The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts

When language models correctly parse "The cat that the dog chased meowed," are they analyzing syntax or simply familiar with dogs chasing cats? Despite extensive benchmarking, we lack methods to distinguish structural understanding from semantic pattern matching. We introduce CenterBench, a dataset of 9,720 comprehension questions on center-embedded sentences (like "The cat [that the dog chased] meowed") where relative clauses nest recursively, creating processing demands from simple to deeply nested structures. Each sentence has a syntactically identical but semantically implausible counterpart (e.g., mailmen prescribe medicine, doctors deliver mail) and six comprehension questions testing surface understanding, syntactic dependencies, and causal reasoning. Testing six models reveals that performance gaps between plausible and implausible sentences widen systematically with complexity, with models showing median gaps up to 26.8 percentage points, quantifying when they abandon structural analysis for semantic associations. Notably, semantic plausibility harms performance on questions about resulting actions, where following causal relationships matters more than semantic coherence. Reasoning models improve accuracy but their traces show semantic shortcuts, overthinking, and answer refusal. Unlike models whose plausibility advantage systematically widens with complexity, humans shows variable semantic effects. CenterBench provides the first framework to identify when models shift from structural analysis to pattern matching.

From Watch to Imagine: Steering Long-horizon Manipulation via Human Demonstration and Future Envisionment

Generalizing to long-horizon manipulation tasks in a zero-shot setting remains a central challenge in robotics. Current multimodal foundation based approaches, despite their capabilities, typically fail to decompose high-level commands into executable action sequences from static visual input alone. To address this challenge, we introduce Super-Mimic, a hierarchical framework that enables zero-shot robotic imitation by directly inferring procedural intent from unscripted human demonstration videos. Our framework is composed of two sequential modules. First, a Human Intent Translator (HIT) parses the input video using multimodal reasoning to produce a sequence of language-grounded subtasks. These subtasks then condition a Future Dynamics Predictor (FDP), which employs a generative model that synthesizes a physically plausible video rollout for each step. The resulting visual trajectories are dynamics-aware, explicitly modeling crucial object interactions and contact points to guide the low-level controller. We validate this approach through extensive experiments on a suite of long-horizon manipulation tasks, where Super-Mimic significantly outperforms state-of-the-art zero-shot methods by over 20\%. These results establish that coupling video-driven intent parsing with prospective dynamics modeling is a highly effective strategy for developing general-purpose robotic systems.

CoBel-World: Harnessing LLM Reasoning to Build a Collaborative Belief World for Optimizing Embodied Multi-Agent Collaboration

Effective real-world multi-agent collaboration requires not only accurate planning but also the ability to reason about collaborators' intents -- a crucial capability for avoiding miscoordination and redundant communication under partial observable environments. Due to their strong planning and reasoning capabilities, large language models (LLMs) have emerged as promising autonomous agents for collaborative task solving. However, existing collaboration frameworks for LLMs overlook their reasoning potential for dynamic intent inference, and thus produce inconsistent plans and redundant communication, reducing collaboration efficiency. To bridge this gap, we propose CoBel-World, a novel framework that equips LLM agents with a collaborative belief world -- an internal representation jointly modeling the physical environment and collaborators' mental states. CoBel-World enables agents to parse open-world task knowledge into structured beliefs via a symbolic belief language, and perform zero-shot Bayesian-style belief updates through LLM reasoning. This allows agents to proactively detect potential miscoordination (e.g., conflicting plans) and communicate adaptively. Evaluated on challenging embodied benchmarks (i.e., TDW-MAT and C-WAH), CoBel-World significantly reduces communication costs by 22-60% and improves task completion efficiency by 4-28% compared to the strongest baseline. Our results show that explicit, intent-aware belief modeling is essential for efficient and human-like collaboration in LLM-based multi-agent systems.

