This week we will be presenting our work at #ACL2025. StateAct is like ReAct but better ;) Shunyu Yao We discovered that if you enhance the Agent with “self-prompting” and “state-tracking” you get greater long-range reasoning performance for free. arxiv.org/abs/2410.02810

Decision day energy: ☕️📬🖱️👀 Cheering on #EMNLP2025 authors and shouting out the organisers & reviewers who made it happen🚀🙏

Reminding myself when doing my ARR reviews this week to stay humble and stay kind. Absolutely loved this post and the advice. x.com/ManlingLi_/sta…

We have released #AgentCoMa, an agentic reasoning benchmark where each task requires a mix of commonsense and math to be solved 🧐 LLM agents performing real-world tasks should be able to combine these different types of reasoning, but are they fit for the job? 🤔 🧵⬇️

💯

Come work with us! Yonatan Belinkov is an amazing advisor, feel free to reach out if you have any questions about the lab!

It's amazing to be part of Sheffield NLP! It's such a huge NLP group, the biggest in England for sure :) If you don't already, follow Sheffield NLP to hear about our cool work 😍

Welcome Joe Stacey as our new postdoc! Great to hear your seminar today about improving the robustness of NLI models, and creating interpretable models using atomic inference. If you're interested in model robustness or creating interpretable models, check out Joe's work!

x.com/nikaletras/sta… Was just reading Nikos Aletras list of tips for writing a good *ACL paper, and was wondering if anyone had random tips that really work for them? If so, would love to hear them 🙂

I really love how polite everyone can be on the tube in London. It’s like “sorry can I squeeze through”, “sorry”, “thank you” Love the UK 😍😍

Sometimes research is so unbelievably exciting. Can't believe it's like an actual job and you get paid to do this. Being a postdoc is really great :)

So excited for #EMNLP2025 ! We have some exciting papers at the conference, so come and check out our work & say hi to the team :) x.com/SheffieldNLP/s…

Just arrived at #EMNLP2025 in Suzhou. Looking forward to meeting with everyone! Will be giving an oral presentation of our paper No Need For Explanations: LLMs Can Implicitly Learn from Mistakes In Context this Friday 7th November at 11.30 am in Hall A108 🎤