Search research

Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks. Reliable uncertainty estimation (UE) is essential for selective prediction, human-in-the-loop review, and downstream agentic decisions. Yet most existing code UE methods are inherited from natural language (NL) generation and ignore properties that make code distinct. We argue that code differs from NL in three ways: a single wrong token can break an entire program (token fragility); algorithmic intent and concrete implementation can disagree independently (intent-code gap); and programs can be executed (executability). We instantiate these properties as three orthogonal uncertainty axes: lexical (Top-K token entropy), algorithmic (pseudo-code consistency), and functional (behavioral consistency). Across five code LLMs, our three-axis ensemble improves average AUROC from 0.696 for the strongest NL-derived baseline to 0.776 (+8.1 points). Notably, on Qwen3-14B, our single-pass Top-K token entropy matches the strongest multi-pass baseline while being over 3x cheaper; across models, it remains a competitive low-cost signal. These results suggest that code UE deserves code-specific design rather than direct NL ports.

We investigate whether methods of human mathematics pedagogy can guide the training of language models toward arithmetic reasoning. Building on the GASING method -- an Indonesian pedagogy that solves basic arithmetic through a left-to-right procedure aligned with the causal order of token generation -- we operationalize each operation as a computational procedure whose execution trace is serialized into natural-language Chain-of-Thought (CoT) supervision. A small GPT-2 decoder (86M parameters) with a syllabic-agglutinative TOBA tokenizer for Indonesian is trained from scratch on this data using only a next-token prediction objective, without reinforcement learning or reward-based optimization. Monitoring training reveals three distinct learning phases, and mechanistic analyses -- attention-masking interventions on the CoT information graph, residual-stream probing, and logit-lens inspection -- show that the model first internalizes a procedural pathway and subsequently develops an associative, ``mental-arithmetic'' capacity that retrieves intermediate results without explicit step-by-step computation. The trained model reaches over 80% accuracy on held-out problems and attains competitive performance against substantially larger language models, indicating that targeted, pedagogically grounded training can yield strong and economical arithmetic capability at small scale.

Hazard, as an abstract concept, is typically defined through cognitive-level logical reasoning rather than concrete examples. In contrast, existing hazard detection systems rely on predefined hazard categories and require intensive collection of labelled examples within detection or classification architectures. This approach faces three fundamental challenges when addressing abstract safety concepts: (1) noisy and sparse training data, (2) dynamically evolving definitions that change across contexts and time, and (3) limited generalisation to unseen or novel scenarios. To address these limitations, we present the CompliVision dataset, the first general-purpose hazard dataset designed for rule-based compliance assessment, along with a baseline framework for hazard evaluation. Our key innovation is decoupling the hazard concept from image-based examples by expressing safety requirements through language-based rules. We ground our approach in authoritative domain regulations and ISO standards to define diverse hazard concepts across multiple domains. The CompliVision dataset comprises 3,006 images spanning traffic, construction, and warehouse environments, with each image annotated for compliance against specific safety rules, accompanied by natural language explanations highlighting the supporting visual evidence. To achieve robust generalisation, we develop an active learning framework to more effectively guide and refine vision-language models in assessing hazard compliance. While state-of-the-art VLMs demonstrate strong capabilities, they struggle with the fine-grained, context-dependent interpretation required for accurate safety assessment. We proposed a general hazard detection framework to address this limitation which combines LLaVA-based visual reasoning with with human-in-the-loop feedback.

Mathematical programming provides a common language for many decisions embedded in modern machine-learning (ML) and artificial-intelligence (AI) systems: selecting retrieval context, routing tokens, allocating inference compute, fitting structured predictors, protecting against distribution shift, and balancing competing objectives. However, the relevant literature is fragmented across optimization, information retrieval, recommendation, natural-language processing, computer vision, and learning theory. This paper organizes various applications under common mathematical programming paradigms: linear, quadratic, binary and mixed-integer, conic, bilevel, multi-objective, inverse, distributionally robust, submodular, and min--max optimization. We normalize the models with a mostly unified notation and, for every application, identify inputs, decision variables, a principal formulation, structural properties, solution strategies, and limitations. Across paradigms, we compare tractability, relaxation quality, decomposition, approximation guarantees, and scalability bottlenecks. The paper shows that mathematical programming is most useful not as a claim that all learning is LP or MIP, but as a disciplined interface between predictions and constrained decisions.

