Related papers: When Only the Final Text Survives: Implicit Execut…
Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is…
Multi-agent systems have demonstrated the ability to improve performance on a variety of predictive tasks by leveraging collaborative decision making. However, the lack of effective evaluation methodologies has made it difficult to estimate…
Missing data in tabular dataset is a common issue as the performance of downstream tasks usually depends on the completeness of the training dataset. Previous missing data imputation methods focus on numeric and categorical columns, but we…
Implicit assumptions and priors are often necessary in text-to-image generation tasks, especially when textual prompts lack sufficient context. However, these assumptions can sometimes reflect outdated concepts, inaccuracies, or societal…
AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…
Text-to-audio (TTA) systems are rapidly transforming music creation and distribution, with platforms like Udio and Suno generating thousands of tracks daily and integrating into mainstream music platforms and ecosystems. These systems,…
Most state-of-the-art information extraction approaches rely on token-level labels to find the areas of interest in text. Unfortunately, these labels are time-consuming and costly to create, and consequently, not available for many…
Although existing fashionable generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, they often result in the inclusion of irrelevant and redundant tokens in rewritten utterances due to their inability…
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…
Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that…
In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering. For example,…
The rapid proliferation of multimodal generative models has sparked critical discussions on their reliability, fairness and potential for misuse. While text-to-image models excel at producing high-fidelity, user-guided content, they often…
Communication lays the foundation for human cooperation. It is also crucial for multi-agent cooperation. However, existing work focuses on broadcast communication, which is not only impractical but also leads to information redundancy that…
This position paper argues that the Authorization-Execution Gap (AEG) is a major safety and security problem in open-world agents. The AEG is the divergence between what a principal intends to authorize and what an open-world agent…
Cooperative information shared among a multi-agent system (MAS) can be useful to agents to efficiently fulfill their missions. Relying on wrong information, however, can have severe consequences. While classical approaches only consider…
We introduce causal-temporal event graphs (CTEGs) as a formal model for fully resolved recursive agent execution records under single-parenthood causal semantics. We formalise direct event emissions and recursive subagent invocations as…
Recent work has shown that NLP tasks such as Relation Extraction (RE) can be recasted as Textual Entailment tasks using verbalizations, with strong performance in zero-shot and few-shot settings thanks to pre-trained entailment models. The…
Interleaving is an online evaluation approach for information retrieval systems that compares the effectiveness of ranking functions in interpreting the users' implicit feedback. Previous work such as Hofmann et al (2011) has evaluated the…
Security policy enforcement in contemporary agentic systems predominantly consists of embedding natural-language policies within an agent's system prompt and delegating compliance to the agent's reasoning. This approach admits no formal…
Entity detection and tracking (EDT) is the task of identifying textual mentions of real-world entities in documents, extending the named entity detection and coreference resolution task by considering mentions other than names (pronouns,…