Sage-A1.5 is a 35B MoE model for long-horizon agents
It adds subagent delegation, progress checks with strategy revision, and exploratory research beyond predefined questions.
Stories per day · 30 days
2 RSS
8 stories, newest first · one card per story
Stories tagged #sage
SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis
SAGE uses MeSH anchors so small local models can synthesize grounded medical QA training data.
Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair
SAGE traces where coding agents first abandon security while producing patches that still pass functional tests.
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
SAGE flags clean-label training poisons from a handful of expert-verified examples using similarity-weighted prediction.
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
SAGE discovers unlabeled visual subtypes in a frozen latent and conditions a diffusion transformer to generate them.
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
SEAD shows a state-aware defense cutting tool-agent attack success from 48 percent to 4 percent.
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
SAGE uses structural guidance to cut long-horizon reasoning biases, with up to an 8-fold gain.
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
SAGE uses algebraic and hyperbolic guidance to reduce long-horizon LLM reasoning biases, with up to an 8-fold gain.