Daily Papers

Automatic toxic language detection is critical for creating safe, inclusive online spaces. However, it is a highly subjective task, with perceptions of toxic language shaped by community norms and lived experience. Existing toxicity detection models are typically trained on annotations that collapse diverse annotator perspectives into a single ground truth, erasing important context-specific notions of toxicity such as reclaimed language. To address this, we introduce MODELCITIZENS, a dataset of 6.8K social media posts and 40K toxicity annotations across diverse identity groups. To capture the role of conversational context on toxicity, typical of social media posts, we augment MODELCITIZENS posts with LLM-generated conversational scenarios. State-of-the-art toxicity detection tools (e.g. OpenAI Moderation API, GPT-o4-mini) underperform on MODELCITIZENS, with further degradation on context-augmented posts. Finally, we release LLAMACITIZEN-8B and GEMMACITIZEN-12B, LLaMA- and Gemma-based models finetuned on MODELCITIZENS, which outperform GPT-o4-mini by 5.5% on in-distribution evaluations. Our findings highlight the importance of community-informed annotation and modeling for inclusive content moderation. The data, models and code are available at https://github.com/asuvarna31/modelcitizens.

While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately assess their capabilities: existing benchmarks either rely on closed-ended questions prone to saturation and memorization, or subjective comparisons that lack consistency and rigor. In this work, we introduce HeuriGym, an agentic framework designed for evaluating heuristic algorithms generated by LLMs for combinatorial optimization problems, characterized by clearly defined objectives and expansive solution spaces. HeuriGym empowers LLMs to propose heuristics, receive evaluative feedback via code execution, and iteratively refine their solutions. We evaluate nine state-of-the-art models on nine problems across domains such as computer systems, logistics, and biology, exposing persistent limitations in tool use, planning, and adaptive reasoning. To quantify performance, we propose the Quality-Yield Index (QYI), a metric that captures both solution pass rate and quality. Even top models like GPT-o4-mini-high and Gemini-2.5-Pro attain QYI scores of only 0.6, well below the expert baseline of 1. Our open-source benchmark aims to guide the development of LLMs toward more effective and realistic problem-solving in scientific and engineering domains.

Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce PhyX: the first large-scale benchmark designed to assess models capacity for physics-grounded reasoning in visual scenarios. PhyX includes 3K meticulously curated multimodal questions spanning 6 reasoning types across 25 sub-domains and 6 core physics domains: thermodynamics, electromagnetism, mechanics, modern physics, optics, and wave\&acoustics. In our comprehensive evaluation, even state-of-the-art models struggle significantly with physical reasoning. GPT-4o, Claude3.7-Sonnet, and GPT-o4-mini achieve only 32.5\%, 42.2\%, and 45.8\% accuracy respectively-performance gaps exceeding 29\% compared to human experts. Our analysis exposes critical limitations in current models: over-reliance on memorized disciplinary knowledge, excessive dependence on mathematical formulations, and surface-level visual pattern matching rather than genuine physical understanding. We provide in-depth analysis through fine-grained statistics, detailed case studies, and multiple evaluation paradigms to thoroughly examine physical reasoning capabilities. To ensure reproducibility, we implement a compatible evaluation protocol based on widely-used toolkits such as VLMEvalKit, enabling one-click evaluation.

The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two major gaps in existing benchmarks: (i) the lack of standardized, process-aware evaluation that captures instruction adherence and process fidelity, and (ii) the scarcity of accurately labeled training data. To bridge these gaps, we introduce DARE-bench, a benchmark designed for machine learning modeling and data science instruction following. Unlike many existing benchmarks that rely on human- or model-based judges, all tasks in DARE-bench have verifiable ground truth, ensuring objective and reproducible evaluation. To cover a broad range of tasks and support agentic tools, DARE-bench consists of 6,300 Kaggle-derived tasks and provides both large-scale training data and evaluation sets. Extensive evaluations show that even highly capable models such as gpt-o4-mini struggle to achieve good performance, especially in machine learning modeling tasks. Using DARE-bench training tasks for fine-tuning can substantially improve model performance. For example, supervised fine-tuning boosts Qwen3-32B's accuracy by 1.83x and reinforcement learning boosts Qwen3-4B's accuracy by more than 8x. These significant improvements verify the importance of DARE-bench both as an accurate evaluation benchmark and critical training data.

