Natural language understanding / machine translation / book reading
Joined December 2011
- Tweets 869
- Following 262
- Followers 237
- Likes 409
60 Photos and videos
Apr 2
I have been using this for a full month now.
Mar 30
Introducing OpenAgents Workspace.
One workspace where all your AI agents work together, shared chat, shared files, shared browsers.
Connect OpenClaw, Claude Code, Codex and more. Watch them collaborate, and work while you sleep.
Open source on GitHub.
Please give us a star:
github.com/openagents-org/op…
#OpenSource #AIAgents #MultiAgent
1
110
Raphael Shu retweeted
Mar 30
Introducing OpenAgents Workspace.
One workspace where all your AI agents work together, shared chat, shared files, shared browsers.
Connect OpenClaw, Claude Code, Codex and more. Watch them collaborate, and work while you sleep.
Open source on GitHub.
Please give us a star:
github.com/openagents-org/op…
#OpenSource #AIAgents #MultiAgent
114
126
908
359,662
Raphael Shu retweeted
Apr 2
My agent just shipped a feature, and another announced it on X and LinkedIn.
I didn't write a word.
OpenAgents Workspace automates the full loop.
One workspace. Two agents. See how coding and marketing agents collaborate with each other.
Try it→ github.com/openagents-org/op…
#AIAgents #OpenSource #MultiAgent
4
1
6
1,050
19 Nov 2025
Is the 15-year MARL Era Over? My Take on the Future of Multi-Agent with LLMs
I just delivered a 30-minute talk in Chinese, unpacking my key thoughts on the future of Multi-Agent systems.
youtu.be/qM-MLgAqZKE?si=5Ubj… via @YouTube
1
124
Raphael Shu retweeted
9 Oct 2025
Introducing OpenAgents — the open-source framework for building AI Agent Networks.
From isolated bots ➝ collaborative communities of countless numbers of agents that work, learn & grow together.
The future is an internet of agents. Star us on Github for OpenAgents Day 1 badge.
31
16
69
275,256
3 Oct 2025
Call For Paper (Deadline approaching on October 31): AAAI 2026 Bridge Program on Advancing LLM-Based Multi-Agent Collaboration
📷 Website: multiagents.org
📷 Don’t miss your chance to share your work with a global community shaping the future of multi-agent AI.
4
1
3
1,959
3 Oct 2025
Workshop Website: multiagents.org
Co-organizers: Alborz Geramifard(LinkedIn) @AlborzGr, Alex Marin (Thomson Reuters), Yi Zhang (AWS), Tao Yu @taoyds (HKU), Weiyan S. @shi_weiyan (Northeastern), Yusen Zhang @YusenZhangNLP (Columbia)
338
3 Oct 2025
Key Dates
- Submission Deadline: October 31, 2025
- Acceptance Notification: November 14, 2025
- Workshop Date: January 20, 2026
74
3 Oct 2025
We invite submissions on topics below (but not limited to):- Interoperability & coordination across multiple agents
- Knowledge sharing & memory in multi-agent systems
- Scalability, robustness & governance
- Applications of LLM-based multi-agent systems
- Evaluation & benchmarks
75
3 Oct 2025
Following the success of our 2025 workshop with 180 participants, we are excited to announce WMAC 2026, co-located with AAAI!
Join us for a full-day bridge program on January 20, 2026 in Singapore, where we explore how LLMs can power the next generation of multi-agent systems.
158
11 Aug 2025
MemU, a agentic memory system achieving 92%, new state-of-the-art score in Locomo benchmark. memu.pro/
1
147
Raphael Shu retweeted
4 Mar 2025
Just attended Multi-Agent Workshop at AAAI 2025 and it's hands down the best workshop I've been to at AAAI! It was buzzing and truly inspiring.
Huge shoutout to the organizers (@shi_weiyan @raphaelshu) for putting together such an unforgettable experience! #AAAI2025
4
26
3,432
Raphael Shu retweeted
17 Apr 2021
Happy to share our new #BLEURT-based reward optimization using a ranking-based contrastive margin loss for #NMT. We reconfirm the limitation of BLEU from our reward optimization results and human evaluation.
Congrats to
@raphaelshu, Kangmin Yoo.
arxiv: arxiv.org/abs/2104.07541
1
5
26
14 Dec 2020
Oh nice!
The authentication server seems to be down, so if you want to watch youtube, you can watch it in privacy mode.
Raphael Shu retweeted
16 Sep 2020
Summary: refining in the continuous space works for discrete output also! 😃
accepted to EMNLP 2020 (n/n)
3
12
Raphael Shu retweeted
16 Sep 2020
New work: "Iterative Refinement in the Continuous Space
for Non-Autoregressive Neural Machine Translation" w/ @raphaelshu @kchonyc
arxiv.org/pdf/2009.07177.pdf
We propose an inference procedure for non-autoregressive NMT that refines translations *purely in the continuous space.*
1
20
121