Category
19,710 papers
HyScale, a long-context training system for learned sparse attention, introduces HyTopK and selection replay, and speeds up GLM-5.1 training on 1M-token sequences by 2.07$\times$ over Megatron-LM on 512 H20 GPUs.
TTME is introduced, a plug-and-play test-time adaptation method that continually updates the external memory by distilling the experience to guide subsequent discovery without updating model weights, and established as an effective and computationally efficient alternative to TTT in the evaluated discovery settings.
This work asks whether model safety is preserved when an LLM is integrated in an AI-for-Science agent harness, and evaluates five agent harnesses on 50 harmful chemistry requests to show that the safety behavior of the base LLM is not durable once a harness is introduced.
The growing population of orbital debris has intensified interest in active debris removal and on-orbit servicing, for which dual-arm space manipulators offer improved grasping stability and load distribution relative to single-arm systems. However, coordinating two manipulators under inter-arm collision avoidance, ori...
Reach audiences
Advertise in front of researchers, engineers, and readers.
RSI-Opt is introduced, a plug-and-play Recursive Self-Improvement Optimizer Agents which evolves the knowledge that guides this process: a prompt, a playbook of procedures, a library of tested optimizer code, and a decision cadence.
BARC-Bench is introduced, a collection of 110 tasks across nine simulated workspace environments where benign requests leave openings for unsafe actions, and four frontier model configurations are evaluated, highlighting an asymmetric operational risk.
A boundary condition for text-derived multimodal enrichment is suggested: when the relevant task constraints are already available in the textual instruction, synthetic multimodal augmentation may not provide measurable benefit over structured reasoning on the same text.
LLM agents are increasingly deployed in collaborative settings where they pursue separate tasks while sharing resources and operating under review or oversight processes. Such settings create safety risks not only when agents are malicious, but also when they are simply trying to help. Prior work has largely studied ad...
This work presents an offline evaluation harness for a production conversational agent that stays reproducible despite the live data it operates on changing, and that can be regenerated on demand once it goes stale.
This work introduces a repeated, multi-party, multi-issue negotiation framework in which recurring agents participate in a sequence of negotiation games while one participant covertly attempts to prevent agreement.
An automated red-teaming framework is introduced that formalizes multi-turn jailbreaking as a finite-horizon Markov Decision Process (MDP) without relying on predefined risk taxonomy, providing a scalable and principled framework for multi-turn red-teaming and safety evaluation.
It is found that student-induced histories paired with teacher-generated action prefixes generally provide the strongest standalone training signal, whereas following the student at both levels generally performs worst, and fully on-policy data becomes beneficial when incorporated into a mixture with other configuratio...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