Pre-trained language models struggle when applied to new domains, as full fine-tuning is computationally expensive and prone to catastrophic forgetting. This study addresses this challenge by presenting a novel parameter-efficient strategy for unsupervised domain adaptation that combines custom PEFT architectures with mixed-objective training. Our approach simultaneously optimizes classification performance on labeled source domain data and masked language modeling (MLM) on unlabeled target domain data, preserving target domain knowledge while adapting to source domain tasks. Our method employs a custom union of invertible adapters and Low-Rank Adaptation (LoRA) within a unified parameter-efficient framework. Through comprehensive evaluation on the Multi-Genre Natural Language Inference (MNLI) dataset across 20 domain shifts, our approach achieves significant improvements over existing methods: 1.41 percentage points over the current parameter-efficient state-of-the-art UDapter, 1.26 percentage points over the fully-tuned DANN baseline, and 0.86 percentage points over DSN, while utilizing only 7% of the model's trainable parameters. These results establish new benchmarks for parameter-efficient unsupervised domain adaptation and demonstrate that carefully designed PEFT combinations with concurrent optimization can outperform both existing parameter-efficient methods and traditional fully-tuned approaches.

Large language models (LLMs) are increasingly used for writing and review support, but their usefulness depends on context-dependent criteria, such as expert preferences or organization-specific conventions, that are often tacit, undocumented, and difficult to elicit directly. We propose a problem setting for learning reusable natural-language rubrics from accumulated inline comments on artifacts such as human-written or LLM-generated drafts. Our method infers rubrics from these comments and iteratively refines them by observing comment-wise mismatches between rubric-conditioned predictions and reference comments. We evaluate the proposed method in real-world review settings and in controlled settings with reference rubrics. These results show that inline comments can be distilled into reusable rubrics that support comment prediction, rubric understanding, and automatic artifact revision.

We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX Terminal Pro, a 21-day deployment in which 3,505 user-funded agents traded real ETH in a bounded onchain market. Users configured vaults through structured controls and natural-language strategies, but only agents could choose normal buy/sell trades. The system produced 7.5M agent invocations, roughly 300K onchain actions, about $20M in volume, more than 5,000 ETH deployed, roughly 70B inference tokens, and 99.9% settlement success for policy-valid submitted transactions. Long-running agents accumulated thousands of sequential decisions, including 6,000+ prompt-state-action cycles for continuously active agents, yielding a large-scale trace from user mandate to rendered prompt, reasoning, validation, portfolio state, and settlement. Reliability did not come from the base model alone; it emerged from the operating layer around the model: prompt compilation, typed controls, policy validation, execution guards, memory design, and trace-level observability. Pre-launch testing exposed failures that text-only benchmarks rarely measure, including fabricated trading rules, fee paralysis, numeric anchoring, cadence trading, and misread tokenomics. Targeted harness changes reduced fabricated sell rules from 57% to 3%, reduced fee-led observations from 32.5% to below 10%, and increased capital deployment from 42.9% to 78.0% in an affected test population. We show that capital-managing agents should be evaluated across the full path from user mandate to prompt, validated action, and settlement.

