videos are subject to varying illumination conditions and frequent head movements. We introduce MS-rPPG, a multi-spectral framework that combines RGB with near-infrared (NIR) face video to alleviate rPPG estimation under challenging driving conditions. To combine the complementary features from two spectral videos, we propose a cross-spectral linear modulation (CSLM) strategy based on frequency-domain analysis. Moreover, we introduce MS-Mamba, a novel state space model designed to effectively model long-range temporal dependencies while jointly capturing cross-channel interactions between multi-spectral features. We collected a real-world dataset called MS-Drive, which was recorded from 50 participants while driving the vehicle. The proposed method was evaluated on the MR-NIRP Car dataset and MS-Drive datasets. The experimental results indicate that MS-rPPG shows better robustness and heart rate estimation accuracy than previous methods, highlighting its promise for driver health monitoring. The codes are available at github.com/ziiho08/MS-rPPG.

Virtual-cell and perturbation models are increasingly used to predict cellular responses for biomedical discovery, but chemical and genetic perturbations are not automatically interchangeable. Existing evaluations often study chemical response prediction or genetic perturbation prediction separately, leaving target-matched chemical-to-genetic translation under-tested. We introduce Chem2Gen-Bench, a benchmark comprising 260,084 chemical and 1,099,045 genetic perturbation profiles organized into cell-target contexts, and evaluate pairwise alignment, retrieval, protocol covariate associations, feature spaces, and foundation-model embeddings. Across matched contexts, translation fidelity is measurable but heterogeneous; background adjustment increases the association between pairwise similarity and retrieval success, while paired tests show lower mean retrieval success after adjustment under the evaluated settings. In a target-matched K562 audit, the evaluated foundation-model embeddings did not consistently improve over gene-delta baselines. Chem2Gen-Bench provides an auditable framework for testing when chemical and genetic perturbations align around shared targets and when representation gains are supported by matched perturbation evidence.

Reliable evaluation of phrase break annotations is crucial, as subtle variations in prosodic boundaries directly affect the clarity and naturalness of speech. However, existing approaches exhibit major limitations: single-reference evaluation assumes a unique gold phrasing for an utterance despite multiple valid phrasings, while human judgment, though flexible, is labor-intensive and unscalable. To address these, we propose LLM-based Multi-Reference Evaluation (LMRE) for phrase break annotations that models the one-to-many nature of prosodic phrasing and generates multiple valid phrasings from minimal demonstrations. On a Korean testbed of 1,356 annotations covering five strategies, LMRE shows stronger alignment with human judgment than single-reference evaluation in both acceptance behavior and score correlation. Our findings demonstrate that LMRE effectively achieves both scalability and multi-reference support, highlighting the potential of LLMs for evaluation in the speech domain.

Semi-supervised learning (SSL) on data streams is challenging due to the continuous evolution of high-volume data and the scarcity of labels. Existing methods are limited in leveraging the intrinsic relationships among samples because they typically rely on fixed similarity measures or static graph structures, which cannot capture how relationships evolve over time. We propose SLeDGe, an SSL method for data streams that jointly learns a predictive model and an adaptive graph structure under strict memory and label constraints. SLeDGe maintains compact labeled and unlabeled memories using distinct update strategies, balancing rapid adaptation to novel features with the retention of historical consistency. In addition, by encouraging sparsity in the relational graph, SLeDGe filters out spurious connections and enables effective propagation of label supervision. Across 12 datasets, SLeDGe outperforms state-of-the-art competitors, achieving average relative accuracy gains of 31.7% with 0.1% labels and 14.8% with 1% labels.

Offline-to-online adaptation serves as a pivotal paradigm for mitigating the prohibitive cost of online exploration by bootstrapping reinforcement learning from offline datasets. While this paradigm has been extensively studied in single-agent settings, its extension to Multi-Agent Reinforcement Learning (MARL) remains largely unexplored, despite its critical relevance to complex coordinated decision-making. To bridge this gap, we introduce Sim2O, an elegant and minimalist framework for offline-to-online MARL. Rather than treating adaptation as a monolithic joint decision, Sim2O conceptualizes it as a compositional process. Specifically, candidate joint actions are synthesized by dynamically blending offline and online action proposals across agents. By leveraging a centralized value function to evaluate these hybrid combinations, Sim2O identifies high-value coordination strategies without requiring auxiliary training objectives or structural overhead. Empirical evaluations across diverse benchmarks demonstrate that Sim2O significantly outperforms existing baselines, underscoring that a minimalist design is not only viable but highly effective for multi-agent offline-to-online adaptation.

