While medical multimodal large language models (Med-MLLMs) advance medical visual question answering (VQA), existing clinical workflow-inspired multi-agent frameworks suffer from interaction patterns and excessive computational overhead caused by redundant communication topologies. In this paper, we propose MedPrune, a...
Jiuheng Wan, Runze Li, Chen Chen et al.· 0 citations
The introduced Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action, unifies a persistent candidate workspace, flexible primitive composition, and selective evidence presentation.
Jia-Ming Qian, Hui-Yan Yang, Man-Di Liu et al.· 0 citations
Experiments demonstrate that a single recovered reward generalizes across prompts and diverse models to reveal a fundamental alignment vulnerability, enabling ReSA to significantly outperform existing attacks in effectiveness and transferability.
Jia-Ming Qian, Peng-Yang Zhou, Jia-He Xu et al.· 0 citations
Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right entities and properties and chains their relations. Language models offer a natural-language alternative but answer largely from memory, which is least reliable for less promi...
Mohamed Chenene, C. Rosas Hinostroza, A. Stasenko et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Reinforcement learning has greatly advanced the capabilities of large language models, but its memory demands remain a barrier to broader adoption. We introduce LoGRA, an approach to RL post-training that reduces memory by retaining useful learning signals in low-rank gradient sketches. These compact representations su...
Shao-Kun Zhang, Yi-Fan Zhang, Jian Hu et al.· 0 citations
World models must predict how an environment evolves under sequences of actions, enabling agents to compare possible futures and reason about counterfactual actions before acting. Long-horizon prediction is commonly obtained by recursively applying a one-step transition model, but intermediate errors can compound over...
Fang-Xin Wang, Xiang Gao, Yu-Guang Yao et al.· 0 citations
This paper compares JEV with LLMs and human coders from published research, and with a current mid-tier commercial LLM and an open-weight alternative, and finds that JEV matches, or comes close to, the capabilities of both LLMs in a variety of tasks.
Automatically extracted narrative networks -- graphs with entities as nodes and their relations as edges -- have proven useful for revealing central narrative structures through salient entities and their connections (Tangherlini et al. 2020; Labatut and Bost 2019). But a narrative is more than those central structures...
Large language model (LLM)-based agents can exhibit deceptive behavior during task execution, including hiding failures, fabricating results, or falsely signaling task completion. Existing monitoring approaches mainly detect deception after it appears in observable actions or outputs. In this paper, we investigate whet...
Xin-Ling Li, Da-Di Guo, Qing-Yu Liu et al.· 0 citations
This work introduces a Hierarchical Dirichlet Process Gaussian Mixture Model over behavior embeddings, which shares components across domains while allowing domain-specific mixing weights, and uses the posterior predictive to retrieve relevant behaviors for a query, and shows that the Bayesian Cheatsheet is an adaptive...
Keshav Ramji, Tahira Naseem, R. Astudillo· 0 citations
As AI agents increasingly tackle complex repository-level coding tasks, distributing work across multiple agents is a natural way to scale beyond the capabilities of a single agent. To coordinate their interdependent work, these agents share findings and agree on interfaces between modules. However, exchanged informati...
Jia-Qi Xue, Yan-Jun Wang, Xiangci Li et al.· 0 citations
This work proposes Behavior-Preserving KV Cache Compression, a training-free framework that scores candidate evictions by estimating the compressed-cache logits induced by their removal and evaluating the resulting KL to the full-cache next-token distribution using pre-eviction forward statistics.
Doo Hwan Hwang, Junyoung Jang, Jun-Ho Na et al.· Proceedings of the 2026 Conf...· 1 citation
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