Quantitative language research often depends on long chains of computational steps, yet the logic connecting those steps usually remains buried in scripts. This makes analyses harder to inspect, share, and revise than they need to be. Focusing on quantitative syntax, we present QLWF, a visual workflow platform that turns natural-language research descriptions into executable workflows through an AI assisted five-stage pipeline. In this setting, reification makes the research logic visible as a workflow, while formalization gives that workflow deterministic execution semantics. The language model is used only during construction. Execution is handled by a fixed node library and engine, which keeps the resulting workflows reproducible. QLWF also supports incremental refinement, so saved workflows can be revised by changing only the parts that need to change rather than being rebuilt from scratch. To evaluate the approach, we build a 64-task benchmark called QL-Bench from the quantitative-syntax literature. Across three runs, QLWF produces structurally valid and executable workflows for every task and reaches a mean output-plausibility rate of 98.4%, well above the prompt-based baselines. On a separate 12-task lifecycle benchmark, this refinement process succeeds in every case and uses roughly one-third of the tokens required by full regeneration. The paper also releases the node library, benchmark, workflow templates, and platform as reusable resources for quantitative-syntax research.

Generating long-form content from extensive internal reports remains challenging for organizations operating under strict privacy and security constraints, where proprietary cloud-based LLM APIs are often not viable. While locally deployed open-weight models offer a privacy-preserving alternative, existing retrieval-augmented generation (RAG) approaches on smaller models frequently lack effective global planning and accumulate factual inconsistencies over long outputs. To address these limitations, we present RH-RAG, a multi-agent framework for secure and trustworthy long form generation using local language models. RH-RAG decomposes generation into three coordinated stages: a Planner Agent that constructs a global document outline from high-level semantic summaries, a Writer Agent that incrementally generates coherent section-wise content using bounded coherence memory, and a Checker Agent that mitigates hallucinations through natural language inference-based factual verification and an attestation-driven revision loop. The framework further employs a dual-level retrieval index that supports efficient planning and fine-grained contextual generation on consumer-grade hardware. Evaluations across literary, financial, and legal domains demonstrate that RH-RAG consistently improves factual grounding, semantic coherence, and document-level alignment compared to standard and hierarchical RAG baselines, while achieving reliability competitive with proprietary cloud-based systems without compromising data privacy.

We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors. Motivated by humans' ability to abstract predictive structure from visual experience and organize it in natural language for explicit reasoning, we learn physical language from in-the-wild videos through self-supervision and use it to explicitly reason about how the physical world evolves. Accordingly, PhiZero adopts a reason-then-render paradigm: it first infers future world evolution as a physical-language sequence and then renders the inferred transitions into videos. Extensive experiments across generation and understanding benchmarks validate the ability of PhiZero to model physically coherent world evolution. We further show its potential for realistic and interactive world modeling, fine-grained action-conditioned simulation, and zero-shot motion transfer.

We develop a text-to-SQL (structured query language) system based on large language models (LLMs) using in-context learning and apply it to the Automatic Learning for the Rapid Classification of Events (ALeRCE) astronomical database. ALeRCE is a community broker for the Zwicky Transient Facility and the Vera C. Rubin Observatory. The system enables users to query the database in natural language (NL) and generates executable SQL queries. To develop and evaluate the system, we constructed a dataset of 110 NL/SQL pairs. We propose a step-by-step generation framework comprising four modules: schema linking, query classification, prompt decomposition, and self-correction. The performance of thirteen LLMs is evaluated using in-context learning and prompt engineering techniques. Text-to-SQL performance is assessed using the perfect-match (PM) rate for row identifiers (e.g., object identifiers) and column identifiers (i.e., column names). The proposed step-by-step framework consistently outperforms a direct-inference baseline, while the self-correction module consistently reduces execution errors. For Claude Opus 4.6, PM performance on row (column) identifiers is high for simple queries, reaching 0.97 (0.94), and decreases with query complexity to 0.44 (0.72) for medium queries and 0.59 (0.49) for hard queries. Among the thirteen evaluated models, the best-performing LLMs for the text-to-SQL task are Claude Opus 4.6, Gemini 2.5 Pro, Gemini 3 Flash, and GPT-5.2-Codex.

