LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards. We study this problem in autonomous investing, where every action is irreversible and based on untrusted Web content. We present Steward, a multi-agent...
Yebo Feng, Jingyang Dai, Liangrui Pan et al.· 0 citations
Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction burden. Reducing this burden requires agents to remember how users want to be assisted. However, existing memory benchmar...
Jia-Lin Li, Zhen-Hao Chen, Han-Jun Luo et al.· 0 citations
Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic effect creates a critical risk for agents operating over confidential data. We quantify its realization with 30 synthetic cybersecurity, medical, and military examples, yieldin...
Daniel Ruiz, Luca Luceri, Emilio Ferrara· 0 citations
Decision models return normalized probability distributions over candidate choices, which downstream applications can use to select among choices. Although their providers emphasize the reliability of these probabilities, calibration on tasks with a single correct choice does not establish their reliability when multip...
Rushab Munot· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces an approach to apply Constitutional AI training with domain-specific mental health principles for safe, domain-adapted CAI systems in computational mental health applications.
Chenhan Lyu, Yu-Tong Song, Pengfei Zhang et al.· International Conference on...· 7 citations
Many recent open-weight language models use n-gram embedding tables to improve performance. These tables store learned representations of short token sequences, such as pairs or triples of consecutive tokens, which the model retrieves during processing. However, they can require substantial memory: DeepSeek-V4.1-Flash,...
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Y...
Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias et al.· 0 citations
Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show t...
Shi-Hui Li, Mette Friis Andersen, Martha Lewis· Proceedings of the 9th Black...· 0 citations
Multilingual language models can give different identity judgments when the same people's names are written in different scripts. We study this effect using 601 audited identity pairs with attested Devanagari and Latin forms, holding the question and relation fixed. Qwen2.5-7B's same-person accuracy falls from 35.1% in...
Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity Knowledge Graph (MEKG) encoding method-level follow-on, competition, and shared-resource relations. The graph supports core-...
Yi-Fan Yuan, Yan-Cheng Zhu, Zuo-Yu Zhang et al.· Conference on Empirical Meth...· 0 citations
Large language models can repeat an instruction while failing to keep obeying it. We study this recall-compliance dissociation in long-horizon dialogue and define State Integrity Collapse: a model preserves a stated constraint in memory but stops applying it to later turns. We introduce StateTrack-Bench, a controlled s...
Yan-Cheng Zhu, Yi-Fan Yuan· Proceedings of the 2026 Conf...· 0 citations
CoWriter is introduced, a proactive agentic scheme that adapts expert human (co-)authoring methodologies from cognitive science to flexibly steer the entire writing workflow while actively encouraging the user to engage.
Shmuel Amar, Benjamin Lieber, Ori Shapira et al.· 0 citations
