SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
arXiv preprint arXiv:2501.15228 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
fields
cs.AI 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
OASES co-trains search policies and evaluators to generate outcome-aligned process rewards, outperforming standard RL baselines on five multi-hop QA benchmarks.
citing papers explorer
-
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
OASES co-trains search policies and evaluators to generate outcome-aligned process rewards, outperforming standard RL baselines on five multi-hop QA benchmarks.