Yukyeong Lee, Yumin Choi, Jinheon Baek, Sung Ju Hwang (KAIST AI) · Evidence-Linked Memory
WikiTrace: Evidence-Linked Memory for LLM Agents
WikiTrace is an evidence-linked memory system for LLM agents that stores each lesson as an insight linked to a summary and to its raw trajectory. Agents can descend these links with terminal tools to check or correct a lesson before acting. The authors report that it outperforms existing memory approaches and a baseline given the same insights alone on five agentic benchmarks, while reducing memory-induced degradation. Code is available on GitHub.
Open the source ↗Similar Research & Safety releases
- Weighted State Souping for Efficient Long-Context Retrieval
Apple Machine Learning Research (with Harvard University co-authors) · Weighted SSM Souping · Week 47, 2026
- Evaluating the Evaluators: Investigating LLM Judges for Personalized Writing Style Assessment
Apple Machine Learning Research (Natalie Mackraz, Andrew Silva, Aini Putkonen, Brihi Joshi, Joelle Alcaidinho, Arnav Arora, Barry-John Theobald, Katherine Metcalf) · LLM Judge Study · Week 47, 2026
- Tree-Ising: Repairing Language Models with Bit-Level Ising Edits
Hadi Salloum, Ammar Ali · Weight-Space LLM Repair · Week 47, 2026
- On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models
Apple Machine Learning Research (with Harvard University authors) · Gating in SSMs · Week 47, 2026
- Coachable health age and SensorWM
Google Research · Wearable health world model · Week 47, 2026
- TOME-Math: Scaling Mathematical Proof Supervision from Structured Textbooks
Intern Large Models (Youqing Fang et al.) · Math Proof Dataset · Week 47, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.