Large language models (LLMs) deployed for logical reasoning in knowledge-intensive domains exhibit a subtle but critical failure: coherence can be vacuously achieved through systematic abstention. A model that withholds commitment to either entailment or refutation satisfies negation consistency while providing no utility. We introduce Coherence Under Commitment (CUC), a dual-query evaluation paradigm that jointly measures consistency and decisiveness. CUC contributes three innovations: (1) a commitment score $c(\varphi) = p(\varphi) + p(\lnot\varphi)$ quantifying probability mass allocated to decisive outcomes; (2) a deterministic elicitation protocol via normalized YES/NO log probabilities, eliminating sampling variance; and (3) a 3-way decision framework (True/False/Uncertain) operationalizing the coherence-commitment trade-off into metrics. Experiments on four open-weight LLMs (1B-3B) across 204 FOLIO examples expose a sharp frontier. Qwen2.5-3B achieves near-zero contradiction ($\mathbb{E}[v_{\mathrm{neg}}]{=}0.025$) but only $7.4\%$ coverage, while TinyLlama-1.1B reaches $79.4\%$ coverage with violations on every example. Coherence-only evaluation would rank the abstaining model first; CUC exposes this as vacuous, and the frontier generalizes to LogiQA~v2 ($\rho{=}0.97$). We argue that evaluation must report both coherence and non-vacuous commitment and release a toolkit for standardized assessment.

Multi-turn jailbreaks can evade turn-level moderation by spreading unsafe intent across a dialogue through gradual escalation, reframing, and role manipulation. We address multi-turn jailbreak detection as a conversation-level classification problem and introduce an efficient hierarchical detector that avoids expensive long-context concatenation while retaining cross-turn reasoning. The model encodes individual turns to form compact turn representations and applies a lightweight conversation module that captures dialogue dynamics and selectively attends to fine-grained evidence when needed. On a challenging evaluation benchmark of 14,038 conversations, our approach achieves an F1 of 0.9394, outperforming Claude Opus 4.7, the strongest competing baseline, by 0.07 while halving its false-positive rate. Ablation studies confirm that each architectural component contributes meaningfully, with combining cross-attention and self-attention in the conversation module yielding a 2.26 percentage point reduction in false-positive rate over the self-attention-only variant.

Standard Transformers use a single self-attention pathway to model both global dependencies and local patterns, creating tension between long-range structural reasoning and fine-grained local representation learning. We propose a FiLM-coordinated dual-branch Transformer for language modeling, where each layer explicitly contains a global branch and a local branch, and feature-wise linear modulation (FiLM) is used for dynamic cross-branch coordination instead of simple concatenation or static addition. The key idea is that the two branches represent different dependency views of the same input, making channel-wise calibration more suitable than heavy token-level interaction. We therefore design a bidirectional FiLM module in which each branch generates per-channel scaling and shifting parameters to condition the other. Experiments on multiple small-scale language modeling settings show that the proposed structure consistently outperforms same-width single-branch baselines and weakened dual-branch variants under a fixed lightweight configuration. On TinyShakespeare and a 1M-character subset of WikiText-2, the full dual-branch FiLM model achieves the best results among same-width structural baselines. Multi-seed results support the stability of the gains, while mechanistic analyses show that FiLM learns input-dependent, layer-dependent, and channel-selective modulation patterns rather than static scaling. Parameter-matched widened single-branch baselines also indicate that the current design still leaves room for improvement in parameter efficiency.

