This episode explores Multi-Agent Transactive Memory, a paper asking whether many agents can dump their raw task trajectories into one shared, searchable repository and let other frozen models retrieve from it. That would improve success rates and cut step counts without any joint training or coordination. It builds up from retrieval-augmented generation and single-agent experience memory (Reflexion, Synapse, ExpeL) to the shared-pool idea, borrowing the name from Wegner's group-psychology notion of transactive memory. The discussion stresses that the analogy is loose: the system is closer to a Stack Overflow for agents than to a team, and the trajectories were never written to be read. It also covers the retrieval design, where the key is the task description plus the last five steps embedded with E5-Base and the stored value is the next five steps from a past run. The pool is seeded with public trajectories from models like GPT-4-Turbo, Claude 3.5 Sonnet, Qwen3-32B and GPT-OSS 20B, then grows as agents work. Listeners get a skeptical look at the ALFWorld and WebArena testbeds, including how small and templated they are, and at the missing private-versus-shared memory control that the paper's central claim needs.
Sources:
1. Multi-Agent Transactive Memory — To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz, 2026
http://arxiv.org/abs/2606.19911
2. The Transactive Memory System in Relationships / Cognitive Interdependence in Close Relationships (Transactive Memory: A Contemporary Analysis of the Group Mind) — Daniel M. Wegner, 1985/1987
https://scholar.google.com/scholar?q=The+Transactive+Memory+System+in+Relationships+%2F+Cognitive+Interdependence+in+Close+Relationships+%28Transactive+Memory%3A+A+Contemporary+Analysis+of+the+Group+Mind%29
3. Generative Agents: Interactive Simulacra of Human Behavior — Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein, 2023
https://scholar.google.com/scholar?q=Generative+Agents%3A+Interactive+Simulacra+of+Human+Behavior
4. Voyager: An Open-Ended Embodied Agent with Large Language Models — Guanzhi Wang, Yuqi Xie, Yunfan Jiang, et al. (Anandkumar, Fan), 2023
https://scholar.google.com/scholar?q=Voyager%3A+An+Open-Ended+Embodied+Agent+with+Large+Language+Models
5. Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control — Longtao Zheng, Rundong Wang, Xinrun Wang, Bo An, 2024 (ICLR)
https://scholar.google.com/scholar?q=Synapse%3A+Trajectory-as-Exemplar+Prompting+with+Memory+for+Computer+Control
6. Reflexion: Language Agents with Verbal Reinforcement Learning — Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao, 2023
https://scholar.google.com/scholar?q=Reflexion%3A+Language+Agents+with+Verbal+Reinforcement+Learning
7. Agent Workflow Memory — Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig, 2024
https://scholar.google.com/scholar?q=Agent+Workflow+Memory
8. ExpeL: LLM Agents Are Experiential Learners — Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, Gao Huang, 2024
https://scholar.google.com/scholar?q=ExpeL%3A+LLM+Agents+Are+Experiential+Learners
9. Retrieval-Enhanced Machine Learning — Hamed Zamani, Fernando Diaz, Mostafa Dehghani, Donald Metzler, Michael Bendersky, 2022
https://scholar.google.com/scholar?q=Retrieval-Enhanced+Machine+Learning
10. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks — Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Douwe Kiela, et al., 2020
https://scholar.google.com/scholar?q=Retrieval-Augmented+Generation+for+Knowledge-Intensive+NLP+Tasks
11. Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving — Xiangru Tang et al., 2025
https://scholar.google.com/scholar?q=Agent+KB%3A+Leveraging+Cross-Domain+Experience+for+Agentic+Problem+Solving
12. Memp: Exploring Agent Procedural Memory — Runnan Fang et al., 2025
https://scholar.google.com/scholar?q=Memp%3A+Exploring+Agent+Procedural+Memory
13. AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases — Zhaorun Chen, Zhen Xiang, Chaowei Xiao, Dawn Song, Bo Li, 2024
https://scholar.google.com/scholar?q=AgentPoison%3A+Red-teaming+LLM+Agents+via+Poisoning+Memory+or+Knowledge+Bases
14. PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models — Wei Zou, Runpeng Geng, Binghui Wang, Jinyuan Jia, 2025
https://scholar.google.com/scholar?q=PoisonedRAG%3A+Knowledge+Corruption+Attacks+to+Retrieval-Augmented+Generation+of+Large+Language+Models
15. Evaluating Retrieval Quality in Retrieval-Augmented Generation (eRAG) — Alireza Salemi, Hamed Zamani, 2024
https://scholar.google.com/scholar?q=Evaluating+Retrieval+Quality+in+Retrieval-Augmented+Generation+%28eRAG%29
16. Retrieval-Augmented Reinforcement Learning — Anirudh Goyal et al., 2022
https://scholar.google.com/scholar?q=Retrieval-Augmented+Reinforcement+Learning
17. Many-Shot In-Context Learning — Rishabh Agarwal et al., 2024
https://scholar.google.com/scholar?q=Many-Shot+In-Context+Learning
18. Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory — Mirac Suzgun, Mert Yuksekgonul, Federico Bianchi, Dan Jurafsky, James Zou, 2025
https://scholar.google.com/scholar?q=Dynamic+Cheatsheet%3A+Test-Time+Learning+with+Adaptive+Memory
