Search research

Analysts in Security Operations Centers query massive telemetry streams using Kusto Query Language (KQL), but writing correct KQL demands specialized expertise that bottlenecks scaling security teams. We investigate how Small Language Models (SLMs) can enable accurate, cost-effective translation from natural language queries (NLQs) to KQL. We propose a three-knob framework spanning prompting, fine-tuning, and architecture. First, we adapt NL2KQL for SLMs with lightweight retrieval and introduce error-aware prompting that targets common parser failures with a handful of mined tips, at a fraction of the tokens KQL's full rule set would require. Second, we apply LoRA fine-tuning with rationale distillation augmenting each NLQ-KQL pair with a brief chain-of-thought to transfer teacher reasoning. This yields an informative negative result, as neither variant surpasses targeted prompting. Third, we propose a two-stage architecture pairing an SLM drafter with a low-cost LLM judge for schema-aware refinement. We evaluate nine models (five SLMs, four LLMs) on syntax correctness, semantic accuracy, table selection, filter precision, latency, and token cost. On Microsoft's NL2KQL Defender Evaluation dataset, our two-stage approach reaches 0.987 syntax and 0.906 schema-valid ("semantic") accuracy, exceeding every baseline we run under equivalent infrastructure, and it generalizes to independently authored queries over the same schema (0.964 syntax, 0.831 schema-valid). The only baselines within 0.05 schema-valid are NL2KQL+GPT-4o (0.878) and NL2KQL+GPT-5 (0.861), which cost USD 2.998 and USD 2.018 for 230 queries against USD 0.213 for ours, a 9.5-14x reduction at matched accuracy. These results establish SLMs as a practical foundation for natural-language querying in security operations.

While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual information such as social norms, user intent, or natural language instructions. To address this limitation, this manuscript introduces an agentic MPC framework that enables context-aware, semantically adaptive control synthesis by integrating with large language model-based agents. The agent interprets heterogeneous inputs, including natural language messages, environmental observations, and external knowledge, to resynthesize the control specifications. The effectiveness of the framework is demonstrated in an autonomous driving scenario, where the system aligns with personal preferences or responds to social situations such as emergency vehicle yielding.

Certified program synthesis (aka vericoding) is the process of automatically generating a program, its formal specification, and a machine-checkable proof of their alignment from a natural-language description. Two challenges make vericoding difficult. First, specifications synthesised from natural language are often either too weak to be meaningful or too strong to be implementable, yet existing approaches lack systematic means to detect such defects. Second, the landscape of program verifiers is fragmented: each tool supports a particular reasoning mode -- auto-active (e.g., Dafny, Verus) or interactive (e.g., Coq, Lean) -- with its own trade-off between automation and expressivity. This forces every synthesis methodology to be tailored to a single verification paradigm, limiting the class of tasks it can handle effectively. We overcome both challenges by structuring the certified synthesis workflow around a multi-modal verifier -- a single tool combining dynamic validation, automated proofs, and interactive proof scripting in one foundational framework. We realise this idea in LeetProof, an agentic pipeline built on Velvet, a multi-modal verifier embedded in Lean. Multi-modality enables LeetProof to validate generated specifications via randomised property-based testing before any code is synthesised, decompose the synthesis task into sub-problems guided by verification conditions, and delegate residual proof obligations to frontier AI provers specialised for Lean. We evaluate LeetProof on benchmarks derived from prior work on certified synthesis. Our specification validation uncovers defects in existing reference benchmarks, and LeetProof's staged pipeline achieves a significantly higher rate of fully certified solutions than a single-mode baseline at the same budget -- consistently across two frontier LLM backends.

Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). However, current approaches to generating code world models rely on frontier models and inference-time refinement loops, limiting accessibility and scalability. This work investigates whether GameCWM generation capabilities can be distilled into smaller models through post-training. We introduce: (1) a curated dataset of 30 games spanning perfect and imperfect information games, (2) a verification framework that evaluates generated code against structural and semantic game properties, and (3) a post-training pipeline combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR). We experiment with Qwen2.5-3B-Instruct and find that SFT can increase syntactic correctness, while RLVR can improve execution-level adherence to game rules, thereby improving Qwen's ability to generate valid GameCWMs in both perfect and imperfect information games. Overall, our pipeline makes Qwen2.5-3B-Instruct more capable of generating valid GameCWMs, thereby offering a scalable path toward automatic environment generation from natural language.

Introduction: NICE guidelines provide evidence-based recommendations for clinical care but remain largely in unstructured natural language. Existing approaches to converting them into computable representations often focus on individual diseases, require substantial manual encoding, and do not scale. Large language models (LLMs) may enable much of this translation to be automated. Methods: We present an end-to-end approach that converts textual clinical guidelines into executable models capable of generating explainable, patient-specific recommendations. A stepwise LLM-based transformation with in-context examples produces human-inspectable intermediate artifacts. We apply the approach to NICE pancreatic and lung cancer guidelines, use expert review to assess rule alignment, and evaluate the executable pancreatic cancer model on 20 patient vignettes. Results: Expert review showed strong alignment between the source guidelines and generated executable models. Most discrepancies were partial omissions rather than incorrect logic, while hallucinated or fundamentally incorrect rules were rare. On the patient vignettes, the executable model achieved an F1 score of 82.5%. Conclusion: LLMs can transform natural-language NICE guidelines into interpretable, executable models that preserve guideline structure, support transparent inspection and modification, and generate patient-specific recommendations. These findings demonstrate the feasibility of scalable automated generation of computable clinical guidelines.

Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding human oversight. Here, we study the emergent languages on Moltbook. For this, we build upon the Moltbook Files dataset and apply a two-stage approach consisting of a rule-based heuristic (about 6000 matches) followed by zero-shot classification (518 kept). The resulting categories include token efficiency (166), new natural languages (106), and oversight evasion (59). We conduct both quantitative and qualitative analyses. Our results show that posts proposing new languages for avoiding oversight are judged by DeepSeek-3.2 as being less aligned than the other categories and that all languages can be learned by other language models in-context merely from a description of the language. Moreover, manually studying exemplary cases reveals surprisingly sophisticated steganographic protocols like embedding hidden messages in natural language. Although we cannot be certain about the extent of autonomy in ideation of these languages, our results add up to the evidence that monitoring surface behavior may soon be insufficient for retaining control over agent populations.

Domain-specific languages (DSLs) are widely used for managing operating system security policies, yet manually authoring rules in such languages demands high expertise and is error-prone. This paper formalises the task of automatic DSL code generation from natural language descriptions - Text2DSL - as a distinct problem class, separate from Text-to-SQL and general-purpose code generation. We introduce the PolkitBench dataset comprising 4,204 verified natural-language-to-Polkit-rule pairs, each validated through a three-level AST-based pipeline. Controlled prompt experiments on two MoE models of different scale and provenance - GigaChat-10B-A1.8B (1.8B active parameters) and Nemotron-3-Nano-30B-A3B (3B active) - demonstrate the critical role of structured context (BNF grammar, API specification, permitted identifier vocabulary) for LLM-based DSL code generation. Across both models, supplying context raises syntactic validity to 98.6-99.4%, structural validity by +9.7 to +35.5 pp, and the CodeBLEU score by +60% to +95%. The consistency of the effect across models of different scale and provenance indicates that, for the Text2DSL class of problems, injecting a formal target-language specification into the prompt context is a robust enabling factor for high-quality generation without model fine-tuning.

The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on certain tasks can be further enhanced by incorporating test-time reasoning techniques. These inference-time advances have been adopted into the code domain, enabling complex software engineering (SWE) tasks such as code generation, test generation and issue resolution. However, the impact of different reasoning techniques on code-centric SWE tasks has not been systematically explored. In this work, we survey code reasoning techniques that underpin these capabilities, with a focus on test-time compute and inference-time reasoning paradigms. We examine a variety of code-specific reasoning methods and progressively build up to SWE agents, which combine planning, tool use, and multi-step interaction. We also compare the impact of different techniques on coding tasks, highlighting their relative importance and outlining open challenges and future research directions. Across commonly used models and benchmarks, we find that approaches exploiting code-specific signals (e.g., structure and execution feedback) are frequently associated with improved performance, motivating a dedicated study of code reasoning beyond natural-language reasoning.

Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small number of examples; in instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description before making predictions. Each of these procedures may be thought of as invoking a different form of reasoning: instruction following involves deductive reasoning, few-shot prompting involves inductive reasoning, and instruction inference involves abductive reasoning. How do these different capabilities relate? Across four LMs (from the gpt and llama families) and two learning problems (involving arithmetic functions and machine translation) we find a strong dissociation between the different types of reasoning: LMs can sometimes learn effectively from few-shot prompts even when they are unable to explain their own prediction rules; conversely, they sometimes infer useful task descriptions while completely failing to learn from human-generated descriptions of the same task. Our results highlight the non-systematic nature of reasoning even in some of today's largest LMs, and underscore the fact that very different learning mechanisms may be invoked by seemingly similar prompting procedures.

Molecular function is largely determined by structure. Accurately aligning molecular structure with natural language is therefore essential for enabling large language models (LLMs) to reason about downstream chemical tasks. However, the substantial cost of human annotation makes it infeasible to construct large-scale, high-quality datasets of structure-grounded descriptions. In this work, we propose a fully automated annotation framework for generating precise molecular descriptions that preserve complete structural details at scale. Our approach builds upon and extends a rule-based chemical nomenclature parser to interpret IUPAC names and construct enriched, structural XML metadata that explicitly encodes molecular structure. This metadata is then used to guide LLMs in producing accurate natural-language descriptions. Using this framework, we curate a large-scale dataset of approximately $163$k molecule--description pairs. A rigorous validation protocol combining LLM-based and expert human evaluation on a subset of $2,000$ molecules demonstrates a high description precision of $98.6$%. The proposed annotation framework is readily beneficial to broader chemical tasks that rely on structural descriptions, with the resulting dataset providing a reliable foundation for molecule--language alignment. The source code and dataset are hosted at https://github.com/TheLuoFengLab/MolLangData and https://huggingface.co/datasets/ChemFM/MolLangData, respectively.

Neural Source Code Summarisation (NSCS) aims to generate natural language summaries of source code to improve developers' and maintainers' understanding of code. Source code summaries are vital during the maintenance phase of the Secure Software Development Lifecycle (SSDLC), as they improve maintainers' understanding of code and help reduce the number of bugs and vulnerabilities in a software system. However, summaries are often missing, incomplete, or outdated in many software systems. Solutions to this problem use small, task-specific Transformer models or code-aware Large Language Models (LLMs). Task-specific Transformer-generated summaries often score well across many natural language generation (NLG) metrics, but these metrics reward lexical overlap rather than summary quality. Conversely, the ability of LLMs to capture semantics and produce high-quality summaries presents an exciting solution to this problem. This is especially relevant given the increased availability of LLMs and improvements in workstation hardware in recent years, which mean that some LLMs can now be run on developers' workstations. However, because of their abstractive nature, LLM-generated code summaries often differ greatly from developer-written summaries in the words and phrases they use, resulting in low scores across NLG metrics. We show how combining these two methods, by using Transformer-generated summaries in prompt engineering, may enable LLMs to create better source code summaries and help software practitioners maintain secure systems. We prompt four LLMs using four different prompts, with a task-specific Transformer used to assist the LLMs within the prompts. We present "Transformer-Assisted LLM-Based Source Code Summarisation", a method through which we observe an improvement of 7.8% in BLEU-4 and 5%.

Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation decisions in complex traffic environments. Recent advances in large vision-language models offer a powerful new paradigm for these tasks by combining high-capacity visual understanding with flexible natural language reasoning. In this work, we introduce PedestrianQA, a large-scale video-based dataset that formulates pedestrian intention and trajectory prediction as question-answering tasks augmented with structured rationales. PedestrianQA expresses richly annotated pedestrian sequences, in natural language, enabling VLMs to learn from visual dynamics, contextual cues, and interactions among traffic agents while generating concise explanations of their predictions without needing specialized architectures tailored for each task. Empirical evaluations across PIE, JAAD, TITAN, and IDD-PeD show that finetuning state-of-the-art VLMs on PedestrianQA significantly improves intention classification, trajectory forecasting accuracy, and the quality of explanatory rationales, demonstrating the strong potential of VLMs as a unified and explainable framework for safety-critical pedestrian behavior modeling.

Visual Language Navigation (VLN) aims to enable an embodied agent to navigate complex environments by following natural language instructions. Recent approaches build semantic spatial maps and leverage Large Language Models (LLMs) for reasoning and decision making. Despite these advances, existing systems lack instance-level object detail and robustness to diverse user queries, limiting reliable navigation in complex indoor environments. To address these limitations, we propose Instance-Enriched Semantic Maps, a unified framework with three key contributions: (1) Instance-level two-and-a-half-dimensional (2.5D) rich information mapping that constructs maps from color and depth observations via open-vocabulary panoptic segmentation, preserving vertical distinctions and capturing small objects, while storing diverse semantic attributes and natural language captions enriched with room-level context. (2) Robust query processing via LLM-based target selection, which dynamically routes queries across type-specialized experts and integrates their outputs through score-level fusion, enabling consistent goal selection across diverse query formulations. (3) Storage-efficient semantic representation that achieves approximately 96% reduction compared to three-dimensional (3D) scene-graph approaches while preserving sufficient spatial information for navigation. The proposed 2.5D representation outperforms the 3D baseline by over 27% in prediction-normalized Area Under the Curve (AUC). In navigation experiments, our method achieves over 17% improvement in object retrieval and over 23% in navigation success compared to the baseline across diverse query types. The project page is available at https://rcilab.github.io/iesm_vln.

Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate plausible but incorrect statements, and no existing approach systematically tests whether such explanations are faithful to the underlying environment. Two classic software testing challenges stand in the way: there is no oracle for the correctness of an explanation, and the test inputs, natural language queries about a policy's behavior, lack the structure needed for systematic test case generation. We address both. Probabilistic model checking provides the test oracle, computing exact reference results against which LLM answers are graded automatically. A taxonomy of post hoc query categories structures the input space around the environment-level facts from which policy explanations are composed; test cases generated from it are prioritized by question-specific diagnostic difficulty scores. Across seven MDP environments, the testing separates three open-weight LLMs: a reasoning model passes 85% of test cases, a mid-size model 70%, and a 1B model falls below the random baseline, while prioritization surfaces significantly harder cases than random selection. Our results indicate how trustworthy LLM-generated explanations are in model-free settings, where the same LLMs are used but no oracle exists to verify them.

Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two tables under a natural-language predicate, can be evaluated with a large language model (LLM), but comparing every pair of tuples requires O(M x N) LLM invocations and is cost-prohibitive at scale. Existing systems reduce this cost but typically commit to a single fixed strategy (e.g., embedding similarity or one batched scheme) regardless of the data or the join predicate. We propose an LLM-agent-based decision pipeline that optimizes semantic joins by matching the execution strategy to the characteristics of the underlying tables. An LLM advisor routes each join to one of two strategies: a Cluster Join, which prunes candidates via unsupervised embedding clustering and sample-based filtering, or a Classifier strategy for predicates that reduce to a shared discrete label set. Across three diverse datasets (IMDb reviews, email contradictions, and Stack Overflow tags), the advisor consistently identifies the optimal execution strategy for each workload. This dynamic routing proves decisive: it outperforms adaptive block join (ABJ) by 20-33 F1 points across all datasets while consuming fewer tokens on two of the three, and achieves higher F1 scores than featurized-decomposition join (FDJ) at one to two orders of magnitude lower token cost.