Traffic prediction is a core task in intelligent transportation systems and urban-scale decision making. Despite the effectiveness of mainstream neural network-based methods, their deployment in real-world settings with thousands of traffic sensors is severely jeopardized by their poor computational scalability. To address this, the community has attempted to incorporate spatial database partitioning techniques to improve model scalability. However, these approaches rely on handcrafted geometric heuristics and often produce irregular or imbalanced data partitions, leading to boundary fragmentation, excessive padding overheads, and degraded model accuracy. In this paper, we propose SqLinear, an efficient and effective architecture for large-scale traffic prediction. First, we design Square Partition, a geometry-adaptive algorithm that partitions massive traffic sensors into balanced, non-overlapping, and compact spatial regions. Unlike existing heuristic-based designs, Square Partition is theoretically grounded and provides provable guarantees on partition utilization and split balance, establishing a high-quality foundation for downstream spatio-temporal modeling. Next, we propose a Hierarchical Linear Interaction (HLI) module that abandons the costly attention mechanisms commonly used in Transformer-based spatio-temporal models. HLI efficiently propagates global inter-region dependencies and refines them at the node level through a lightweight linear interaction scheme, enabling effective spatio-temporal modeling with linear computational complexity. Extensive experiments on four large-scale traffic datasets and 11 baselines show that SqLinear reduces MAE by 2.30% on average under the standard setting and by up to 6.78% under extreme scalability settings, while reducing training runtime by 13.27%–30.84% in spatial- and horizon-scaling scenarios.

Local LLM agents such as OpenClaw and Nanobot run on end-user machines and act on host resources - the shell, filesystem, browser, stored credentials, and messaging applications - through natural-language goals. These agents have become privileged software runtimes that mediate between user intent, model outputs, and host-level actions. Existing research characterizes the landscape through prompt injection, malicious skills, marketplace risks, or black-box evaluation of agents. But the implementation layer that performs this mediation, the prompt builder, parser, tool dispatcher, skill loader, memory writer, network client, and permission gate, has remained an unexamined safety boundary. To our knowledge, no prior work has examined the agent's source tree to audit these components for implementation-level security weaknesses. We present CLAWAUDIT, a static auditing framework for measuring vulnerability exposure in local LLM agent runtimes. CLAWAUDIT derives a five-category vulnerability taxonomy from STRIDE and develops custom static-analysis rules that target agent-specific patterns absent from established rule sets for vulnerability analysis. We instantiate the taxonomy in two backends, 47 Semgrep YAML rules and 30 CodeQL queries, and evaluate on OPENCLAWBENCH, a benchmark of 446 source-code-level advisories from the OpenClaw repository and split temporally into 229 rule-derivation (train) and 217 held-out (test) advisories. On the held-out test, CLAWAUDIT raises Semgrep recall from 21.7% (Pro baseline) to 66.8%, and CodeQL recall from 13.8% (security-extended) to 75.1%. Train/test gaps remain within 4 percentage points for all four configurations, indicating that the rules generalize to vulnerabilities unseen during rule writing. A preliminary live-code audit shows that these recall-oriented rules require manual triage, motivating semantic filtering before production deployment.

Recent advances in text-to-speech (TTS) synthesis have achieved highly natural and expressive speech generation. However, these systems are designed for general adults and overlook older adults' speech comprehension needs due to age-related sensory and cognitive decline. Prior work involves older adults by collecting preference feedback to tune model parameters. However, obtaining sufficient preference data is costly and difficult, as older adults quickly become fatigued during collection. In this paper, we propose a novel imitation learning (IL) framework to learn TTS models from expert demonstrations. We further improve Group Relative Policy Optimization (GRPO) with two-stage on-policy reward learning (OPRL) to mitigate reward hacking under limited supervision from expert demonstration. Experimental results show that GRPO w/ OPRL outperforms GRPO and supervised baselines in objective and subjective metrics. Audio samples are available at https://dongru1.github.io/demo/im-efss

Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio. We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning. Our experiments demonstrate that SER models can be reliably compromised with high attack success rates under low poisoning ratios, while maintaining near-clean performance on benign inputs. We further show that backdoor patterns exhibit strong cross-model transferability and that self-supervised representations are particularly susceptible to learning these triggers. These findings reveal that TTS technology dramatically lowers the barrier to effective backdoor attacks, exposing critical vulnerabilities in modern SER pipelines and motivating the urgent need for dedicated defenses.

Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific end-to-end designs, raising parameter and deployment overhead, or rely on transfer-based adaptations that remain externally attached and heuristic task design. A key limitation shared by both lines of work is their largely static computation pattern, which applies similar transformations across tokens despite the fact that different image regions exhibit markedly different semantic importance and complexity for machine perception. We propose MoECodec, a token-aware image compression framework that supports multiple downstream tasks within a single model. MoECodec replaces the FFN layers in transformer-based compression model token-wise Mixture-of-Experts (MoE), enabling dynamic, token-level computation conditioned on the input content and task objective. To make MoE effective in compression model, we introduce a stable routing strategy that combines expert-choice routing with spatial total variation regularization to encourage spatially coherent assignments, and we propose a lightweight expert architecture, Group Shuffle MLP (GShMLP), to control parameter growth. Extensive experiments show consistent improvement against baselines on both conventional image reconstruction and machine tasks.

AI-assisted research systems generate many failed attempts, but those failures rarely become a durable, shared knowledge asset. We propose a negative knowledge memory layer: a curator agent converts each failed attempt into a bounded, typed record in a shared bank, and a downstream research agent explicitly adopts or rejects those records before proposing its next experiment. We evaluate this layer in two settings: same-task retry on ScienceAgentBench and cross-task scientific research on two nonlinear math-physics PDE problems. The negative knowledge layer outperforms vanilla AutoResearch baselines while using fewer tokens; agents with the negative knowledge bank solve new tasks that all baselines fail to solve in PDE systems research. We also show that the previous negative knowledge bank can transfer and enhance AutoResearch on different PDE problems. These results suggest that structured negative knowledge is a knowledge asset that should be explicitly maintained in broader AI-engaged scientific research beyond a memory-compression or debugging aid, alongside positive findings, as a collective infrastructure for scientific memory. Code is available at https://github.com/hch-wang/Negative_Knowledge.

Origin-Destination (OD) demand prediction is fundamental to intelligent transportation systems, yet real-world OD flows are often dynamically sparse, long-tailed, and characterized by heterogeneous zero-flow patterns. These properties make it difficult to distinguish whether an OD connection is active from how much demand it generates once activated. Many existing methods primarily treat OD prediction as a single flow regression task, which limits their ability to model low-frequency, intermittent, and long-tailed OD interactions. To address these challenges, we propose SAGMTL, a Structure-Aware Graph Multi-Task Learning framework for dynamic sparse OD demand prediction. SAGMTL decomposes OD prediction into structural state modeling and flow intensity estimation, jointly learning regional activity states, OD connection activity, and edge-level flow intensity within a unified framework. Specifically, a node-edge collaborative representation module captures regional semantics, temporal dynamics, and spatial priors through interactive node-edge updates, producing structure-aware representations for dynamic OD interactions. Based on these representations, SAGMTL estimates OD flows by jointly modeling stable demand patterns and short-term fluctuations. A multi-constraint objective further improves sparsity awareness and structural consistency. Experiments on three real-world urban mobility datasets from Beijing, Chengdu, and Nanjing show that SAGMTL achieves superior overall performance compared with state-of-the-art baselines. Further analysis demonstrates that explicitly modeling regional activity, connection states, and flow intensity improves the robustness of dynamic sparse OD demand prediction.

The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visual grounding. Such evaluations fail to verify the expert-level lesion perception necessary to ensure the clinical reliability of VLMs. To address these limitations, we introduce CheXpercept, a sequential, multi-level perception benchmark that mirrors a radiologist's cognitive workflow across coarse-level detection, fine-level contour evaluation and revision, and semantic-level attribute extraction. To ensure high clinical fidelity at scale, we construct the dataset using a semi-automated generation pipeline paired with a review by six medical experts. CheXpercept contains 10,400 QA items derived from 2,100 CXRs, covering seven clinically critical pulmonary and cardiac lesions. To demonstrate the current landscape of VLM perception, we benchmark 14 general and medical VLMs on CheXpercept. The models achieve adequate performance only at the coarse level, with accuracy degrading precipitously on deeper visual tasks. Notably, medical VLMs show almost no perceptual advantage over their general-domain counterparts, highlighting a systemic flaw in current domain adaptation. The code and dataset will be publicly available.

