In real-world scenarios, providing user queries with visually enhanced responses can considerably benefit understanding and memory, underscoring the great value of interleaved image-text generation. Despite recent progress, like the visual autoregressive model that unifies text and image processing in a single transformer architecture, generating high-quality interleaved content remains challenging. Moreover, evaluations of these interleaved sequences largely remain underexplored, with existing benchmarks often limited by unimodal metrics that inadequately assess the intricacies of combined image-text outputs. To address these issues, we present RAG-IGBench, a thorough benchmark designed specifically to evaluate the task of Interleaved Generation based on Retrieval-Augmented Generation (RAG-IG) in open-domain question answering. RAG-IG integrates multimodal large language models (MLLMs) with retrieval mechanisms, enabling the models to access external image-text information for generating coherent multimodal content. Distinct from previous datasets, RAG-IGBench draws on the latest publicly available content from social platforms and introduces innovative evaluation metrics that measure the quality of text and images, as well as their consistency. Through extensive experiments with state-of-the-art MLLMs (both open-source and proprietary) on RAG-IGBench, we provide an in-depth analysis examining the capabilities and limitations of these models. Additionally, we validate our evaluation metrics by demonstrating their high correlation with human assessments. Models fine-tuned on RAG-IGBench's training set exhibit improved performance across multiple benchmarks, confirming both the quality and practical utility of our dataset. Our benchmark is available at https://github.com/USTC-StarTeam/RAG-IGBench.

The integration of external tools is pivotal for empowering Large Language Model (LLM) agents with real-world capabilities. However, training these agents through direct, continuous interaction with diverse tools is often prohibitively expensive, slow, and introduces additional development and maintenance overhead. To address this challenge, we introduce the Generalist Tool Model (GTM), a 1.5-billion-parameter model that learns to act as a universal tool simulator. With only prompt-level configuration, GTM accesses tool functionalities along with input arguments and generates outputs that faithfully mimic real tool execution, providing a fast and cost-effective solution that eliminates development overhead. To build GTM, we propose the Context-Aware Response Generation (CARG) pipeline, which synthesizes comprehensive training data covering over 20,000 tools across 300 domains including physics, medicine, robotics, and finance. Through this pipeline, GTM learns to produce not only syntactically correct outputs but also logically coherent and contextually appropriate responses. Experiments demonstrate that GTM produces high-quality outputs with strong consistency and reliability. Besides when used in real reinforcement learning scenarios for agent training, GTM exhibits significantly faster simulation speed compared to real tools while maintaining comparable output quality, along with remarkable generalization and domain adaptability. Our results establish GTM as a foundational component for developing future AI agents, enabling efficient and scalable training of tool-augmented systems.

Hallucinations are a key concern when creating applications that rely on Foundation models (FMs). Understanding where and how these subtle failures occur in an application relies on evaluation methods known as \textit{evals}. Prior work focuses on defining new eval methods or benchmark datasets for specific tasks. However, neither helps a software team with a task-specific FM application when there is no metric or dataset. The demand for both automated approaches and deep integration of human insight makes this a challenging problem. We address this gap by proposing an approach to synthesise a FM task-specific evaluator program that provides automation and a custom UI for capturing feedback. The core novelty of our approach lies in: (1) a task-agnostic meta-model that captures properties of any FM task, (2) an interaction protocol for efficient use of human feedback, and (3) an eval synthesiser that selects or generates an appropriate set of evals. We implement our approach in \toolname and demonstrate the concept on two diverse FM tasks: chart data extraction and document question answering. A preliminary evaluation on the quality of our selected evals shows 93\% and 90\% accuracy respectively. Our research tackles a growing problem facing engineering teams, how to evaluate and review outputs from FM tasks.

Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven robots. To enhance the reliability of operation code generated by LLMs, corrective designs with feedback from the observation of executing code have been increasingly adopted in existing research. However, the code execution in these designs relies on either a physical experiment or a customized simulation environment, which limits their deployment due to the high configuration effort of the environment and the potential long execution time. In this paper, we explore the possibility of directly leveraging LLM to enable static simulation of robot operation code, and then leverage it to design a new reliable LLM-driven corrective robot operation code generation framework. Our framework configures the LLM as a static simulator with enhanced capabilities that reliably simulate robot code execution by interpreting actions, reasoning over state transitions, analyzing execution outcomes, and generating semantic observations that accurately capture trajectory dynamics. To validate the performance of our framework, we performed experiments on various operation tasks for different robots, including UAVs and small ground vehicles. The experiment results not only demonstrated the high accuracy of our static text-based simulation but also the reliable code generation of our LLM-driven corrective framework, which achieves a comparable performance with state-of-the-art research while does not rely on dynamic code execution using physical experiments or simulators.

Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on explicit pixel-level triggers or imperceptible perturbations injected into images. While effective, these approaches reduce stealthiness and remain vulnerable to image-based defenses. We introduce concept-guided backdoor attacks, a new paradigm that operates at the semantic concept level rather than on raw pixels. We propose two different attacks. The first, Concept-Thresholding Poisoning (CTP), uses explicit concepts in natural images as triggers: only samples containing the target concept are poisoned, causing the model to behave normally in all other cases but consistently inject malicious outputs whenever the concept appears. The second, CBL-Guided Unseen Backdoor (CGUB), leverages a Concept Bottleneck Model (CBM) during training to intervene on internal concept activations, while discarding the CBM branch at inference time to keep the VLM unchanged. This design enables systematic replacement of a targeted label in generated text (for example, replacing "cat" with "dog"), even when the replacement behavior never appears in the training data. Experiments across multiple VLM architectures and datasets show that both CTP and CGUB achieve high attack success rates while maintaining moderate impact on clean-task performance. These findings highlight concept-level vulnerabilities as a critical new attack surface for VLMs.

