Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deployment. We propose MTR, a simulation-first training framework for tool-augmented reasoning. Instead of relying on live APIs, MTR learns from complete ReAct traces with schema-validated, simulated observations. Our approach operates through a multi-agent architecture where a ToolMaker generates task-specific, OpenAI-compatible tool interfaces, an AutoAgent produces structured think-act-observe sequences, and a ToolActor simulates realistic responses. Training proceeds in two stages: Stage-1 Supervised Fine-Tuning (SFT) teaches 'trace grammar' from complete reasoning sequences; Stage-2 Group Relative Policy Optimization (GRPO) optimizes strategy with a composite trace reward that balances answer correctness and internal consistency. Across four multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA, Bamboogle), MTR attains competitive Exact Match (EM) scores to live-API systems and excels on reasoning-intensive tasks, suggesting that effective tool reasoning can be learned from structured traces without live interactions.

We introduce an incremental summarization system for customer support agents that intelligently determines when to generate concise bullet notes during conversations, reducing agents' context-switching effort and redundant review. Our approach combines a fine-tuned Mixtral-8x7B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. Agent edits refine the online notes generation and regularly inform offline model retraining, closing the agent edits feedback loop. Deployed in production, our system achieved a 3% reduction in case handling time compared to bulk summarization (with reductions of up to 9% in highly complex cases), alongside high agent satisfaction ratings from surveys. These results demonstrate that incremental summarization with continuous feedback effectively enhances summary quality and agent productivity at scale.

We introduce an Agent-in-the-Loop (AITL) framework that implements a continuous data flywheel for iteratively improving an LLM-based customer support system. Unlike standard offline approaches that rely on batch annotations, AITL integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge. These feedback signals seamlessly feed back into models' updates, reducing retraining cycles from months to weeks. Our production pilot involving US-based customer support agents demonstrated significant improvements in retrieval accuracy (+11.7% recall@75, +14.8% precision@8), generation quality (+8.4% helpfulness) and agent adoption rates (+4.5%). These results underscore the effectiveness of embedding human feedback loops directly into operational workflows to continuously refine LLM-based customer support system.

Large language models (LLMs) have transformed natural language processing, achieving remarkable performance across diverse tasks. However, their impressive fluency often comes at the cost of producing false or fabricated information, a phenomenon known as hallucination. Hallucination refers to the generation of content by an LLM that is fluent and syntactically correct but factually inaccurate or unsupported by external evidence. Hallucinations undermine the reliability and trustworthiness of LLMs, especially in domains requiring factual accuracy. This survey provides a comprehensive review of research on hallucination in LLMs, with a focus on causes, detection, and mitigation. We first present a taxonomy of hallucination types and analyze their root causes across the entire LLM development lifecycle, from data collection and architecture design to inference. We further examine how hallucinations emerge in key natural language generation tasks. Building on this foundation, we introduce a structured taxonomy of detection approaches and another taxonomy of mitigation strategies. We also analyze the strengths and limitations of current detection and mitigation approaches and review existing evaluation benchmarks and metrics used to quantify LLMs hallucinations. Finally, we outline key open challenges and promising directions for future research, providing a foundation for the development of more truthful and trustworthy LLMs.

Advances in large language models (LLMs) and real-time speech recognition now make it possible to issue any graphical user interface (GUI) action through natural language and receive the corresponding system response directly through the GUI. Most production applications were never designed with speech in mind. This article provides a concrete architecture that enables GUIs to interface with LLM-based speech-enabled assistants. The architecture makes an application's navigation graph and semantics available through the Model Context Protocol (MCP). The ViewModel, part of the MVVM (Model-View-ViewModel) pattern, exposes the application's capabilities to the assistant by supplying both tools applicable to a currently visible view and application-global tools extracted from the GUI tree router. This architecture facilitates full voice accessibility while ensuring reliable alignment between spoken input and the visual interface, accompanied by consistent feedback across modalities. It future-proofs apps for upcoming OS super assistants that employ computer use agents (CUAs) and natively consume MCP if an application provides it. To address concerns about privacy and data security, the practical effectiveness of locally deployable, open-weight LLMs for speech-enabled multimodal UIs is evaluated. Findings suggest that recent smaller open-weight models approach the performance of leading proprietary models in overall accuracy and require enterprise-grade hardware for fast responsiveness. A demo implementation of the proposed architecture can be found at https://github.com/hansvdam/langbar