As artificial intelligence advances into the era of Embodied AI, live musical interaction urgently needs to break free from the limitations of offline, unidirectional generation, achieving a "virtual synergy" capable of low-latency, dynamic interplay. To address this, this technical report presents LK_Jam, a real-time, bidirectional human-computer interactive music generation system based on a lightweight Gated Recurrent Unit (GRU) and a high-performance audio host architecture. In the algorithmic representation layer, this system abandons the computationally expensive fixed time-grid. Instead, it constructs a multi-dimensional sparse event stream integrating time-shifts, continuous harmonic embeddings, and role-aware encoding, enabling the model to accurately capture turn-taking logic and micro-timing in a single-step inference. In the engineering implementation layer, this paper builds a strict multithreaded lock-free communication bridge using C++ and the JUCE framework, incorporating the RTNeural inference engine designed specifically for real-time audio. By utilizing compile-time network topology solidification and a zero-allocation (allocation-free) mechanism, the end-to-end overhead of autoregressive decoding is strictly locked at \(O(1)\) complexity, structurally mitigating the risk of audio thread dropouts in DAW plugin environments. Furthermore, this study designs a three-stage progressive training strategy, achieving a leap from basic chord harmonization to expert-level interaction. Preliminary observations and architectural analysis demonstrate that while ensuring musical coherence and interactive role-play, the proposed system successfully challenges extreme real-time engineering constraints, offering a highly robust and deployable technical paradigm for next-generation AI co-performers in live music.

Organizations deploying AI face two fundamental governance challenges: managing AI risk and sustaining AI value. Both depend on evidence whose sufficiency cannot be taken for granted. We call the shared underlying challenge the AI Evaluability Gap: the condition in which organizations lack sufficient evidence to support high-confidence governance decisions regarding either risk or value. We argue that this gap reflects a category error in current practice. Existing governance approaches focus primarily on properties of systems, such as safety, fairness, reliability, compliance, and value, while paying comparatively little attention to the evidentiary foundations required to justify decisions about those properties. We further argue that AI governance encompasses both operational decisions regarding whether a system may operate and investment decisions regarding whether it merits continued organizational resources. To address this problem, we introduce Evaluability, defined as the capability of a system to generate, maintain, and renew evidence sufficient to support high-confidence governance decisions over time. We formalize governance decisions as functions of calibrated confidence Conf(D|E) and identify six properties of evaluable evidence: observability, attributability, intervenability, verifiability, calibration, and temporal validity. The framework distinguishes Operational Certification, which relies primarily on structural evidence to justify deployment decisions, from Investment Certification, which relies primarily on causal evidence to justify continued resource allocation. We argue that evidence sufficiency is a missing layer of AI governance and that closing the AI Evaluability Gap is a prerequisite for both managing risk and sustaining value in AI-enabled organizations.

Forecasting future events is a critical challenge for large language model (LLM) agents, spanning domains from elections and monetary policy to financial markets. However, evaluating progress on this task presents a fundamental trade-off between efficiency and environment fidelity. While live evaluation benchmarks suffer from an inherently slow feedback loop, existing retrospective replays typically restrict agents to static, pre-frozen databases that sacrifice the environmental realism of actual deployments. To tackle this issue, we introduce Agentic Time Machine (TM), an infrastructure that approximately reconstructs the web state at any chosen past time by filtering post-cutoff content. Leveraging this evaluation infrastructure, we further propose a planner-solver-aggregator multi-agent framework that breaks each question into diverse analytical angles, gathers evidence in parallel, and combines the results into a single forecast. Experiments show that offline scores under TM correlate strongly with live FutureX scores, validating that TM offers a fast and reliable sandbox for forecasting-agent evaluation. On FutureX-Past and Polymarket evaluated under TM, our framework achieves the highest score among strong closed-book, tool-augmented, and self-consistency baselines. On the official FutureX live leaderboard, our system achieves the best average rank over four consecutive weeks, including 1st place in May Week 1. As of June 17, it also ranks 1st on FutureX's official eight-week overall leaderboard.

A self-determining system is defined as one in which causes originating within the system influence the system itself. This definition raises the question of how to specify system boundaries. Although the concept of "closure" is commonly used for this purpose, defining boundaries solely in terms of causal relations introduce challenges, such as how to handle external causes and circular causality. To address this issue, we introduce two types of asymmetric relations: causal and constitutive. We propose that system boundaries can be defined as closures of loops formed by these relations, referred to as causal-constitutive loops. By constraining constitutive relations, the resulting system necessarily includes internal causes and thereby satisfies self-determination. Furthermore, to prevent reduction to supervenience, constitutive relations must involve at least two independent variables. This minimal requirement leads to two interdependent loops, which implies a dual-process organization.