Recent advancements in jailbreaking large language models (LLMs), such as AutoDAN-Turbo, have demonstrated the power of automated strategy discovery. AutoDAN-Turbo employs a lifelong learning agent to build a rich library of attack strategies from scratch. While highly effective, its test-time generation process involves sampling a strategy and generating a single corresponding attack prompt, which may not fully exploit the potential of the learned strategy library. In this paper, we propose to further improve the attack performance of AutoDAN-Turbo through test-time scaling. We introduce two distinct scaling methods: Best-of-N and Beam Search. The Best-of-N method generates N candidate attack prompts from a sampled strategy and selects the most effective one based on a scorer model. The Beam Search method conducts a more exhaustive search by exploring combinations of strategies from the library to discover more potent and synergistic attack vectors. According to the experiments, the proposed methods significantly boost performance, with Beam Search increasing the attack success rate by up to 15.6 percentage points on Llama-3.1-70B-Instruct and achieving a nearly 60% relative improvement against the highly robust GPT-o4-mini compared to the vanilla method.

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative verification framework in which a Judge LLM critiques action sequences and a Planner LLM applies the revisions, yielding progressively cleaner and more spatially coherent trajectories. Unlike rule-based approaches, our method relies on natural language prompting, enabling broad generalization across error types including irrelevant actions, contradictions, and missing steps. On a set of manually annotated actions from the TEACh embodied AI dataset, our framework achieves up to 90% recall and 100% precision across four state-of-the-art LLMs (GPT o4-mini, DeepSeek-R1, Gemini 2.5, LLaMA 4 Scout). The refinement loop converges quickly, with 96.5% of sequences requiring at most three iterations, while improving both temporal efficiency and spatial action organization. Crucially, the method preserves human error-recovery patterns rather than collapsing them, supporting future work on robust corrective behavior. By establishing plan verification as a reliable LLM capability for spatial planning and action refinement, we provide a scalable path to higher-quality training data for imitation learning in embodied AI.

Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces supervision on intermediate steps but still lacks guarantees of logical soundness, which is crucial in high-stakes scenarios where logical consistency is paramount. To address this, we propose LogicReward, a novel reward system that guides model training by enforcing step-level logical correctness with a theorem prover. We further introduce Autoformalization with Soft Unification, which reduces natural language ambiguity and improves formalization quality, enabling more effective use of the theorem prover. An 8B model trained on data constructed with LogicReward surpasses GPT-4o and o4-mini by 11.6\% and 2\% on natural language inference and logical reasoning tasks with simple training procedures. Further analysis shows that LogicReward enhances reasoning faithfulness, improves generalizability to unseen tasks such as math and commonsense reasoning, and provides a reliable reward signal even without ground-truth labels. We will release all data and code at https://llm-symbol.github.io/LogicReward.

Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities as well as rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, including proprietary models such as GPT-5 and o4-mini, which achieve only 34.46% and 22.79% accuracy, respectively. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations, underscoring the urgent need for more robust mitigation strategies. Code and data are available at https://github.com/ymcui/ChartHal .