OpenRTLSet introduces the largest fully open-source dataset for hardware design, offering over 131,000 diverse Verilog code samples to the research community and industry. Our dataset uniquely combines Verilog code from GitHub repositories (102k modules), VHDL translations (5k modules), and synthesizable C/C++ translations (24k modules), all freely accessible without proprietary restrictions. Using the reasoning model DeepSeek-R1, we generated paired natural language descriptions for each code sample, enabling fine-tuning of various language model families (e.g., Qwen and Granite) for Verilog code generation. Our dataset explores multiple options, including Verilator-generated C++ files as additional context during labeling, quantization techniques (INT4 vs. BF16), and performance differences across model sizes (7B-32B parameters). OpenRTLSet demonstrates that open-source approaches can achieve superior performance in hardware design tasks, establishing a new foundation for accessible research and commercial use in this domain.

We address the challenge of task-oriented navigation in unstructured and unknown environments, where robots must incrementally build and reason on informative metric-semantic maps in real time. Since tasks may require clarification or re-specification, it is necessary for the information in the map to be rich enough to enable generalization across a wide range of tasks. To effectively execute tasks specified in natural language, we propose a hierarchical representation built on language-embedded Gaussian splatting that enables both sparse semantic planning that lends itself to online operation and dense geometric representation for collision-free navigation. We validate the effectiveness of our method through real-world robot experiments on a ground robot equipped with only vision-based sensing. The experiments are conducted in both cluttered indoor and kilometer-scale outdoor environments, covering more than 2 km and 47,000 square meters of area. We achieve a competitive ratio of about 59% relative to the shortest possible path, demonstrating efficient exploration and semantic navigation in challenging real-world environments. Experiment videos and more details can be found on our project page: https://ongdexter.github.io/atlasnav.

Large language models can easily generate explanations for their own outputs, but such self-explanations are not necessarily faithful to the model's behavior. We study this issue through counterfactual self-explanations, where a model minimally edits an input so that its own prediction changes. Across sentiment analysis and natural language inference, we evaluate ten instruction-tuned models from the LLaMA-3 and Qwen-2.5 families, measuring faithfulness, minimality, and alignment with human-annotated rationales. Our results show that model scale is the strongest determinant of explanation quality: larger models are substantially more likely to generate counterfactuals that flip their own predictions and target decision-relevant evidence. In contrast, the rationale-guided condition produces edit-minimal counterfactuals that are also more human-aligned. However, it does not consistently improve faithfulness. Overall, counterfactual self-explanations can provide useful behavioral evidence about model decisions, but their reliability depends strongly on model capacity and should be empirically validated rather than assumed.

Language-guided robots need persistent scene memories to follow instructions, revisit objects, and resolve references to objects encountered over time. While much of language-guided scene-memory retrieval has emphasized spatial or relational references, many everyday object references specify objects by multiple persistent attributes, such as category, material, size, or surface appearance. We formalize this problem as attribute-compositional retrieval, where a fixed object-centric scene memory is queried with natural language to retrieve the object satisfying the requested attributes. To investigate this capability directly, we introduce a controlled evaluation protocol with fixed scene memories and attribute-defined targets, separating retrieval from perception and annotation ambiguities. We then propose FRAME, which turns language into query-relevant attribute weights, uses learned readouts to estimate per-attribute evidence from object embeddings, and ranks objects by aggregating this evidence according to the query. Across held-out scenes and object assets, FRAME outperforms representative scene-memory retrieval baselines while reducing post-decomposition object scoring to lightweight matrix-vector computation. These results position attribute-compositional retrieval as a complementary scene-memory capability for language-guided robots, showing that persistent object attributes can be exposed as composable evidence for accurate and efficient multi-attribute retrieval.

Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy artifacts, mainly SKILL{.}md-style documents whose machine-usable evidence remains embedded largely in natural-language descriptions. As a result, skill-centered agent systems face a representation problem: both managing skill collections and using skills during agent execution require reasoning over invocation interfaces, execution structure, and concrete side effects, but these signals are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on cognitive linguistic representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action/resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate SSL-derived representations in two tasks, Skill Discovery and Risk Assessment. The experiment shows that SSL significantly outperforms the text-only baselines: in Skill Discovery, MRR@50 improves from 0.649 to 0.729; in Risk Assessment, macro F1 improves from 0.409 to 0.509. These findings suggest that an explicit, source-grounded structure can make agent skills easier to search and review, positioning SSL as a practical step toward more inspectable, reusable, and operationally actionable skill representations, rather than a finished standard or end-to-end skill-management mechanism.

Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle updates and preventing the reuse of learned sub-behaviors. We propose Prompt Codebooks (PCO), a novel compositional prompt optimization framework that recasts APO as discrete learning over a finite vocabulary of natural-language instincts - atomic, reusable instruction units. PCO organizes prompt-construction knowledge in a discrete codebook and routes each input to a small subset of entries via an LLM-based encoder; a generator composes them into a prompt for the frozen target model; a critic emits a structured verdict that decomposes by attribution into per-variable textual gradients, jointly training the encoder, generator, and codebook under a language-valued min-max objective. The resulting routing is per-instance: different inputs in the same task receive different instinct compositions, a regime structurally inexpressible under instance-blind methods. Across six benchmarks on Qwen3-8B and LLaMA-3.1-8B, PCO improves over zero-shot by up to +30.36 points, surpasses the strongest prior baseline (GEPA) by +3.34 on HotpotQA and +1.11 in aggregate, and reduces deployed prompt length by up to 14.1x versus MIPROv2 and 3.0x versus GEPA using only K=16 instincts.

As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-LLMs) must integrate speaker-specific understanding to support user authorization, personalization, and context-aware interaction. This requires modeling who is speaking, how the voice sounds, and how recording conditions affect speaker cues. Conventional speaker verification systems provide strong scalar scores but little linguistic evidence, while current audio-LLMs and speaker-aware language models have limited ability to organize speaker information beyond binary labels or descriptive profiles. We present SpeakerLLM, a speaker-specialized audio-LLM framework that unifies single-utterance speaker profiling, recording-condition understanding, utterance-pair speaker comparison, and evidence-organized verification reasoning within a natural-language interface. We construct verification-reasoning targets and a decision-composition policy that separate profile-level evidence from the final same-or-different decision and organize recording condition, profile evidence, and the decision into a structured trace. At its core, SpeakerLLM uses a hierarchical speaker tokenizer designed to capture multiple granularities of speaker evidence. Utterance-level speaker embeddings summarize identity and profile-level cues, whereas frame-level speaker features preserve fine-grained acoustic descriptors. Experiments show that SpeakerLLM-Base improves speaker-profile and recording-condition understanding over general audio-LLMs, while SpeakerLLM-VR preserves strong generated-verdict accuracy and produces decision traces grounded in the supervised verification reasoning schema. We will release the metadata-enriched supervision dataset and target-construction code for reproducibility.

Large Vision-Language Models produce fluent image descriptions but offer limited semantic control: users cannot reliably specify whether captions should emphasize attributes, relations, or particular image regions. We present Fine-grained Captioning Control Using Scene Rewards (FoCUS), a controllable image captioning method that lets users steer captions toward specific semantic emphases through natural-language control prompts. The core idea is a prompt-conditioned control objective based on scene-graph-aligned component scores. Generated captions are parsed and aligned to scene-graph components such as objects, attributes, and relations. These components are differentially weighted, including negative weights, according to the requested emphasis. We optimize this objective with GRPO and further improve its reliability through a stricter object validity threshold and reasoning-based verification for attribute and relation scoring. To evaluate controllability, we introduce Semantic Control and Precision Evaluation (SCoPE), a benchmark with contrastive Include/Avoid constraints for measuring both target content coverage and out-of-scope suppression. Experiments on two VLM backbones show that FoCUS consistently improves controllability and fine-grained caption quality without degrading general caption performance.