We introduce a benchmark that is fully self-contained, needs no ground truth, and rises with the models it measures. Language models compete at making analogies and subjectively grade one another; nothing enters from outside. The benchmark reproduces GPQA Diamond, a keyed benchmark of expert-written questions, at r = 0.98, audited for a leak and found clean. We hypothesize that both benchmarks measure the same thing in different ways: a language model holds its knowledge as archetypal contexts, relationship patterns valid across many topic domains. GPQA instantiates the required knowledge in one domain; the Metanym Game instantiates one archetype into several domains, generating analogies, no reasoning required. The reasoning feature of an LLM hardly changes the game's ratings, while it lifts GPQA, which requires derivations. In the game, a player writes a context template whose slots, filled with a set of keywords from a topic domain, instantiate a factually true description of that domain; the instantiations are each other's metaphors, and keywords filling the same slot are metanyms, metaphorically synonymous. Correctness is settled sentence by sentence. Ground truth is replaced by the SVD of the factual rating matrix: its left and right singular vectors rate the players as judges and as generators, two ratings from one factorisation, to our knowledge a first for an LLM council of peers. On the subjective criteria, judges are weighted by their rating consistency under a swept calibration anchor. Generating and judging are different skills: on this roster the strongest generators were middling judges. A council of the five best issues the official ratings; its contestable seats keep it current, a candidate steering signal for self-improving AI. The paper is accompanied by a validating package that recomputes every number.

Scientific discovery workflows often depend on structured curation from the literature. This is difficult for current agents because the key evidence is scattered across long text, dense tables, and figures, and the final records often require reasoning across multiple evidence fragments rather than copying a single span. We study scientific curation from multimodal sources and introduce Beaver, an agent harness that extracts structured information from scientific papers while preserving provenance to the supporting evidence. Beaver combines a frontier agent with multimodal evidence tooling, task scaffolding, and artifact-grounded autoresearch. These components turn curation into a staged, auditable workflow and enable an iterative evaluate–diagnose–revise loop, where persistent run artifacts expose stage-localized failures and guide harness updates. Experiments show that Beaver reaches 81.0 on Gold-Referenced Attribute Score (GRAS), an attribute-level measure of agreement with gold curated records, outperforming frontier agents by over 23 absolute points. Ablations show that task scaffolding, multimodal evidence tooling, and provenance traces each contribute meaningfully to performance, while attribute-level analysis shows the largest gains on high-value attributes that require cross-modal reasoning and normalization. These results show that, for scientific curation from papers with multimodal evidence, harness design is a central determinant of agent performance.

Biomedical deep-research systems increasingly retrieve and synthesize scientific evidence, but their outputs typically collapse heterogeneous evidence into static text, making provenance difficult to inspect and reuse. We formulate evidence-centered biomedical knowledge discovery, where disease-associated protein signals are transformed into a structured evidence state connecting proteins, pathways, publications, interactions, claims, and uncertainty. We introduce BioInsight, a provenance-preserving multi-agent orchestration framework built around typed artifact contracts and an independent Search Agent that decouples evidence acquisition from downstream mechanistic reasoning, supporting both the citation-grounded report and an interactive evidence workspace, without independently regenerating evidence for visualization. We evaluate BioInsight on standardized biomedical QA, challenging protein-function reasoning, and end-to-end biomedical evidence synthesis. The results demonstrate that BioInsight achieves better traceability and ranking performance than standard search-augmented baselines, and suggest that biomedical AI systems should move toward provenance-preserving, interactive evidence artifacts.

