A: e scr ven utin top y; models this is a lik drop e o1 of ac up hie to ve 65.5% less than from 10% their ov accuracy erall accuracy consider under ing s onl tep-wise y final answer equivalence.

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has increasingly explored adversarial attacks on VLMs to reveal their vulnerabilities. However, these attacks either rely on overly strong assumptions, requiring full knowledge of the victim VLM, which is impractical for attacking VLM-based agents, or exhibit limited effectiveness. The latter stems from disrupting most semantic information in the image, which leads to a misalignment between the perception and the task context defined by system prompts. This inconsistency interrupts the VLM's reasoning process, resulting in invalid outputs that fail to affect interactions in the physical world. To this end, we propose a fine-grained adversarial attack framework, ADVEDM, which modifies the VLM's perception of only a few key objects while preserving the semantics of the remaining regions. This attack effectively reduces conflicts with the task context, making VLMs output valid but incorrect decisions and affecting the actions of agents, thus posing a more substantial safety threat in the physical world. We design two variants of based on this framework, ADVEDM-R and ADVEDM-A, which respectively remove the semantics of a specific object from the image and add the semantics of a new object into the image. The experimental results in both general scenarios and EDM tasks demonstrate fine-grained control and excellent attack performance.

Prevailing scene coordinate regression methods for LiDAR localization suffer from localization ambiguities, as distinct locations can exhibit similar geometric signatures -- a challenge that current geometry-based regression approaches have yet to solve. Recent vision-language models show that textual descriptions can enrich scene understanding, supplying potential localization cues missing from point cloud geometries. In this paper, we propose GTR-Loc, a novel text-assisted LiDAR localization framework that effectively generates and integrates geospatial text regularization to enhance localization accuracy. We propose two novel designs: a Geospatial Text Generator that produces discrete pose-aware text descriptions, and a LiDAR-Anchored Text Embedding Refinement module that dynamically constructs view-specific embeddings conditioned on current LiDAR features. The geospatial text embeddings act as regularization to effectively reduce localization ambiguities. Furthermore, we introduce a Modality Reduction Distillation strategy to transfer textual knowledge. It enables high-performance LiDAR-only localization during inference, without requiring runtime text generation. Extensive experiments on challenging large-scale outdoor datasets, including QEOxford, Oxford Radar RobotCar, and NCLT, demonstrate the effectiveness of GTR-Loc. Our method significantly outperforms state-of-the-art approaches, notably achieving a 9.64%/8.04%

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g., missing type annotations). Existing methods, such as supervised fine-tuning and rule-based post-processing, rely on labor-intensive annotations or brittle heuristics, limiting their scalability and effectiveness. We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code using program analysis-guided feedback. Specifically, REAL integrates two automated signals: (1) program analysis detecting security or maintainability defects and (2) unit tests ensuring functional correctness. Unlike prior work, our framework is prompt-agnostic and reference-free, enabling scalable supervision without manual intervention. Experiments across multiple datasets and model scales demonstrate that REAL outperforms state-of-the-art methods in simultaneous assessments of functionality and code quality. Our work bridges the gap between rapid prototyping and production-ready code, enabling LLMs to deliver both speed and quality.

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models but face prohibitive memory demands due to massive parameterization. Existing pruning methods rely on heuristic metrics or impractical enumeration of expert subsets, leading to suboptimal performance or scalability. In this paper, we propose Shapley-MoE, an efficient pruning method for MoE models inspired by cooperative game theory. By quantifying each expert's contribution via Shapley value, our method identifies important experts without exhaustive combination evaluations. To overcome the NP-hard complexity of exact Shapley computation, we introduce a Monte Carlo sampling strategy for efficient approximation that reduces complexity to quadratic time. However, vanilla Monte Carlo sampling still faces issues of insufficient estimation accuracy and low sampling efficiency.

We introduce REAL, a benchmark and framework for multi-turn agent evaluations on deterministic simulations of real-world websites. REAL comprises high-fidelity, publicly hosted, deterministic replicas of 11 widely-used websites across domains such as e-commerce, travel, communication, and professional networking. We also release a benchmark consisting of 112 practical tasks that mirror everyday complex user interactions requiring both accurate information retrieval and state-changing actions. All interactions occur within this fully controlled setting, eliminating safety risks and enabling robust, reproducible evaluation of agent capability and reliability. REAL environments are highly configurable, offer complete action/observation space control, and allow researchers to inspect state-changes at any step to define reward signals for training. Our novel evaluation framework combines programmatic checks of website state for action-based tasks with rubric-guided LLM-based judgments for information retrieval, and our harness supports both open-source and proprietary agentic systems. Our empirical results show that frontier language models achieve at most a 41%success rate on REAL, highlighting critical gaps in current autonomous capabilities. REAL enables easy integration of new tasks, reproducible evaluation, and scalable data generation for post-training web agents. The websites, framework, and leaderboard are available at https://realevals.xyzand https://github.com/agi-inc/REAL.

Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior ef ask: forts can often MLLMs rely on reason explicit about 3D 3D inputs space or specialized using only model structur architectures, ed 2D represenwe tations derived from perception? We introduce Struct2D, a perception-guided prompting marks and object-centric framework that metadata, combines optionally bird's-eye-vie incorporating w (BEV) egocentric images with keyframes object when needed. Using Struct2D, we conduct an in-depth zero-shot analysis of closed-source spatial reasoning MLLMs abilities (e.g.

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average reward, while methods explicitly focused on reducing the probability of undesired outputs typically come at a cost to average-case performance. To improve this tradeoff, we introduce RePULSe, a new training method that augments the standard RL loss with an additional loss that uses learned proposals to guide sampling low-reward outputs, and then reduces those outputs' probability. We run experiments demonstrating that RePULSe produces a better tradeoff of expected reward versus the probability of undesired outputs and is more adversarially robust, compared to standard RL alignment approaches and alternatives.

Large language models have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity of multi-hop queries as well as the irrelevant retrieved content. To address these limitations, we propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds through a selfincentivized process. At each step, the LLM decides what to retrieve (thinking), triggers an external retriever (search), and extracts fine-grained evidence (recording) to support next-step reasoning. To enable LLM with this capability, EXSEARCH adopts a generalized expectation-maximization algorithm.

Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also called efficient LLM evaluation) aims to select a small subset of evaluation points and predict overall benchmark performance from that subset. In this paper, we systematically assess the strengths and limitations of 11 benchmark prediction methods across 19 diverse benchmarks. First, we identify a highly competitive baseline: Take a random sample and fit a regression model on the sample to predict missing entries. Outperforming most existing methods, this baseline challenges the assumption that careful subset selection is necessary for benchmark prediction.