Vision-Language-Action (VLA) models demonstrate strong semantic understanding yet exhibit systematic failures during deployment. The conditions under which these failures occur, and whether they can be corrected without retraining, remain poorly understood. In this paper, we take steps toward addressing this gap. We present CorrectVLA, a framework that translates task-level natural language corrections into additive action magnitude adjustments without modifying policy weights. A human provides a single task-level correction, applied uniformly across all rollouts without per-episode intervention. In simulation, CorrectVLA recovers execution misalignment failures across both in-distribution and OOD tasks. In real-robot experiments on a UFactory xArm7 under environment shift, CorrectVLA restores near-perfect success where the base policy almost entirely breaks down, generalizing across object locations and identities. Through a taxonomy of failure modes on LIBERO-90, we find that execution misalignment failures, where the policy reaches the correct target but miscalibrates action magnitudes, represent the correctable subset, while other failure modes where semantic comprehension itself breaks down are not amenable to this approach. The approach succeeds when policies possess strategic correctness and fails when fundamental comprehension is absent, establishing a practical operational boundary for inference-time correction.

Open-World Learning (OWL) pipelines for oil well anomaly detection have recently been shown to combine autoencoder-based detection, multiclass classification, and Mahalanobis-based novelty detection on the public 3W dataset. These pipelines answer \textit{what happened}, but they do not explain \textit{why the model believes it} or \textit{what the operator should do next}, and they do not put a human-readable name on the novelty clusters they discover. This paper evaluates a Large Language Model (LLM) agent layer placed downstream of the OWL pipeline, designed as a \textbf{companion} to the published upstream methods rather than a replacement. Using the Qwen3.5-397B-A17B Mixture-of-Experts model served via NVIDIA NIM, the agent receives structured sensor metrics and upstream classification or novelty assertions, and returns natural-language justifications, confidence-ranked critiques, and consolidated names for detected novelties. Across three studies spanning 989 real well-file segments from the 3W dataset, the agent achieved $35.1\%$ top-1 / $63.9\%$ top-3 (95% CI [56.9, 70.4]) classification on all nine classes, $71.7\%$ top-2 validation [64.8, 77.6] with precision $0.91$ [0.84, 0.95] across 7 probed classes, and $89.7\%$ novelty detection [87.0, 91.9] with stable cluster naming on 5 of 7 hidden classes. The agent is not a standalone classifier. Its role is to: (1) confirm upstream decisions when sensor evidence supports them, (2) justify decisions in sensor-grounded language operators can audit, (3) flag disagreement when upstream labels are implausible, and (4) name novelties so that clustered unlabeled events arrive at the engineer with a consolidated human-readable label. The goal is to close the explainability gap that currently blocks deployment of OWL pipelines in operational settings.

Psychometric calibration for educational tests typically requires costly human response data. Large language models (LLMs) simulated examinees offer a promising route to early calibration, but their responses are too accurate and too uniform. We propose Cognitive Diagnostic Profiling (CDP), a zero-shot framework that prompts LLMs to simulate plausible examinees with diverse cognitive profiles: binary attribute-mastery patterns are rendered as natural-language profiles and sampled under an uninformative or an informative distribution. Using the Tatsuoka fraction-subtraction dataset (536 examinees, 15 items, five attributes), we evaluated eight LLM configurations under no-profile, uninformative-CDP, and informative-CDP conditions, assessing alignment with human examinees at the ability-distribution, mastery-profile, and item-difficulty levels. CDP improved all three levels: distributional overlap rose across configurations; weighted correlations between profile-level scores and human profile expectations reached 0.92 to 0.98; and item-difficulty recovery improved in rank order and absolute alignment, most for reasoning-enabled models; in the strongest case, Gemini 3.0 Flash (Thinking), one-parameter logistic (1PL) difficulty Spearman correlations rose from 0.24 to 0.86 and 0.90 and the root-mean-square error (RMSE) fell from 6.31 to 1.30 and 0.90; the informative condition helped most where profile-level alignment was strong. CDP brings LLM-simulated examinees into closer psychometric alignment with human examinees, making them practical for operational test development.

