
Join us at the Computer Use Agents workshop at ICML2025. Happening now in West Meeting Room 211, Vancouver Convention Centre! We have a day packed with fantastic invited and contributed talks, posters, and discussions!

Workshop on Computer Use Agents @ ICML 2025 Workshop, Vancouver, Canada

Join us at the Computer Use Agents workshop at ICML2025. Happening now in West Meeting Room 211, Vancouver Convention Centre! We have a day packed with fantastic invited and contributed talks, posters, and discussions!

There's less than 1 day left to send your work to the ICML 2025 Workshop on Computer Use Agents, deadline is May 20, 11:59pm AoE! ✅ Concurrent submissions (e.g., NeurIPS) allowed ✅ Works-in-progress encouraged Don’t miss it! 🔗 icml-computeruseagents.com/c… #ICML2025 #CUA #LLMAgents #Agents #ComputerUse

🧬 HippoRAG: LLM Memory Inspired by the Brain w/ @bernaaaljg et al Yu’s latest work brings neuroscience full circle. HippoRAG, inspired by the hippocampal indexing theory, gives LLMs a robust long-term memory mechanism, essential for persistent, intelligent behavior. #NeuroAI #MemoryInLLMs Don't miss Yu Su at the Computer Use Agents Workshop @ ICML 2025!

Mind2Web (NeurIPS 2023 Spotlight) w/ Xiang Deng et al A dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website 🔗osu-nlp-group.github.io/Mind…

TravelPlanner (ICML 2024 Spotlight) w/ @jianxie_ , @DrogoKhal4 et al A real-world benchmark where language agents tackle complex planning tasks like booking trips—multi-step, goal-oriented, and web-based. #LanguageAgents #WebAutomation 🔗 arxiv.org/abs/2402.01622

Mind2Web (NeurIPS 2023 Spotlight) w/ Xiang Deng et al A dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website 🔗osu-nlp-group.github.io/Mind…

⏳ Less than 1 day left to submit! 🔦 Speaker Spotlight Time! We’re thrilled to welcome Yu Su (@ysu_nlp), Distinguished Assistant Professor at The Ohio State University, as an invited speaker at the ICML 2025 Workshop on Computer Use Agents! His work bridges LLM agents, memory, and planning, driving some of the most cited advances in the field. #ICML2025 #LLMAgents #ComputerUseAgents #NLProc

There's now less than 2 days left to submit your work for the paper track - May 20, 2025 11:59pm AoE! We accept concurrent submissions under review elsewhere (e.g. NeurIPS!) and encourage authors to submit works-in-progress. 🔗icml-computeruseagents.com/c…

🚨Less than 2 days left to submit your work, check below! Make sure to follow the page and check out our individual speaker spotlights for the #ICML2025 Workshop on Computer Use Agents which will, amongst demo tracks and poster sessions, feature talks and a panel by our amazing speakers: @sercanarik @alexandredrouin @nouhadziri @gneubig @rsalakhu @ysu_nlp @alsuhr @qingyun_wu @zywu_hku @hllo_wrld #ICML2025 #ComputerUse #Agents #WCUA

Submit your papers and demos for the Workshop on Computer Use Agents here: ➡️icml-computeruseagents.com/c… We're excited to see your contributions! #ICML2025 #WCUA #CUA #AIagents

📢 Deadline Extended for the Workshop on Computer Use Agents at #ICML2025! 📢 #NeurIPS2025 deadline passed? Take a breath & send your amazing work our way! We've extended the paper submission deadline to May 20, 2025, at 11:59 pm AoE. More time to polish those papers on AI agents for real-world computer tasks! Submission link in the next tweet! 👇 #WCUA #CUA #AI #ML #ComputerUseAgents #Agents #ICML2025

Nouha’s insights will be great to hear contextualised for the post-training, alignment and responsible deployment of autonomous computer use agents. Don't miss her insights at the ICML 2025 Workshop on Computer Use Agents! 🔗 Workshop Details: icml-computeruseagents.com/ #ICML2025 #AI #LLMAgents #ComputerUseAgents

📄 RewardBench: Evaluating Reward Models w/ @natolambert, @valentina__py, et al. RewardBench is a benchmark designed to evaluate the capabilities and safety of reward models (including those trained with Direct Preference Optimization, DPO). The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety, to benchmark how reward models perform on challenging, structured and out-of-distribution queries. The authors present many findings on propensity for refusals, reasoning limitations, and instruction following shortcomings of various reward models towards a better understanding of the RLHF process. 🔗 arxiv.org/abs/2403.13787v2

📄 Faith and Fate:Limits of Transformers on Compositionality w/ @GXiming, @melaniesclar, et al. Under what conditions do Transformers succeed, fail, and why? What types of errors do they make? Can Transformers uncover implicit problem-solving rules or be taught to follow reasoning paths? This work provides novel insights and a nuanced understanding of why and when Transformers succeed or struggle in compositional problems requiring strict multi-hop reasoning to derive correct solutions. To do this it focuses on three tasks: multiplication, logic grid puzzles, and a classic dynamic programming problem. 🔗 arxiv.org/abs/2305.18654

📄 WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models w/ @liweijianglw, @kavel_r, et al. "WildTeaming" is an automatic red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics, and then composes selections of multiple mined tactics for systematic exploration of novel and even more challenging jailbreaks. WildTeaming intends to address two challenges: (1) 🔍 Broadly identifying jailbroken behaviors of LLMs. (2) 🛠️ Creating a publicly open, large-scale safety training resource for systematic defense (WildJailbreak). 🔗 arxiv.org/abs/2406.18510

🔦 Speaker Spotlight: Nouha Dziri (@nouhadziri) We are delighted to have and showcase Nouha Dziri as our invited speaker at the ICML 2025 Workshop on Computer Use Agents! Nouha is a research scientist at the Allen Institute for AI (Ai2) who’s focused on researching the topics of post-training, safety and alignment of LLMs, and the limits of Transformers. #ICML2025 #ComputerUseAgents #LLMAgents #AI