Large Language Models (LLMs) are prone to hallucination, the generation of plausible yet factually incorrect statements. This work investigates the intrinsic, architectural origins of this failure mode through three primary contributions. First, to enable the reliable tracing of internal semantic failures, we propose Distributional Semantics Tracing (DST), a unified framework that integrates established interpretability techniques to produce a causal map of a model's reasoning, treating meaning as a function of context (distributional semantics). Second, we pinpoint the model's layer at which a hallucination becomes inevitable, identifying a specific commitment layer where a model's internal representations irreversibly diverge from factuality. Third, we identify the underlying mechanism for these failures. We observe a conflict between distinct computational pathways, which we interpret using the lens of dual-process theory: a fast, heuristic associative pathway (akin to System 1) and a slow, deliberate, contextual pathway (akin to System 2), leading to predictable failure modes such as Reasoning Shortcut Hijacks. Our framework's ability to quantify the coherence of the contextual pathway reveals a strong negative correlation ($ρ= -0.863$) with hallucination rates, implying that these failures are predictable consequences of internal semantic weakness. The result is a mechanistic account of how, when, and why hallucinations occur within the Transformer architecture.

Large language models (LLMs) have achieved impressive performance in text summarization, yet their performance often falls short when applied to specialized domains that differ from their original pre-training distribution. While fine-tuning can improve summarization quality, it typically relies on costly and scarce high-quality labeled data. In this work, we explore continual pre-training as a scalable, self-supervised approach to adapt LLMs for downstream summarization tasks, particularly in the context of noisy real-world conversation transcripts. We conduct extensive experiments using large-scale, unlabeled business conversation data to investigate whether continual pre-training enhances model capabilities in conversational summarization. Our results demonstrate that continual pre-training yields substantial gains in both in-domain and out-of-domain summarization benchmarks, while maintaining strong generalization and robustness. We also analyze the effects of data selection strategies, providing practical guidelines for applying continual pre-training in summarization-focused industrial applications.

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the magnitude of information leakage and raises serious privacy risks. Hence, it is more crucial than ever to quantify privacy risk before the release of LLMs. The standard method to quantify privacy is via membership inference attacks, where the state-of-the-art approach is the Robust Membership Inference Attack (RMIA). In this paper, we present InfoRMIA, a principled information-theoretic formulation of membership inference. Our method consistently outperforms RMIA across benchmarks while also offering improved computational efficiency. In the second part of the paper, we identify the limitations of treating sequence-level membership inference as the gold standard for measuring leakage. We propose a new perspective for studying membership and memorization in LLMs: token-level signals and analyses. We show that a simple token-based InfoRMIA can pinpoint which tokens are memorized within generated outputs, thereby localizing leakage from the sequence level down to individual tokens, while achieving stronger sequence-level inference power on LLMs. This new scope rethinks privacy in LLMs and can lead to more targeted mitigation, such as exact unlearning.

Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn conversations. Since human studies are costly, time-consuming, and hard to reproduce, recent work explores using LLMs to simulate users for automatic assistant evaluation. However, there is no benchmark or systematic study to evaluate whether these simulated users are reliable stand-ins for real users. To address this, we introduce SimulatorArena, a benchmark of 909 annotated human-LLM conversations on two interactive tasks -- math tutoring and document creation. SimulatorArena evaluates simulators based on how closely their messages match human behavior and how well their assistant ratings align with human judgments. Experiments on various simulator methods show that simulators conditioned on user profiles, capturing traits like background and message styles, align closely with human judgments. They reach Spearman's $ρ$ of 0.7 on both tasks, providing a practical, scalable alternative to human evaluation. Using the best simulator for each task, we benchmark 18 assistants, including the latest LLMs such as GPT-5, Claude 4.1 Opus, and Gemini 2.5 Pro.

In-context learning (ICL) enables efficient few-shot learning in large language models (LLMs) without training, but suffers from the quadratic input complexity of transformers, limiting the maximum number of exemplars. While various efficient ICL approaches partition the context into blocks to process (e.g., ensembling, compression, cross-attention), they often ignore the information redundancy or under-representation caused by different partition strategies, leading to suboptimal performance. To tackle this problem, we propose Sub-CP, a block-aware context selection framework that leverages submodular objectives to control block diversity. Sub-CP supports a flexible spectrum of selection strategies, allowing each block to range from globally diverse to locally coherent. This allows fine-grained control over semantic structure while enabling precomputation. Extensive experiments across diverse tasks on multiple datasets show that Sub-CP consistently improves performance across model scales.