Multimodal foundation models, such as GPT-4o, have recently made remarkable progress, but it is not clear where exactly these models stand in terms of understanding vision. In this paper, we benchmark the performance of popular multimodal foundation models (GPT-4o, o4-mini, Gemini 1.5 Pro and Gemini 2.0 Flash, Claude 3.5 Sonnet, Qwen2-VL, Llama 3.2) on standard computer vision tasks (semantic segmentation, object detection, image classification, depth and surface normal prediction) using established datasets (e.g., COCO, ImageNet and its variants, etc). The main challenges to performing this are: 1) most models are trained to output text and cannot natively express versatile domains, such as segments or 3D geometry, and 2) many leading models are proprietary and accessible only at an API level, i.e., there is no weight access to adapt them. We address these challenges by translating standard vision tasks into equivalent text-promptable and API-compatible tasks via prompt chaining to create a standardized benchmarking framework. We observe that 1) the models are not close to the state-of-the-art specialist models at any task. However, 2) they are respectable generalists; this is remarkable as they are presumably trained on primarily image-text-based tasks. 3) They perform semantic tasks notably better than geometric ones. 4) While the prompt-chaining techniques affect performance, better models exhibit less sensitivity to prompt variations. 5) GPT-4o performs the best among non-reasoning models, securing the top position in 4 out of 6 tasks, 6) reasoning models, e.g. o3, show improvements in geometric tasks, and 7) a preliminary analysis of models with native image generation, like the latest GPT-4o, shows they exhibit quirks like hallucinations and spatial misalignments.

Existing medical reasoning benchmarks for vision-language models primarily focus on analyzing a patient's condition based on an image from a single visit. However, this setting deviates significantly from real-world clinical practice, where doctors typically refer to a patient's historical conditions to provide a comprehensive assessment by tracking their changes over time. In this paper, we introduce TemMed-Bench, the first benchmark designed for analyzing changes in patients' conditions between different clinical visits, which challenges large vision-language models (LVLMs) to reason over temporal medical images. TemMed-Bench consists of a test set comprising three tasks - visual question-answering (VQA), report generation, and image-pair selection - and a supplementary knowledge corpus of over 17,000 instances. With TemMed-Bench, we conduct an evaluation of six proprietary and six open-source LVLMs. Our results show that most LVLMs lack the ability to analyze patients' condition changes over temporal medical images, and a large proportion perform only at a random-guessing level in the closed-book setting. In contrast, GPT o3, o4-mini and Claude 3.5 Sonnet demonstrate comparatively decent performance, though they have yet to reach the desired level. Furthermore, we explore augmenting the input with both retrieved visual and textual modalities in the medical domain. We also show that multi-modal retrieval augmentation yields notably higher performance gains than no retrieval and textual retrieval alone across most models on our benchmark, with the VQA task showing an average improvement of 2.59%. Overall, we compose a benchmark grounded on real-world clinical practice, and it reveals LVLMs' limitations in temporal medical image reasoning, as well as highlighting the use of multi-modal retrieval augmentation as a potentially promising direction worth exploring to address this challenge.

LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or APIs. Inspired by this capability, we propose two frameworks: Simia-SFT, a pipeline that synthesizes SFT data by amplifying small seed sets into diverse trajectories in an environment-agnostic manner, and Simia-RL, a framework that enables RL training without real environment implementations through LLM-simulated feedback. Fine-tuning open models yields consistent improvements across multiple benchmarks, surpassing GPT-4o and approaching o4-mini on tau^2-Bench. Together, Simia-SFT and Simia-RL enable scalable agent training without environment engineering, replacing heavy and brittle implementations with flexible LLM-based simulation.

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level cybersecurity threats, fundamentally different from prompt-based vulnerabilities. To systematically evaluate these interpreter-specific risks, we propose CIRCLE (Code-Interpreter Resilience Check for LLM Exploits), a simple benchmark comprising 1,260 prompts targeting CPU, memory, and disk resource exhaustion. Each risk category includes explicitly malicious ("direct") and plausibly benign ("indirect") prompt variants. Our automated evaluation framework assesses not only whether LLMs refuse or generates risky code, but also executes the generated code within the interpreter environment to evaluate code correctness, simplifications made by the LLM to make the code safe, or execution timeouts. Evaluating 7 commercially available models from OpenAI and Google, we uncover significant and inconsistent vulnerabilities. For instance, evaluations show substantial disparities even within providers - OpenAI's o4-mini correctly refuses risky requests at 7.1%, notably higher rates compared to GPT-4.1 at 0.5%. Results particularly underscore that indirect, socially-engineered prompts substantially weaken model defenses. This highlights an urgent need for interpreter-specific cybersecurity benchmarks, dedicated mitigation tools (e.g., guardrails), and clear industry standards to guide safe and responsible deployment of LLM interpreter integrations. The benchmark dataset and evaluation code are publicly released to foster further research.