Parse Graph-Based Visual-Language Interaction for Human Pose Estimation

Parse graphs boost human pose estimation (HPE) by integrating context and hierarchies, yet prior work mostly focuses on single modality modeling, ignoring the potential of multimodal fusion. Notably, language offers rich HPE priors like spatial relations for occluded scenes, but existing visual-language fusion via global feature integration weakens occluded region responses and causes alignment and location failures. To address this issue, we propose Parse Graph-based Visual-Language interaction (PGVL) with a core novel Guided Module (GM). In PGVL, low-level nodes focus on local features, maximizing the maintenance of responses in occluded areas and high-level nodes integrate global features to infer occluded or invisible parts. GM enables high semantic nodes to guide the feature update of low semantic nodes that have undergone cross attention. It ensuring effective fusion of diverse information. PGVL includes top-down decomposition and bottom-up composition. In the first stage, modality specific parse graphs are constructed. Next stage. recursive bidirectional cross-attention is used, purified by GM. We also design network based on PGVL. The PGVL and our network is validated on major pose estimation datasets. We will release the code soon.

Automated Evidence Extraction and Scoring for Corporate Climate Policy Engagement: A Multilingual RAG Approach

InfluenceMap's LobbyMap Platform monitors the climate policy engagement of over 500 companies and 250 industry associations, assessing each entity's support or opposition to science-based policy pathways for achieving the Paris Agreement's goal of limiting global warming to 1.5{\deg}C. Although InfluenceMap has made progress with automating key elements of the analytical workflow, a significant portion of the assessment remains manual, making it time- and labor-intensive and susceptible to human error. We propose an AI-assisted framework to accelerate the monitoring of corporate climate policy engagement by leveraging Retrieval-Augmented Generation to automate the most time-intensive extraction of relevant evidence from large-scale textual data. Our evaluation shows that a combination of layout-aware parsing, the Nomic embedding model, and few-shot prompting strategies yields the best performance in extracting and classifying evidence from multilingual corporate documents. We conclude that while the automated RAG system effectively accelerates evidence extraction, the nuanced nature of the analysis necessitates a human-in-the-loop approach where the technology augments, rather than replaces, expert judgment to ensure accuracy.

Automating the Deep Space Network Data Systems; A Case Study in Adaptive Anomaly Detection through Agentic AI

The Deep Space Network (DSN) is NASA's largest network of antenna facilities that generate a large volume of multivariate time-series data. These facilities contain DSN antennas and transmitters that undergo degradation over long periods of time, which may cause costly disruptions to the data flow and threaten the earth-connection of dozens of spacecraft that rely on the Deep Space Network for their lifeline. The purpose of this study was to experiment with different methods that would be able to assist JPL engineers with directly pinpointing anomalies and equipment degradation through collected data, and continue conducting maintenance and operations of the DSN for future space missions around our universe. As such, we have researched various machine learning techniques that can fully reconstruct data through predictive analysis, and determine anomalous data entries within real-time datasets through statistical computations and thresholds. On top of the fully trained and tested machine learning models, we have also integrated the use of a reinforcement learning subsystem that classifies identified anomalies based on severity level and a Large Language Model that labels an explanation for each anomalous data entry, all of which can be improved and fine-tuned over time through human feedback/input. Specifically, for the DSN transmitters, we have also implemented a full data pipeline system that connects the data extraction, parsing, and processing workflow all together as there was no coherent program or script for performing these tasks before. Using this data pipeline system, we were able to then also connect the models trained from DSN antenna data, completing the data workflow for DSN anomaly detection. This was all wrapped around and further connected by an agentic AI system, where complex reasoning was utilized to determine the classifications and predictions of anomalous data.

MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models

Paraphrases are a vital tool to assist language understanding tasks such as question answering, style transfer, semantic parsing, and data augmentation tasks. Indic languages are complex in natural language processing (NLP) due to their rich morphological and syntactic variations, diverse scripts, and limited availability of annotated data. In this work, we present the L3Cube-MahaParaphrase Dataset, a high-quality paraphrase corpus for Marathi, a low resource Indic language, consisting of 8,000 sentence pairs, each annotated by human experts as either Paraphrase (P) or Non-paraphrase (NP). We also present the results of standard transformer-based BERT models on these datasets. The dataset and model are publicly shared at https://github.com/l3cube-pune/MarathiNLP

Reliable Weak-to-Strong Monitoring of LLM Agents

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels of agent and monitor situational awareness; (2) distinct adversarial strategies to evade the monitor, such as prompt injection; and (3) two datasets and environments -- SHADE-Arena for tool-calling agents and our new CUA-SHADE-Arena, which extends TheAgentCompany, for computer-use agents. We run MRT on existing LLM monitor scaffoldings, which orchestrate LLMs and parse agent trajectories, alongside a new hybrid hierarchical-sequential scaffolding proposed in this work. Our empirical results yield three key findings. First, agent awareness dominates monitor awareness: an agent's knowledge that it is being monitored substantially degrades the monitor's reliability. On the contrary, providing the monitor with more information about the agent is less helpful than expected. Second, monitor scaffolding matters more than monitor awareness: the hybrid scaffolding consistently outperforms baseline monitor scaffolding, and can enable weaker models to reliably monitor stronger agents -- a weak-to-strong scaling effect. Third, in a human-in-the-loop setting where humans discuss with the LLM monitor to get an updated judgment for the agent's behavior, targeted human oversight is most effective; escalating only pre-flagged cases to human reviewers improved the TPR by approximately 15% at FPR = 0.01. Our work establishes a standard workflow for MRT, highlighting the lack of adversarial robustness for LLMs and humans when monitoring and detecting agent misbehavior. We release code, data, and logs to spur further research.

Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context

Large Language Models (LLMs) have demonstrated impressive fluency and task competence in conversational settings. However, their effectiveness in multi-session and long-term interactions is hindered by limited memory persistence. Typical retrieval-augmented generation (RAG) systems store dialogue history as dense vectors, which capture semantic similarity but neglect finer linguistic structures such as syntactic dependencies, discourse relations, and coreference links. We propose Semantic Anchoring, a hybrid agentic memory architecture that enriches vector-based storage with explicit linguistic cues to improve recall of nuanced, context-rich exchanges. Our approach combines dependency parsing, discourse relation tagging, and coreference resolution to create structured memory entries. Experiments on adapted long-term dialogue datasets show that semantic anchoring improves factual recall and discourse coherence by up to 18% over strong RAG baselines. We further conduct ablation studies, human evaluations, and error analysis to assess robustness and interpretability.

$NavA^3$: Understanding Any Instruction, Navigating Anywhere, Finding Anything

Embodied navigation is a fundamental capability of embodied intelligence, enabling robots to move and interact within physical environments. However, existing navigation tasks primarily focus on predefined object navigation or instruction following, which significantly differs from human needs in real-world scenarios involving complex, open-ended scenes. To bridge this gap, we introduce a challenging long-horizon navigation task that requires understanding high-level human instructions and performing spatial-aware object navigation in real-world environments. Existing embodied navigation methods struggle with such tasks due to their limitations in comprehending high-level human instructions and localizing objects with an open vocabulary. In this paper, we propose $NavA^3$, a hierarchical framework divided into two stages: global and local policies. In the global policy, we leverage the reasoning capabilities of Reasoning-VLM to parse high-level human instructions and integrate them with global 3D scene views. This allows us to reason and navigate to regions most likely to contain the goal object. In the local policy, we have collected a dataset of 1.0 million samples of spatial-aware object affordances to train the NaviAfford model (PointingVLM), which provides robust open-vocabulary object localization and spatial awareness for precise goal identification and navigation in complex environments. Extensive experiments demonstrate that $NavA^3$ achieves SOTA results in navigation performance and can successfully complete longhorizon navigation tasks across different robot embodiments in real-world settings, paving the way for universal embodied navigation. The dataset and code will be made available. Project website: https://NavigationA3.github.io/.