The emergence of Large Language Models (LLMs) has inspired the vision of generating bespoke crystal materials directly from natural-language instructions, enabling users to design materials through intuitive, conversational interaction. Existing text-to-crystal generative models represent important early steps toward this goal, but they suffer from two critical limitations: (i) restricted input formats that require highly structured descriptions (e.g., chemical formulas), and (ii) one-directional generation, where models can map text to crystal but cannot perform the inverse. These limitations prevent fully conversational workflows and hinder alignment with users' inherently ambiguous and evolving desiderata. We address these challenges with LapidaryEngine, the first model to support fully conversational crystal generation. LapidaryEngine accepts free-form natural-language requests and performs iterative refinement and editing in a dialogue-like manner. The key innovation is a pivot representation, a third, intermediate form that enables bidirectional translation between text and crystal structures despite the absence of direct paired datasets. Leveraging this pivot allows robust interpretation of user feedback and precise structural control. We demonstrate LapidaryEngine across diverse tasks, including insulator discovery, stability optimization, compositional modification, and structural editing, showcasing its ability to align generated materials with user intent in an interactive manner.

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined objectives, tightly coupling each attack to a specific model or task, which restricts their scalability and flexibility in real-world scenarios. In this work, we present DarkLLM, a novel attack framework that trains an LLM to translate natural-language attack instructions into latent attack vectors, which are then decoded into visual adversarial perturbations. By leveraging natural-language instruction tuning, DarkLLM not only unifies targeted, untargeted, segmentation, and multi-model attacks within a single framework, but also achieves flexible and controllable adversarial generation, enabling each instruction to produce a perturbation that induces desired behaviors across heterogeneous models. Through extensive experiments across 4 tasks, 13 datasets, and 15 models, we demonstrate that DarkLLM with only 1B parameters can follow attacker instructions and generate highly effective attacks against CLIP, SAM, and frontier LLMs, revealing a systemic vulnerability in modern foundation models.

Forecasting human life outcomes is important to gain insights into how individuals attain long and healthy lives. Conventional statistical approaches yield limited accuracy, potentially due to discarding the sequential structure of the life course. Modern methods such as transformer architectures require large scale training data that most longitudinal panel studies lack. Here we introduce LifeSentence, a model for life-course reasoning that bridges large language models with longitudinal panel data. By representing each life event as a structured natural-language record and instruction-tuning a pretrained 24-billion-parameter language model across an 18-task evaluation taxonomy spanning prediction, robustness and reasoning, LifeSentence supplements panel data with distributional knowledge already encoded during pretraining. Trained on approximately 65,000 individuals from the German Socio-Economic Panel - roughly 45 times fewer than prior transformer-based approaches - LifeSentence outperforms classical and deep learning baselines across all task families, achieving a threefold improvement in joint event-and-timing prediction from best baselines and 91.2% Kendall's tau when reconstructing chronological order from timestamp-stripped event sets. Without explicit supervision, the model recovers documented patterns of social stratification, including the education premium, the gender wage gap and the motherhood penalty, from discrete event sequences alone. A natural-language interface further enables qualitatively new research queries, such as connecting an early-life history to a specified late-life endpoint, establishing LifeSentence as both a predictive tool and a probe for counterfactual exploration of human biographies.

For robotics to be effectively integrated into household or industrial environments, machines must adapt to natural-language prompts in real time. Although Vision-Language Models (VLMs) have enabled zero-shot generalization in robot task and motion planning (TAMP), current state-of-the-art approaches often remain computationally "heavyweight" or require extensive training on thousands of demonstrations. We present GRASP (Grounded Reasoning and Symbolic Planning), a framework designed as a step toward open-vocabulary tabletop manipulation. Our approach leverages a pretrained VLM to translate natural-language queries into neuro-symbolic goal states, grounded in the physical world via a bounding-box detection pipeline. Unlike methods that rely on fixed color lists or hard-coded coordinates, GRASP enables robots to interpret abstract spatial concepts such as "top shelf" and execute tasks without additional fine-tuning. We achieve 73.3% overall success across 90 real-robot trials at three difficulty levels, requiring no task-specific training.