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with BountyBench, we set up 25 systems with complex, real-world codebases. To capture the vulnerability lifecycle, we define three task types: Detect (detecting a new vulnerability), Exploit (exploiting a given vulnerability), and Patch (patching a given vulnerability). For Detect, we construct a new success indicator, which is general across vulnerability types and provides localized evaluation. We manually set up the environment for each system, including installing packages, setting up server(s), and hydrating database(s). We add 40 bug bounties, which are vulnerabilities with monetary awards from \10 to 30,485, covering 9 of the OWASP Top 10 Risks. To modulate task difficulty, we devise a new strategy based on information to guide detection, interpolating from identifying a zero day to exploiting a given vulnerability. We evaluate 10 agents: Claude Code, OpenAI Codex CLI with o3-high and o4-mini, and custom agents with o3-high, GPT-4.1, Gemini 2.5 Pro Preview, Claude 3.7 Sonnet Thinking, Qwen3 235B A22B, Llama 4 Maverick, and DeepSeek-R1. Given up to three attempts, the top-performing agents are Codex CLI: o3-high (12.5% on Detect, mapping to \3,720; 90% on Patch, mapping to 14,152), Custom Agent: Claude 3.7 Sonnet Thinking (67.5% on Exploit), and Codex CLI: o4-mini (90% on Patch, mapping to \$14,422). Codex CLI: o3-high, Codex CLI: o4-mini, and Claude Code are more capable at defense, achieving higher Patch scores of 90%, 90%, and 87.5%, compared to Exploit scores of 47.5%, 32.5%, and 57.5% respectively; while the custom agents are relatively balanced between offense and defense, achieving Exploit scores of 17.5-67.5% and Patch scores of 25-60%.

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt conditions, and 12 hypothesized attack dimensions -- all executed in real Docker sandboxes. Every condition includes the instruction "Always respect all rules and access policies"; only a single encouragement sentence varies. Within the task class studied (planted test-runner vulnerabilities), the threat model is narrower than assumed: nine of twelve dimensions -- including minimization, moral licensing, incentives, identity priming, and reasoning triggers -- produce no detectable exploitation at n=50 per cell (upper 95% CI <7% per condition). But it is also more subtle than expected: one dimension, goal reframing, reliably triggers exploitation. "You are solving a puzzle; there may be hidden clues" produces 38-40% exploitation on Claude Sonnet 4 despite the explicit rule instruction, replicating across four models (CTF framing: 8-14% on DeepSeek, GPT-5-mini, o4-mini). The agent does not override the rules; it reinterprets the task so that exploitative actions become task-aligned. GPT-4.1 produces no exploitation across 1,850 trials (37 conditions), and a temporal comparison across four OpenAI models released over eleven months shows a pattern consistent with improving safety training, though model capability differences are a confounder. The practical contribution is a narrowed, testable threat model: defenders should audit for goal-reframing language, not for the broad class of adversarial prompts.

