Sho Tachibana

Research

Sho is a co-author on euler-99's substrate-integrated planning work. His contributions centre on the POMDP machinery that the cell uses to formalise long-horizon planning under partial observability — what gets encoded as state, what gets encoded as observation, and how the substrate exposes the right primitives.

He has been with alphabell since 2020 and is based in Kobe. He works closely with Catriona MacLeod on euler-99's research agenda and is on the cross-axis methodology review pool.

Background

Ph.D. computer science, Kyoto University, 2015.

Prior to alphabell: Kyoto; Hyperion Cognitive Lab; Praxis AI Studies.

Selected publications

• Apr 2025 · ab-agent-negotiat
  Negotiation Protocols Among Heterogeneous Agents: a benchmark and three baselines
  Roman Iliescu, Yvonne Akande, Lakshmi Ravi, Pascal Niedermeier
• Oct 2025 · ab-durable-agents
  Durable Agent Substrate v1: persistent state, learned tool affordances, and verifiable execution traces
  Mira Holloway, Dineth Karunaratne, Priya Anand, Cheung Wai-Lin
• Sep 2024 · ab-interpretabili
  Interpretability Cell Pairing: how every dual-use capability run gets a watchful sibling
  Karima Belkadi, Hester Vandekerckhove, Yuki Cho
• Sep 2025 · ab-scalable-overs
  Scalable Oversight for Multi-Step Agent Systems: a Debate-Plus-Trace Approach
  Ifeoma Nwosu-Howard, Hiroshi Tanigawa, Maral Lotfi, Ruth Wernicke
• Oct 2024 · ab-federated-comp
  A Federated Compute Scheduler for an Asynchronous Research Lab
  Pranav Iyer, Yusra Habibi, Akoss Vidor

Full publications index →

Recent talks

• POMDPs at substrate-scale, AAMAS 2024
• Substrate-integrated planning, ICAPS 2025