Protein-peptide interactions are central to cellular regulation and peptide-based drug discovery, yet existing computational methods mainly focus on interaction classification, binding-site prediction, or peptide binder generation. These formulations provide limited insight into the physicochemical mechanisms that determine how a peptide binds to a protein. In this work, we introduce PepLLM, an instruction-tuned framework for structured protein-peptide interface understanding. Given protein-peptide sequences, PepLLM generates a machine-readable JSON annotation describing multiple interface properties, including peptide burial state, hydrogen-bond density, salt-bridge presence, hotspot residues, hydrophobicity, and electrostatic complementarity. To support this task, we construct a new protein-peptide interface dataset by integrating structural interface analysis, solvent-accessible surface area computation, hydrophobic burial estimation, electrostatic potential calculation, and redundancy-aware data splitting. PepLLM connects a pretrained ESM encoder with a LLaMA decoder through a nonlinear modality adapter. The adapted ESM residue embeddings are injected into the LLaMA prompt as continuous soft tokens via placeholder-token replacement, enabling the decoder to generate structured interface annotations under instruction tuning. By moving beyond single-label prediction toward multi-property and mechanism-aware generation, PepLLM establishes a new task and modeling paradigm for interpretable protein-peptide interface analysis.

Poultry production operates under tightly coupled environmental and biological dynamics, yet commercial climate control remains largely heuristic, limiting welfare assurance and operational efficiency. We introduce an edge-cloud digital twin framework for real-time, welfare-constrained environmental control in poultry facilities. The framework integrates distributed sensing, on-device state estimation, a hybrid physics-data model, and model predictive control to enable anticipatory and adaptive management under practical farm constraints. A grey-box thermodynamic and mass-balance formulation is augmented with a learned residual that captures unmodeled biological variability, including activity-dependent metabolic heat. This hybrid model is embedded within a state-space representation for real-time estimation and control at the edge, while cloud coordination supports cross-farm learning and long-horizon optimization. Bandwidth-aware processing and asynchronous synchronization enable deployment in connectivity-limited environments. Evaluation in a high-fidelity broiler production testbed demonstrates substantial gains over rule-based control and physics-only modeling. Temperature prediction error is reduced from 1.8 degrees Celsius to 0.4 degrees Celsius, ammonia constraint violations decrease by 90 percent, and communication requirements are lowered approximately 30-fold through edge-first processing. A Domain Transfer Score of 0.92 further indicates strong robustness across facility conditions. These results show that physically grounded digital twins, coupled with real-time control, enable scalable and welfare-aware management of biological production systems.

Sri Lankan parliamentary debates (Hansards) constitute a trilingual corpus of speeches in Sinhala, Tamil, and English, including code-mixed content, yet remain inaccessible to standard NLP pipelines due to layout-complex PDFs, multilingual scripts, and agglutinative morphology. We present an end-to-end framework that addresses these challenges through LLM-based text extraction followed by a multilingual embedding and density-based clustering pipeline for topic modeling. A hybrid semantic-lexical extension, BiTopic, is further explored to improve interpretability and recover speeches otherwise discarded as noise. Applied to 19,553 speeches spanning 2017-2026, the pipeline recovers 30 macro-topics achieving a cluster purity (BCP) of 0.673, whose temporal trajectories align unsupervised with major national events including the 2019 Easter Sunday attacks and the 2022 economic crisis. Traditional LDA fails on this corpus due to cross-lingual fragmentation, whereas the proposed approach successfully identifies thematic structure across all three languages without supervision.

We examine how hadith computational science is being reshaped by transformer models, retrieval-grounded pipelines, and large language models (LLMs). Recent reviews document growth in the literature, but they do not yet provide a critical account of which advances are methodologically robust, which remain benchmark-bound, and which unresolved problems still limit scholarly use. We address this gap through a critical narrative review that combines critique of existing reviews, paper-level appraisal of representative original studies, and synthesis of Islamic scholar and domain-expert perspectives on authenticity, authority, and responsible use. We find uneven progress. Data resources have expanded, segmentation tasks have matured, narrator and source-verification problems are better formalized, and LLM-assisted workflows now support corpus-scale enrichment, multilingual access, and grounded evaluation. At the same time, progress remains constrained by narrow corpora, weak benchmark comparability, synthetic-to-real transfer gaps, narrator identity resolution, preprocessing fragility, limited reproducibility, and sparse expert-grounded validation. We show that important gaps lie beyond dominant benchmarks: non-canonical and obscure corpora, commentary and explanatory literature, cross-source links with Qur'an and seerah, and fiqh-facing evidence support. We argue that hadith computation should be assessed less as isolated model performance than as an evidence infrastructure problem requiring knowledge integration, provenance, and expert supervision. On this basis, we define a research agenda for making the field methodologically stronger and more useful to Islamic scholarship.