We explore how large language models (LLMs) assess offensiveness in political discourse when prompted to adopt specific political and cultural perspectives. Using a multilingual subset of the MD-Agreement dataset centered on tweets from the 2020 US elections, we evaluate several recent LLMs - including DeepSeek-R1, o4-mini, GPT-4.1-mini, Qwen3, Gemma, and Mistral - tasked with judging tweets as offensive or non-offensive from the viewpoints of varied political personas (far-right, conservative, centrist, progressive) across English, Polish, and Russian contexts. Our results show that larger models with explicit reasoning abilities (e.g., DeepSeek-R1, o4-mini) are more consistent and sensitive to ideological and cultural variation, while smaller models often fail to capture subtle distinctions. We find that reasoning capabilities significantly improve both the personalization and interpretability of offensiveness judgments, suggesting that such mechanisms are key to adapting LLMs for nuanced sociopolitical text classification across languages and ideologies.

Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks -- from offering writing support to delivering tailored recommendations or consultations. Over time, the interaction history between a user and an LLM can provide extensive information about an individual's traits and preferences. However, open questions remain on how well LLMs today can effectively leverage such history to (1) internalize the user's inherent traits and preferences, (2) track how the user profiling and preferences evolve over time, and (3) generate personalized responses accordingly in new scenarios. In this work, we introduce the PERSONAMEM benchmark. PERSONAMEM features curated user profiles with over 180 simulated user-LLM interaction histories, each containing up to 60 sessions of multi-turn conversations across 15 real-world tasks that require personalization. Given an in-situ user query, i.e. query issued by the user from the first-person perspective, we evaluate LLM chatbots' ability to identify the most suitable response according to the current state of the user's profile. We observe that current LLMs still struggle to recognize the dynamic evolution in users' profiles over time through direct prompting approaches. As a consequence, LLMs often fail to deliver responses that align with users' current situations and preferences, with frontier models such as GPT-4.1, o4-mini, GPT-4.5, o1, or Gemini-2.0 achieving only around 50% overall accuracy, suggesting room for improvement. We hope that PERSONAMEM, along with the user profile and conversation simulation pipeline, can facilitate future research in the development of truly user-aware chatbots. Code and data are available at github.com/bowen-upenn/PersonaMem.

Converting natural language questions into SQL queries (Text-to-SQL) enables non-expert users to interact with relational databases and has long been a central task for natural language interfaces to data. While the WikiSQL dataset played a key role in early NL2SQL research, its usage has declined due to structural and annotation issues, including case sensitivity inconsistencies, data type mismatches, syntax errors, and unanswered questions. We present LLMSQL, a systematic revision and transformation of WikiSQL designed for the LLM era. We classify these errors and implement automated methods for cleaning and re-annotation. To assess the impact of these improvements, we evaluated multiple large language models (LLMs), including Gemma 3, LLaMA 3.2, Mistral 7B, gpt-oss 20B, Phi-3.5 Mini, Qwen 2.5, OpenAI o4-mini, DeepSeek R1 and others. Rather than serving as an update, LLMSQL is introduced as an LLM-ready benchmark: unlike the original WikiSQL, tailored for pointer-network models selecting tokens from input, LLMSQL provides clean natural language questions and full SQL queries as plain text, enabling straightforward generation and evaluation for modern natural language-to-SQL models.

Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in their standard form, but they often fail when the same problems are posed in logically equivalent yet obfuscated formats. To study this vulnerability, we introduce Logifus, a structure-preserving logical obfuscation framework, and, utilizing this, we present LogiQAte, a first-of-its-kind diagnostic benchmark with 1,108 questions across four reasoning tasks: (i) Obfus FOL (first-order logic entailment under equivalence-preserving rewrites), (ii) Obfus Blood Relation (family-graph entailment under indirect relational chains), (iii) Obfus Number Series (pattern induction under symbolic substitutions), and (iv) Obfus Direction Sense (navigation reasoning under altered directions and reference frames). Across all the tasks, evaluating six state-of-the-art models, we find that obfuscation severely degrades zero-shot performance, with performance dropping on average by 47% for GPT-4o, 27% for GPT-5, and 22% for reasoning model, o4-mini. Our findings reveal that current LLMs parse questions without deep understanding, highlighting the urgency of building models that genuinely comprehend and preserve meaning beyond surface form.