Tired of comparing LLMs across proprietary, apples-to-oranges agent scaffolds for SWE tasks? 📢📢 Introducing a unified leaderboard: all models are evaluated using live-SWE-agent, the first live software agent that self-evolves on the fly. 🔥 Opus 4.5 + live-SWE-agent hits

🤯🤯🤯 Gemini 3 Pro + Live-SWE-agent hits 77.4% on SWE-bench Verified, beating ALL existing models, including Claude 4.5!! 🤖 Live-SWE-agent is the first live software agent that autonomously self-evolves on the fly — and it even outperforms the manually engineered scaffold

Work with Xudong! Absolutely brilliant researcher and great person. Xudong will be an outstanding advisor!

⏰ 3 days left to submit to #LLM4Code2026 (co-located with @ICSEconf 2026)! Pls submit by Oct 31: https://t.co/TdfOMMXw7V We hope to create a platform for researchers/practitioners to discuss the latest in LLMs/Agents for Code across diverse fields: SE, PL, ML, and beyond.

Excited to announce the 3rd LLM4Code workshop collocated with ICSE26 @ICSEconf in Rio, Brazil🇧🇷! 🌟Website: https://t.co/vD4NQSmKcl 🌟Deadline: Oct 31 🌟8-page research paper/4-page position paper (including references) @LingmingZhang @yiling__LOU @devanbu @Kexin_Pei @llm4code

🌟🌟🌟We are thrilled to announce AIware 2025 keynote speakers! For more details, please visit AIware website: https://t.co/2n1Lq0TFc3 📅Early bird registration deadline: Oct 15th Registration link: https://t.co/ujbmRL5ZAd

Thrilled to announce that I'll be joining UIUC CS @siebelschool as an Assistant Professor in Spring 2026! 📢 I’m looking for Fall '26 PhD students who are interested in the intersection of Software Engineering and AI, especially in LLM4Code and Code Agents. Please drop me an

📢 Excited to announce #LLM4Code 2026 (co-located with @ICSEconf 2026)! 🎯 Pls submit by Oct 20: https://t.co/TdfOMMXw7V We hope to create a platform for researchers/practitioners to discuss the latest in LLMs/Agents for Code across diverse fields: SE, PL, ML, and beyond.

🚨 10 days left to submit to AIware 2025! 🏆🏆The best full-length papers will be recognized with an ACM SIGSOFT Distinguished Paper Awards

If you are still at #icse25, join us this Saturday for the @llm4code workshop. We have two wonderful keynote talks by Federico Cassano @ellev3n11 from @cursor_ai and Ofir Press @OfirPress from @Princeton on building next-generation software engineering models/agents!

🚀 Announcing the 1st International Workshop on Language Models and Programming Languages (LMPL) at SPLASH 2025! Join us to explore the intersection of generative AI & programming languages. See you in Singapore! 🇸🇬 🔗 https://t.co/kIT3MyHU29📝 #LMPL2025 #ProgrammingLanguages

Don’t forget to register our workshop/conference at https://t.co/D7fyzOTMXi! Early registration is due soon (Feb 18)!

o1-level w/ open access! Excited to see Agentless being used by both DeepSeek & OpenAI to evaluate their models on SWE-bench! Agentless😺, a simplistic but powerful AI software engineer, has been just accepted by @FSEconf: 🧑‍💻 https://t.co/AKyiZhmi7B 📝 https://t.co/Oc4QCaQult

🎉Exciting news! AIware is BACK this year and will take place Nov 20–21, 2025, co-located with @ASE_conf in beautiful Seoul, South Korea! 🌸 Don't miss the opportunity to contribute — stay tuned for updates on our website https://t.co/4wjDNh78sc! 🤖

Thrilled to share that my PhD student, Nan Jiang, is on the academic job market! Nan, working on SE+AI, is the ideal kind of PhD student one can ask for. I’m confident he will be a great professor! https://t.co/d74mrCh5ZR Nan has papers in ICSE, FSE, NeurIPS, AAAI, and more.

🔮 ACM TOSEM Perspective Paper on Software Security in 2030 (Invited). 📝 https://t.co/giCT87yiWz Collab w/ Eric Bodden, Tevfik Bultan, Cristian Cadar, Liu Yang, and Giuseppe Scanniello // @ACM_TOSEM @c_cadar @Sun450gmailcom1 @g_scanniello

🚨Just 2 days left to submit to @llm4code 2025, co-located with ICSE🚀 🎯We welcome papers on various topics, including but not limited to: 🌟LLMs/agents for coding tasks 🌟Code model design/optimization 🌟Datasets/evaluation 🔗Submit now: https://t.co/tSp98rIIJd #LLM4Code

🚨Just one week left to submit to #LLM4Code25!(Co-located with ICSE) We also offer a non-archival option, if selected, your camera-ready will be shared only on our workshop website, not the proceedings (no need to worry about double submission if you have other submission plan)

All LLMs including GPT-4o achieve < 30% pass@1 on real-world code completion: Check out 🐟REPOCOD, a real-world code generation benchmark: - Repository-level context - Whole function generation - Validation with test cases - 980 instances from 11 Python projects #LLM #LLM4Code

😱LLMs show significant biases during role-playing🔥 🚨Check out our recent paper “Benchmarking Bias in Large Language Models during Role-Playing,” where we uncover biases in GPT-4o-mini, DeepSeek, Qwen, Llama, and Mistral. 📑 https://t.co/3FuVgvpvLQ 📊 https://t.co/j1B3cBVTQM