Found 20 document(s)
Page 1 of 2
-
Language models behind coding agents are post-trained with outcome rewards, and recent methods concentrate credit on the turns that decide the outcome. We find that defensive actions beyond what a task requires escape bo...
-
Robot deployment generates experience that can support policy improvement, but continued reliance on expert corrective actions makes learning difficult to scale across growing fleets. We propose learning from fleet exper...
-
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not onl...
-
Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interactive extended reality (XR) applications remains an o...
-
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and efficient pre-training, co...
-
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selecti...
-
Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery tasks. However, TTT intro...
-
LLM-powered agents increasingly rely on third-party skills that combine natural-language instructions with executable code, creating supply-chain risks that may span both artifacts. Existing skill scanners often rely on ...
-
Multi-Head Latent Attention (MLA) has been adopted by recent frontier large language models. Instead of per-head keys and values, MLA caches a compressed KV latent that is up-projected into keys and values at decode time...
-
Few-step distillation for autoregressive (AR) video generation commonly first initializes an AR student and then refines it with distribution matching distillation (DMD). This refinement process faces two challenges. Fir...
-
ClinVerse: A Realistic Multi-Agent Diagnostic Environment for Training and Evaluating Medical AgentsDisease diagnosis is a key application of large language model (LLM) agents in healthcare. However, existing medical agents are primarily trained and evaluated with static question-answering data, providing limited oppor...
-
This open access book provides a detailed exploration of how dynamic disturbances, such as those caused by blasting or seismic activity, affect the damage and failure mechanisms of rocks. When excavation is carried out u...