Category
3,445 papers
Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured R...
This work proposes a distributed UAV-agent architecture that enables continuous local SLM control through an event-driven reason-act-observe lifecycle and approximately halves inference-token consumption, reduces transmitted data, and achieves lower survivor-count error.
Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents to work together on these tasks. Recent methods train LLMs to construct better workflows from execution outcomes, but they optimize only th...
Directional verification mitigates the transfer of errors from teacher-generated answers to students by providing more accurate training targets, and introduces directional label distillation, in which frozen teachers score candidate answers in that known direction and the best-scoring candidate becomes the student's t...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on the dense model's outputs needs to know how many of its decisions changed. We show that total variation, not KL, answers this directly. Across 802 compressed and perturbed...
An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability to generalize as network scale changes. Hierarchical RL reduces decision complexity by separating strategic targeting from tactical execution, but it does not eliminate th...
As Large Language Models (LLMs) increasingly serve as foundational reasoning engines, their tendency to hallucinate remains a critical vulnerability. While recent internal state probes offer a promising alternative to slow external retrieval systems, they largely reduce hallucination detection to a token-wise binary cl...
Natural language descriptions can provide rich semantic representations of audio-visual urban scenes, yet datasets that jointly describe both auditory and visual information remain limited. In this paper, we introduce AVSD-Scenes, a paired audio-visual scene description dataset for urban environments. The dataset conta...
An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of solution coverage. Although this trade-off has been observed in math and coding tasks, it need not extend to...
This work introduces OpenMTB-Audit, an open-source benchmark of 500 synthetic non-small cell lung cancer cases spanning five adversarial error categories and four safety labels, and developed MTB-AuditAgent, a deterministic seven-module framework separating evidence verification, missing-information detection, safety c...
This work forms SLM-LLM collaboration as an information acquisition problem, under an API budget constraint, and develops a three-stage RLVR framework that learns whether to call the advisor, how to formulate useful queries, and how to integrate the collaboration into the reasoning process by jointly refining advisor i...
Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement policies are tested in...
A Blog post by IBM Granite on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
