Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate safety reasoning at two levels: (1) an action-level dataset that tests whether a single action is safe given its environmental context, and (2) a plan-level dataset that evaluates whether agents can generate safe long-horizon plans for complex hazardous household tasks. CAPSafe models safety conditions where hazards are situational (inferred from object properties), multiple hazards can co-occur within the same environment, and each is annotated with a relative severity level for fine-grained analysis. Evaluating nine closed and open-source LLMs reveals a substantial gap between hazard recognition and safe long-horizon planning. Several models achieve high accuracy in recognizing unsafe actions (exceeding 90% in the best cases), yet safe long-horizon planning remains substantially harder. Gemini-3-pro achieves the highest safe success rate (78.19%), while other models remain below 65%. These results highlight that robust safety reasoning over long action sequences remains an open challenge.

In this work, we explore the use of large language models (LLMs) as interpreters of user utterances within a human-robot language interface. A user interacting with a robot that operates in a physical environment should be able to issue commands that interrupt the robot’s actions, for example, corrections or refinement of the task. This study addresses the context-aware interpretation of user utterances, including those issued while the robot is actively engaged in task execution, exploring whether LLMs, without fine-tuning, can translate user commands into corresponding sequences of robot actions. Using an interactive multimodal interface—combining text and video—for a virtual robot operating in simulated home environments, we collect a dataset of user utterances that guide the robot through various household tasks simultaneously capturing manual interpretation when the automatic one fails. Driven by practical considerations, the collected dataset is used to compare the interpretive performance of GPT models with smaller publicly available alternatives. Our findings reveal that action-interrupting utterances pose challenges for all models. While GPT consistently outperforms the smaller models, interpretation accuracy improves across the board when relevant dynamically selected in-context learning examples are included in the prompt.

We introduce Conversational Object Grounding, a new task in which an agent must identify a target object in a complex 3D scene by engaging in natural language dialogue with a user who knows the target. It extends multimodal reference resolution on a single referring expression to conversations over multiple turns, combining it with clarification question generation and answer understanding to resolve ambiguities. For this task, we propose a zero-shot modular approach that combines the reference resolution, object captioning, and dialogue capabilities of foundation models, using prompt chaining in conjunction with an image-grounded scene graph. Evaluations on a new benchmark constructed with 3D scenes from ScanNet show that the proposed modular approach outperforms end-to-end baselines in terms of both grounding performance (up to 13% improvement) and image processing cost (up to 63% reduction).

When retrieved evidence contradicts parametric memory, language models frequently ignore the context and revert to memorized priors—a failure that undermines the purpose of retrieval augmentation. Contrastive decoding amplifies context-conditioned output to suppress parametric bias, but fixed coefficients cannot track changing disagreement, while output-only adaptive coefficients observe only the final prediction distributions. We propose FIDES (Faithful Inference via Deep Evidence Signals), a training-free decoder that combines signals from output distributions, hidden representations, and prediction trajectories to recompute contrastive intervention strength at every step. A matched, formula-verified audit on 128 NQ-Swap pairs shows that conflict raises Opposition by 0.0969 and the resulting coefficient α by 0.0727 at the same answer-prediction position (both p < 10⁻⁴). The audit also finds only a small Shift effect and saturated clipped Noise, clarifying the limits of the mechanism interpretation. Across three benchmarks and six backbones—four primary 7B/8B models and two scaling backbones up to 70B—FIDES achieves the best context fidelity in all 18 settings, outperforming the strongest training-free baseline by +3 to +13 points. At 70B, fidelity reaches 92–94% while F1 reaches 62–63%, showing that multi-depth stepwise contrast can preserve generation utility while improving evidence following.

Embodied agents performing complex tasks are susceptible to execution failures, motivating the need for effective failure recovery mechanisms. In this work, we introduce a conditional multi-stage failure recovery framework that employs zero-shot chain prompting. The framework is structured into four error-handling stages, with three operating during task execution and one functioning as a post-execution reflection phase.Our approach utilises the reasoning capabilities of LLMs to analyse execution challenges within their environmental context and devise strategic solutions.We evaluate our method on the TfD benchmark of the TEACH dataset and achieve state-of-the-art performance, outperforming a baseline without error recovery by 11.5% and surpassing the strongest existing model by 19%.

Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space defense due to their reliance on overfitting high-perplexity trigger patterns. We firstly reveal that, model editing in the fingerprint domain exhibits unique advantages including significantly lower false positive rates, enhanced harmlessness, and superior robustness. Building on this foundation, this paper innovatively proposes a Prefix-enhanced Fingerprint Editing Framework (PREE), which encodes copyright information into parameter offsets through dual-channel knowledge edit to achieve covert embedding of fingerprint features. Experimental results demonstrate that the proposed solution achieves the 90% trigger precision in mainstream architectures including LLaMA-3 and Qwen-2.5. The minimal parameter offset (change rate < 0.03) effectively preserves original knowledge representation while demonstrating strong robustness against incremental fine-tuning and multi-dimensional defense strategies, maintaining zero false positive rate throughout evaluations.