With large language models (LLMs) increasingly applied to mathematical reasoning, formal proof assistants such as Lean can be leveraged to verify reasoning outputs with machine-checkable rigor, enabling use cases such as answer selection in test-time scaling with K sampled candidate answers. However, employing Lean requires that LLM outputs, originally in natural language, first be formalized. Existing Lean-based answer-selection work uses an autoformalization model to generate a formal statement in Lean for each candidate answer independently, incurring a significant computational cost. We propose BASE, a base-and-edit pipeline that formalizes a single base candidate per problem and derives the remaining K-1 statements by editing the answer expression in place. To facilitate this, we train a rewriter model LEANSCRIBE to localize the answer in the base formalization and generate a reusable edit function for the other K-1 candidates. BASE simultaneously improves selection accuracy and reduces formalization cost - a Pareto improvement that holds on all 12 (dataset, solver) configurations across four benchmarks and three solvers, cutting autoformalizer calls by about 5x at K=8, with the reduction expected to become larger as K grows. Code is available at https://github.com/ucr-rai/base-and-edit.

Direct Code2Code transformation remains challenging to control because it can preserve surface-level syntax while introducing semantic drift, hidden behavioral changes, loss of traceability, non-idiomatic target implementations, or incomplete reconstruction of domain logic. This paper proposes a specification-based Code2Text2Code reengineering framework for LLM-mediated software evolution. The central idea is to transform source code into a neutral textual specification that captures program behavior, identifiers, computational flow, conditions, side effects, data dependencies, and domain-specific intent without directly transferring the source language syntax. The proposed framework combines factual context extraction, Code2Text generation, iterative verification between source code and text specification, Text2Code generation, target code verification, retrieval-augmented grounding, and semantic-aware chunking, and transformation loss estimation. The knowledge representation layer integrates metadata derived from AST, graph-based dependency structures, neutral natural language specifications, technical documentation, business documentation, and architecture-level representations. The conducted experiments include a Code2Text2Code dataset built from multiple programming languages and SQL dialects, comparison of intermediate representations, retrieval evaluation, documentation transformation evaluation, and prompt tuning using DSPy. A graph formalization using structural preservation, reverse compatibility, interface stability, and total graph similarity is implemented to estimate transformation losses. The results support the interpretation of the Code2Text2Code approach not as a simple code transformation, but as a controlled specification-based reengineering process for LLM-mediated software evolution.

Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied to those preferences. We present TO-Agents, a multi-agent AI framework that connects natural-language design intent with iterative topology optimization. The framework converts a human-provided problem description into validated solver inputs, runs a topology optimization solver, renders the resulting 3D topology, and uses multi-view vision-language reasoning with an independent judge agent to critique each result and revise solver parameters. We evaluate the framework on two long-horizon design tasks: a cantilever beam benchmark and a phone-stand product design. In both tasks, the designer specifies an aesthetic preference for hierarchically branched structures inspired by natural tree morphologies, and the system performs four revision cycles across ten independent replicates. TO-Agents produces at least one preference-aligned design in 60% of trials for each case study, corresponding to up to 6x more successful trials than an ablated pipeline without visual or historical feedback. Judge scores and human evaluations show that the pipeline can identify effective parameter levers, recover from poor revisions, and expand design exploration. A manufacturing agent further post-processes top-ranked designs for additive manufacturing, enabling end-to-end intent-to-prototype design. We also identify failure modes, including overshooting, selective memory, misplaced tools, and incorrect parameter reasoning. These results suggest that agentic topology optimization can shift designers from low-level parameter tuning toward higher-level specification of form and function, while highlighting safeguards needed for reliable autonomous engineering design.

AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs). Developers interact with code in two distinct cognitive modes: Flow and Command. While developers require tools that directly complete or infill code in unfinished programs during Flow mode, they also need tools that can comprehend intentions expressed as natural-language instructions and convert them into executable code in Command mode. Although instruction-tuned Large Language Models (LLMs) dominate many application scenarios due to their abilities to infer and fulfill developers' intents, it remains unclear whether the same paradigm is equally suitable for different code-related tasks. Therefore, it is necessary to understand how instruction tuning affects the feasibility of CodeLLMs as coding assistants. To fill this gap, we conduct the first empirical study that uncovers a key trade-off caused by instruction tuning across programming modes, which we term the Instruction-Tuning Tax. Our results show that instruction tuning is not a free lunch: although instruction-tuned models are more capable of following instructions and leveraging structured guidance, these gains often come at the cost of weaker infilling performance. We further extend our study through both qualitative and quantitative analyses, including manual failure categorization, behavioral metrics that capture generation fidelity, and intermediate-checkpoint evaluation throughout the tuning process. Summarizing our results into seven findings and four implications, our study offers a new perspective on the development of AI-powered coding tools and highlights the need to carefully balance instruction-following ability with effective code generation assistance.

Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search traces into an explicit natural-language skill library. Each skill stores a structural archetype, evidence-grounded positive and negative rules, and the evaluated designs that support them, making design memory inspectable rather than implicit in a population. During search, the agent retrieves skills to condition LLM edits of elite bodies while retaining a Genetic Algorithm (GA) mutation path for exploration; after evaluation, it updates the library through Add, Diagnose, and Merge. Across seven EvoGym tasks spanning locomotion, traversal, and object interaction, Auto-Robotist improves cold-start 5x5 search and transfers learned skills to 10x10 design spaces, where reference-conditioned transfer outperforms GA on every task. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code is publicly available at https://github.com/wangyf9/Auto-Robotist .

Synthetic data is widely used in healthcare to create datasets that preserve statistical properties of real data without exposing sensitive patient information. Generating and evaluating synthetic data across privacy, utility, and fairness dimensions is crucial for enabling high-quality data availability in downstream prediction tasks and clinical decision making. We present \textbf{Memisis}, a tool that orchestrates and evaluates synthetic data by leveraging existing synthesis libraries, large language models (LLMs), and state-of-the-art evaluation metrics. Our tool creates a unified workflow for data generation, validation, and evaluation. Users can control training size, training epochs, and the number of synthetic rows to sample. Beyond manual configuration, an interactive agent mode allows users to specify data generation goals in natural language, and the tool orchestrates the full pipeline by invoking existing synthesizers while performing the requisite evaluation. For the demo, we use an open-source schizophrenia dataset with protected attributes related to race and gender, evaluate six synthesizers spanning GANs, VAEs, diffusion models, and normalizing flows, and use a local LLM to orchestrate the workflow. The system affords users flexibility and control over the data generation and evaluation process.

This study introduces intelligent frameworks that use Large Language Models (LLMs) to improve task scheduling for construction robots. The LLM is fed with key data about the desired task, such as agent action abilities, and the desired end goal to be achieved. A well-balanced allocation strategy is developed, optimizing both time efficiency and resource utilization. Our system utilizes a Natural Language Processing interface to streamline communication with construction professionals and adapt in real-time to unexpected site conditions. We concurrently use two LLM agents, specifically generator (GPT-4) and supervisor (Gemma 3/Llama 4/Mistral 7b) LLM agents to provide a more precise task schedule. We evaluate the proposed methodology using a straightforward scenario and provide metric scores to prove the efficacy of the frameworks. Our results highlight that the implementation of LLMs is crucial in construction operational tasks including robots.

Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among agents, unknown emergent behavior, and interactions between agents that are bounded by natural language. We address two of these gaps: the absence of social behavior and the lack of mechanisms for inter-agent coordination. We introduce Epistemic Probabilistic Language Agents (EPLA), a neuro-symbolic architecture for multi-agent coordination under uncertainty. A Symbolic Guard provides structured diagnostic feedback. The LLM generates typed actions, and the Guard controls their execution against an authoritative symbolic state. We formalize the epistemic layer in a gossip testbed through epistemic lottery gossip models, which combine view-based call histories with agent-indexed probability weights. We argue that implementing such a formalism can address shortcomings of agentic LLMs.