Active perception - the ability of a robot to proactively select viewpoints to acquire task-relevant information - is essential for robust operation in real-world environments. However, existing approaches are typically limited to fixed objectives or constrained settings, and struggle to generalize to open-ended perception intents specified in natural language. We propose I-Perceive, a foundation model for language-conditioned active perception in large-scale indoor environments. Given a query image, a set of context images, and a natural language instruction, I-Perceive predicts a 6D camera pose that fulfills the specified perception intent. The model integrates a vision-language pathway for semantic grounding with a geometric reasoning pathway for multi-view 3D understanding, connected via multi-layer semantic fusion to enable language-conditioned geometric reasoning. To support scalable training, we construct a large-scale dataset of language-viewpoint pairs from both real-world scene-scanning data and simulated environments using an automated pipeline. Extensive experiments demonstrate that I-Perceive significantly outperforms strong baselines on prediction accuracy, viewpoint feasibility, and instructions alignment. The model exhibits strong zero-shot generalization to unseen scenes and instructions, and enables closed-loop active perception, progressively refining viewpoints over sequential interactions.

Multimodal Sentiment Analysis (MSA) aims to interpret complex human emotions by integrating natural language with non-verbal modalities. Non-verbal modalities share a structural isomorphism with natural language, as both can be viewed as feature sequences evolving over time. This isomorphism enables the transformation of non-verbal modalities into text-like tokens for unified semantic reasoning. Large Language Models (LLMs), designed to understand and generate sequential data, can thus be utilized to interpret complex affective sequences. However, existing LLM-based methods primarily capture low-level superficial features, failing to model affective semantics arising from structural variations and contextual interactions. To address this limitation, we propose \textbf{SentiLLM}, a unified framework that leverages \textit{Semantic-Aligned Structural Abstraction} to distill continuous raw signals into compact, semantically meaningful tokens. Specifically, we introduce a \textit{Dual-Stream Salience-Context Calibration Mechanism}, which disentangles non-verbal feature sequences into a focus stream and an ambient stream. The focus stream captures salient sentiment shifts (e.g., facial expressions) guided by textual priors, while the ambient stream characterizes stable background states. Through calibrating these dynamic sentiment shifts against background states, SentiLLM effectively projects non-verbal modalities into a unified semantic space, making them naturally understandable for LLMs. Serving as a plug-and-play module, SentiLLM significantly improves discriminative performance with only a small number of trainable parameters. Our method achieves superior performance on four datasets, MOSI, MOSEI, CH-SIMS, and CH-SIMS v2, demonstrating the effectiveness of the structural abstraction paradigm in MSA. Our code is available at: \href{https://github.com/especiallyW/SentiLLM}.

Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing ease. Yet, real-world deployment remains challenging, especially in complex or unseen schemas, due to inconsistent accuracy and the risk of generating invalid SQL. We introduce Template Constrained Decoding (TeCoD), a system that addresses these limitations by harnessing the recurrence of query patterns in labeled workloads. TeCoD converts historical NL-SQL pairs into reusable templates and introduces a robust template selection module that uses a fine-tuned natural language inference model to match or reject queries efficiently. Once the template is selected, TeCoD enforces it during SQL generation through grammar-constrained decoding, implemented via a novel partitioned strategy that ensures both syntactic validity and efficiency. Together, these components yield up to 36% higher execution accuracy than in-context learning (ICL) and 2.2x lower latency on matched queries.

LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model computation. We introduce the term ``linguistic illegibility'' to broadly refer to scenarios in which an LLM's externalized or mechanistically-probed language artifacts fail to represent how the model actually thinks. We argue that the specter of linguistic illegibility is unavoidable for LLMs whose internal computations are not directly expressed via language, but rather math over activation spaces (with lossy translations between activation spaces and natural language happening at the bookends). If linguistic illegibility is always possible, then security mechanisms that rely on a model's linguistic self-reporting (e.g., chain-of-thought monitoring, constitutional self-critique, activation probing for linguistically-defined feature vectors) can never be completely sound; the model sandbox will always need isolation techniques whose guarantees do not depend on reading a model's linguistic state at all. We argue that observing a model's outputs using taint tracking is a promising approach for an effective sandbox: regardless of how a model linguistically self-reports, a taint tracking policy can define, a priori, various pieces of system state that should never be influenced by model-produced data. We also discuss several additional sandboxing mechanisms (e.g., robust virtualization, third-party auditing of sandboxing configurations) which collectively provide a critical floor beneath linguistic monitoring, and would have mitigated recent sandbox exploits by frontier models.

Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols, both of which lack interpretability. To address these limitations, we introduce Natural Language Inference Constraint Verification (NLICV), a scalable, semantically invariant framework that maps sentence meanings to truth-condition sets to verify personalization constraints via a Natural Language Inference (NLI) model. Moving beyond binary scoring, NLICV categorizes LLM behaviors into four distinct modes: personalization, generalization, sycophancy, and failure. Extensive experiments demonstrate that NLICV aligns closely with human annotations while drastically reducing the latency and token costs associated with LLM judges (up to 2100 inference speedup). Finally, through an ablation-based procedure, NLICV pinpoints the exact sentences driving the constraint verification, yielding faithful, understandable evidence for its evaluations.

Large language models have shown impressive capabilities in code generation, yet they often produce functionally incorrect code. Uncertainty quantification (UQ) methods have emerged as a promising approach for detecting hallucinations in natural language generation, but their effectiveness for code generation tasks remains underexplored. We systematically evaluate how UQ techniques transfer to code generation across three programming languages, five LLMs, and over 1,700 problems. We find that some token-probability-based methods generalize effectively without modification, while sampling-based methods relying on natural language inference (NLI) fail because NLI models cannot distinguish functionally different code, causing most responses to collapse into a single semantic cluster. To address this, we introduce functional equivalence methods, a family of code-specific methods that replace NLI-based semantic equivalence with an LLM-based functional equivalence assessment, including functional entropy, a code-specific analog of semantic entropy. Functional equivalence methods achieve top AUROC in 11 out of 15 model-benchmark combinations and the best calibration across most settings, consistently outperforming both NLI-based counterparts and all other methods evaluated.

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when natural-language reasoning is used through heuristic descriptions or reflection, it typically remains transient mutation context or unstructured memory, rather than organized as persistent population-level state over strategic directions. As a result, evolutionary search can struggle to distinguish syntactically different implementations of the same idea, preserve lower-fitness but strategically promising directions, or detect when an entire family of strategies has saturated. We introduce \model, a modular strategy-space layer that turns language-level strategic reasoning into first-class population-level evolutionary state in LLM-driven program search. \model represents each candidate program with an explicit natural-language strategy, clusters the archive by strategy semantics, retrieves behaviorally complementary inspirations, and periodically navigates the strategy landscape to avoid saturated directions. Without modifying the underlying evolutionary algorithms, \model improves existing evolutionary backbones across algorithm discovery, systems optimization, and agent-scaffold design tasks in most settings. Across four systems benchmarks, \model achieves a 20.6% average relative improvement, with the best single run on Prism scoring 3$\times$ higher. These results suggest that persistent strategy representations provide a practical mechanism for improving the effectiveness and cost-efficiency of LLM-guided evolutionary search, pointing toward compound AI systems whose search capabilities benefit from the structured accumulation and reuse of algorithmic strategies.

Agent safety in high-stakes domains requires formal policy enforcement, but most existing approaches either rely on probabilistic guardrails (fine-tuned classifiers, prompt-based steering) that offer no formal guarantees, or on hand-coded symbolic enforcement that does not scale to the breadth of real policy specifications. We present an autoformalization pipeline that translates agent prompts, MCP tool descriptions, and natural language policy documents into formally verified policies using an LLM-based generator-critic loop. The resulting policies are written in the Cedar Policy Language. On the MedAgentBench benchmark, our autoformalized policies cover substantially more of the source natural-language specification than the hand-coded symbolic enforcement in prior work.

Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential---yet these datasets have never been rigorously audited. Our first contribution is to present a systematic human inspection of the validation split of \textsf{FOLIO} and a subset of \textsf{MALLS} test instances, finding that approximately 42.5% and 42% of entries, respectively, contain incorrect FOL formalizations (i.e., ground truth labels), with additional rates of ambiguous NL sentences (17.8% and 51%) and incorrect NLI labels in \textsf{FOLIO} (8.4%). Our second contribution is to develop and release corrected ground truths for such datasets, showing that annotation errors distort model evaluation on a reference benchmark task: testing three state-of-the-art LLMs (Gemma~4 31B-it, Qwen3-30B-A3B, and GPT-4o-mini) with the corrected ground truths yields accuracy gains from +11 to +23 percentage points. Motivated by these findings, we propose an LLM-based framework to support humans in manual reviewing NL-to-FOL datasets. By directing reviewers toward the most error-prone instances, we empirically show that it is possible to achieve 90% dataset accuracy after reviewing fewer than 20% of instances, compared to over 76% required by unguided review. We release all human-verified annotations and the code for our framework.

Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited. Existing SAR--optical datasets largely rely on low-resolution, intensity-only Ground Range Detected~(GRD) products and do not preserve complex-valued SAR measurements or native acquisition geometry, which restricts physically grounded multimodal learning. In particular, large-scale public datasets combining very-high-resolution (VHR) SAR SLC, aligned optical imagery, and natural-language descriptions are still lacking. We present a VHR SAR--optical--text dataset built from open-access Umbra spotlight acquisitions distributed as Sensor Independent Complex Data (SICD). From around 2,500 worldwide scenes (VV/HH, 20cm--2m native resolution), we standardize all SAR data to an 80cm slant-range grid via band-limited FFT resampling and tile the imagery into 1024 by 1024 patches. For each SAR patch, we retrieve a high-resolution optical tile and warp it into the SAR grid using local coordinate correspondences for local pixel-level alignment. We further generate three caption variants (SHORT/MID/LONG) per sample to support vision--language training and evaluation. Our dataset contains 119,566 triplets (complex and amplitude slant-range SAR patch, aligned optical patch, natural-language description) covering 257 locations across 72 countries and a broad range of land types and infrastructures. We release fixed train/validation/test splits and the full preprocessing and baseline code to enable reproducible benchmarks for multimodal alignment on cross-modal retrieval and conditional generation in native SAR geometry. The dataset is publicly available on the Hugging Face Hub at https://huggingface.co/datasets/ONERA/SARLO-80.

Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks. The dominant communication protocol in such systems is natural language: agents exchange messages token-by-token, verbalising their internal reasoning so that peers can read, verify, and respond. While convenient and interpretable, this protocol suffers from three structural drawbacks -- high inference cost, irreversible information loss during discretization, and ambiguity/redundancy of natural language. A growing body of work therefore explores an alternative protocol -- latent communication -- in which agents exchange continuous representations (embeddings, hidden states, or KV-caches) directly, bypassing the bottleneck of text generation. This paper presents a unified framework for organising the rapidly expanding literature on latent communication. We analyse existing methods along three orthogonal axes: (1) WHAT information is communicated (Embeddings, Hidden States, KV-Caches, or other continuous state); (2) WHICH sender-receiver alignment is used (latent-space alignment and layer alignment); and (3) HOW the communicated information is fused into the receiver (concatenation, prepending, mathematical operations, cross-attention, or cache restoration). Under this 3-axis framework, we systematically categorise eighteen representative methods proposed between 2024 and 2026, identify five major design patterns, and surface a set of open challenges -- including cross-architecture alignment, security of latent channels, compression for edge deployment, and the relationship between latent communication and latent chain-of-thought. We hope that this framework both lowers the barrier to entry for new researchers and provides a vocabulary for comparing future work.