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SPD) mitigates this issue by verifying candidate tokens in parallel from a smaller draft model, yet its strict exact-match verification discards many semantically valid continuations. Moreover, existing training-based SPD methods often suffer from performance degradation on out-of-distribution (OOD) tasks. To this end, we propose Training-Free Loosely Speculative Decoding (FLy), a novel method that loosens the rigid verification criterion by leveraging the target model's self-corrective behavior to judge whether a draft-target mismatch remains semantically valid. FLy introduces a two-tier mechanism: an entropy-level gate that identifies whether the current token allows multiple plausible alternatives or is nearly deterministic, and a token-level deferred window that distinguishes genuine errors from differently worded yet semantically correct variants. To further reduce latency, we design a multi-level acceleration strategy that accelerates not only the target model but also the drafter itself. Owing to its training-free design, FLy composes seamlessly with arbitrary draft-target pairs and generalizes across models and domains without hyperparameter re-tuning. Experiments show that FLy preserves more than 99% of the target model's accuracy while achieving an average 2.81x speedup on Llama-3.1-70B-Instruct and 5.07x speedup on the 405B variant. Notably, on out-of-domain datasets, our method remains highly effective and outperforms the training-based method EAGLE-3 by 1.62x.

Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes before assembling sentences with an n-gram language model (LM), preventing joint optimization of all stages simultaneously. Here, we introduce an end-to-end Brain-to-Text (BIT) framework that translates neural activity into coherent sentences using a single differentiable neural network. Central to our approach is a cross-task, cross-species pretrained neural encoder, whose representations transfer to both attempted and imagined speech. In a cascaded setting with an n-gram LM, the pretrained encoder establishes a new state-of-the-art (SOTA) on the Brain-to-Text '24 and '25 benchmarks. Integrated end-to-end with audio large language models (LLMs) and trained with contrastive learning for cross-modal alignment, BIT reduces the word error rate (WER) of the prior end-to-end method from 24.69% to 10.22%. Notably, we find that small-scale audio LLMs markedly improve end-to-end decoding. Beyond record-setting performance, BIT aligns attempted and imagined speech embeddings to enable cross-task generalization. Altogether, our approach advances the integration of large, diverse neural datasets, paving the way for an end-to-end decoding framework that supports seamless, differentiable optimization.

Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better systems is the scarcity of benchmarks that capture the complexity of real therapeutic interactions. Most existing benchmarks either only test clinical knowledge through multiple-choice questions or assess single responses in isolation. To bridge this gap, we present MindEval, a framework designed in collaboration with Ph.D-level Licensed Clinical Psychologists for automatically evaluating language models in realistic, multi-turn mental health therapy conversations. Through patient simulation and automatic evaluation with LLMs, our framework balances resistance to gaming with reproducibility via its fully automated, model-agnostic design. We begin by quantitatively validating the realism of our simulated patients against human-generated text and by demonstrating strong correlations between automatic and human expert judgments. Then, we evaluate 12 state-of-the-art LLMs and show that all models struggle, scoring below 4 out of 6, on average, with particular weaknesses in problematic AI-specific patterns of communication. Notably, reasoning capabilities and model scale do not guarantee better performance, and systems deteriorate with longer interactions or when supporting patients with severe symptoms. We release all code, prompts, and human evaluation data.

Recent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoning, the lack of transparent and reproducible data curation and training strategies remains a major barrier to scalable research. In this work, we introduce OpenMMReasoner, a fully transparent two-stage recipe for multimodal reasoning spanning supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we construct an 874K-sample cold-start dataset with rigorous step-by-step validation, providing a strong foundation for reasoning capabilities. The subsequent RL stage leverages a 74K-sample dataset across diverse domains to further sharpen and stabilize these abilities, resulting in a more robust and efficient learning process. Extensive evaluations demonstrate that our training recipe not only surpasses strong baselines but also highlights the critical role of data quality and training design in shaping multimodal reasoning performance. Notably, our method achieves a 11.6% improvement over the Qwen2.5-VL-7B-Instruct baseline across nine multimodal reasoning benchmarks, establishing a solid empirical foundation for future large-scale multimodal reasoning research. We open-sourced all our codes, pipeline, and data at https://github.com/EvolvingLMMs-Lab/OpenMMReasoner.

Large Language Model (LLM) agents have developed rapidly in recent years to solve complex real-world problems using external tools. However, the scarcity of high-quality trajectories still hinders the development of stronger LLM agents. Most existing works on multi-turn dialogue synthesis validate correctness only at the trajectory level, which may overlook turn-level errors that can propagate during training and degrade model performance. To address these limitations, we introduce ToolMind, a large-scale, high-quality tool-agentic dataset with 160k synthetic data instances generated using over 20k tools and 200k augmented open-source data instances. Our data synthesis pipeline first constructs a function graph based on parameter correlations and then uses a multi-agent framework to simulate realistic user-assistant-tool interactions. Beyond trajectory-level validation, we employ fine-grained turn-level filtering to remove erroneous or suboptimal steps, ensuring that only high-quality reasoning traces are retained. This approach mitigates error amplification during training while preserving self-corrective reasoning signals essential for robust tool-use learning. Models fine-tuned on ToolMind show significant improvements over baselines on several benchmarks.