Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the stateless nature of large language models (LLMs), these agents rely heavily on external memory systems to maintain context across interactions. Unlike centralized systems where context is securely stored server-side, agent memory is often managed client-side or by third-party applications, creating significant security vulnerabilities. This was recently exploited to attack production systems. We introduce and formalize "plan injection," a novel context manipulation attack that corrupts these agents' internal task representations by targeting this vulnerable context. Through systematic evaluation of two popular web agents, Browser-use and Agent-E, we show that plan injections bypass robust prompt injection defenses, achieving up to 3x higher attack success rates than comparable prompt-based attacks. Furthermore, "context-chained injections," which craft logical bridges between legitimate user goals and attacker objectives, lead to a 17.7% increase in success rate for privacy exfiltration tasks. Our findings highlight that secure memory handling must be a first-class concern in agentic systems.

Accurate and complete product descriptions are crucial for e-commerce, yet seller-provided information often falls short. Customer reviews offer valuable details but are laborious to sift through manually. We present PRAISE: Product Review Attribute Insight Structuring Engine, a novel system that uses Large Language Models (LLMs) to automatically extract, compare, and structure insights from customer reviews and seller descriptions. PRAISE provides users with an intuitive interface to identify missing, contradictory, or partially matching details between these two sources, presenting the discrepancies in a clear, structured format alongside supporting evidence from reviews. This allows sellers to easily enhance their product listings for clarity and persuasiveness, and buyers to better assess product reliability. Our demonstration showcases PRAISE's workflow, its effectiveness in generating actionable structured insights from unstructured reviews, and its potential to significantly improve the quality and trustworthiness of e-commerce product catalogs.

As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak oracle problem: given a model, prompt, and decoding strategy, determine whether a jailbreak response can be generated with likelihood exceeding a specified threshold. This formalization enables a principled study of jailbreak vulnerabilities. Answering the jailbreak oracle problem poses significant computational challenges -- the search space grows exponentially with the length of the response tokens. We present Boa, the first efficient algorithm for solving the jailbreak oracle problem. Boa employs a three-phase search strategy: (1) constructing block lists to identify refusal patterns, (2) breadth-first sampling to identify easily accessible jailbreaks, and (3) depth-first priority search guided by fine-grained safety scores to systematically explore promising low-probability paths. Boa enables rigorous security assessments including systematic defense evaluation, standardized comparison of red team attacks, and model certification under extreme adversarial conditions.

We present Mercury, a new generation of commercial-scale large language models (LLMs) based on diffusion. These models are parameterized via the Transformer architecture and trained to predict multiple tokens in parallel. In this report, we detail Mercury Coder, our first set of diffusion LLMs designed for coding applications. Currently, Mercury Coder comes in two sizes: Mini and Small. These models set a new state-of-the-art on the speed-quality frontier. Based on independent evaluations conducted by Artificial Analysis, Mercury Coder Mini and Mercury Coder Small achieve state-of-the-art throughputs of 1109 tokens/sec and 737 tokens/sec, respectively, on NVIDIA H100 GPUs and outperform speed-optimized frontier models by up to 10x on average while maintaining comparable quality. We discuss additional results on a variety of code benchmarks spanning multiple languages and use-cases as well as real-world validation by developers on Copilot Arena, where the model currently ranks second on quality and is the fastest model overall. We also release a public API at https://platform.inceptionlabs.ai/ and free playground at https://chat.inceptionlabs.ai

This study investigates semantic uncertainty in large language model (LLM) outputs across different decoding methods, focusing on emerging techniques like speculative sampling and chain-of-thought (CoT) decoding. Through experiments on question answering, summarization, and code generation tasks, we analyze how different decoding strategies affect both the diversity and reliability of model outputs. Our findings reveal that while CoT decoding demonstrates higher semantic diversity, it maintains lower predictive entropy, suggesting that structured exploration can lead to more confident and accurate outputs. This is evidenced by a 48.8% improvement in code generation Pass@2 rates, despite lower alignment with reference solutions. For summarization tasks, speculative sampling proved particularly effective, achieving superior ROUGE scores while maintaining moderate semantic diversity. Our results challenge conventional assumptions about trade-offs between diversity and accuracy in language model outputs, demonstrating that properly structured decoding methods can increase semantic exploration while maintaining or improving output quality. These findings have significant implications for deploying language models in practical applications where both reliability and diverse solution generation are crucial.

Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of knowledge erasure more efficient and effective by removing specific knowledge while preserving overall model performance, especially for retained information. However, it has been observed that the unlearning techniques tend to suppress and leave the knowledge beneath the surface, thus making it retrievable with the right prompts. In this work, we demonstrate that \textit{step-by-step reasoning} can serve as a backdoor to recover this hidden information. We introduce a step-by-step reasoning-based black-box attack, Sleek, that systematically exposes unlearning failures. We employ a structured attack framework with three core components: (1) an adversarial prompt generation strategy leveraging step-by-step reasoning built from LLM-generated queries, (2) an attack mechanism that successfully recalls erased content, and exposes unfair suppression of knowledge intended for retention and (3) a categorization of prompts as direct, indirect, and implied, to identify which query types most effectively exploit unlearning weaknesses. Through extensive evaluations on four state-of-the-art unlearning techniques and two widely used LLMs, we show that existing approaches fail to ensure reliable knowledge removal. Of the generated adversarial prompts, 62.5% successfully retrieved forgotten Harry Potter facts from WHP-unlearned Llama, while 50% exposed unfair suppression of retained knowledge. Our work highlights the persistent risks of information leakage, emphasizing the need for more robust unlearning strategies for erasure.

Retrieval-Augmented Generation (RAG) systems are increasingly vital for navigating the ever-expanding body of scientific literature, particularly in high-stakes domains such as chemistry. Despite the promise of RAG, foundational design choices -- such as how documents are segmented and represented -- remain underexplored in domain-specific contexts. This study presents the first large-scale, systematic evaluation of chunking strategies and embedding models tailored to chemistry-focused RAG systems. We investigate 25 chunking configurations across five method families and evaluate 48 embedding models on three chemistry-specific benchmarks, including the newly introduced QuestChemRetrieval dataset. Our results reveal that recursive token-based chunking (specifically R100-0) consistently outperforms other approaches, offering strong performance with minimal resource overhead. We also find that retrieval-optimized embeddings -- such as Nomic and Intfloat E5 variants -- substantially outperform domain-specialized models like SciBERT. By releasing our datasets, evaluation framework, and empirical benchmarks, we provide actionable guidelines for building effective and efficient chemistry-aware RAG systems.

Recent advances in vision-language models (VLMs) have greatly improved cross-modal semantic understanding, yet significant limitations remain in fine-grained discrimination and deep causal reasoning tasks. Existing VLMs often rely on superficial statistical correlations, lacking the ability to capture the underlying causal logic between visual and textual content. To address this, we propose CounterFactual Vision-Language Fine-tuning (CF-VLM), a novel framework that enhances the causal reasoning capabilities of VLMs through the targeted use of counterfactual samples. CF-VLM introduces three complementary training objectives: maintaining foundational cross-modal alignment, reinforcing the uniqueness and stability of factual scene representations against coherent counterfactuals, and sharpening the model's sensitivity to minimal but critical causal edits. Extensive experiments demonstrate that CF-VLM consistently outperforms strong baselines and state-of-the-art methods on compositional reasoning and generalization benchmarks. Furthermore, it shows promise in mitigating visual hallucinations, indicating improved factual consistency. Our CF-VLM provides a robust foundation for deploying VLMs in high-stakes, real-world scenarios requiring reliable reasoning and interpretability.

Large language models (LLMs) [1, 8, 13] have become central to natural language processing (NLP) but their adaptation to downstream tasks remains resource-intensive. Fine-tuning these models, particularly using gradient-based methods [16, 11, 15], requires substantial memory and compute due to the overhead of backpropagation. Zeroth-order optimization (ZO) [18, 23] has emerged as a promising alternative, offering memory-efficient fine-tuning by estimating gradients through forward passes alone. This approach is especially appealing for environments with limited computational resources, such as edge devices or single-GPU setups [9]. However, despite its advantages, ZO typically exhibits slower convergence and higher variance in gradient estimates [14, 18, 7], often leading to suboptimal model performance. Prior work has explored algorithmic adjustments, including tuning hyperparameters like perturbation magnitude and sampling strategies. However, these refinements have produced only limited improvements [22, 23]. This limitation suggests a need for complementary strategies that address ZO's sensitivity to data characteristics. This paper presents a new perspective on adapting training data for ZO.

The rapid growth of large language models (LLMs) has outpaced the memory constraints of edge devices, necessitating extreme weight compression beyond the 1-bit limit. While quantization reduces model size, it is fundamentally limited to 1 bit per weight. Existing multiple-to-one compression methods either rely on mapping tables (inducing memory overhead) or incur severe accuracy degradation due to random weight grouping. We introduce UltraSketchLLM, an index-free, sketch-based framework that achieves ultra-low bit compression (down to 0.5 bits per weight) while preserving model performance. UltraSketchLLM leverages data sketching, a sub-linear representation technique from streaming applications, to map multiple weights to single values with bounded error. Our approach integrates an underestimate AbsMaxMin sketch to minimize relative errors for small weights, importance-aware space allocation to prioritize salient weights, and a straight-through estimator for compression-aware finetuning. Experiments on Llama-3.2-1B demonstrate up to 0.5-bit compression with competitive perplexity, alongside tolerable latency overhead. UltraSketchLLM offers a practical solution for deploying LLMs in resource-constrained environments.