Xing Han Lu
@xhluca
Followers
2K
Following
6K
Media
214
Statuses
2K
Vibe agents @Mila_Quebec @McGill_NLP
The Wired
Joined December 2017
"Build the web for agents, not agents for the web". This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
9
54
194
RT @MassCaccia: π Our paper βπ»ππ€ π‘π πππππ πππ’π πΏπΏπ πππ π΄ππππ‘: π΄ ππ‘ππ‘ππ π‘ππππ π·ππππππ ππ β got an π¨π«ππ₯ at next weekβs πππ π πͺπΌπΏπΈππ΅πΌπ½ πΌπ» ππΌπΊπ½πππ²πΏβ¦.
0
26
0
AgentRewardBench will be presented at @COLM_conf 2025 in Montreal! See you soon and ping me if you want to meet up!.
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories . We are releasing the first benchmark to evaluate how well automatic evaluators, such as LLM judges, can evaluate web agent trajectories. We find that rule-based evals underreport success rates, and
2
7
31
RT @yoavartzi: @COLM_conf decisions are out, and so are we . The strength of submissions this year amazed us! Many many hard decisions π©β¦.
0
8
0
RT @kyutai_labs: Kyutai TTS and Unmute are now open source!.The text-to-speech is natural, customizable, and fast: it can serve 32 users wiβ¦.
0
172
0
RT @BlackboxNLP: π¨ Excited to announce two invited speakers at #BlackboxNLP 2025!. Join us to hear from two leading voices in interpretabilβ¦.
0
10
0
RT @vernadankers: I miss Edinburgh and its wonderful people already!! Thanks to @tallinzen and @PontiEdoardo for inspiring discussions duriβ¦.
0
8
0
RT @xhluca: @webagentlab Would appreciate if the authors could avoid copying the title of our paper, which was release more than 2 months aβ¦.
0
1
0
RT @benno_krojer: Started a new podcast with @tvergarabrowne !. Behind the Research of AI: .We look behind the scenes, beyond the polishedβ¦.
0
13
0
RT @cesare_spinoso: A blizzard is raging in Montreal when your friend says βWow, the weather is amazing!β Humans easily interpret irony, whβ¦.
0
11
0
RT @benno_krojer: The video is online now!. 3min speed science talk on "From a soup of raw pixels to abstract meaning". .
0
6
0
RT @ReviewAcl: Dear ACL community, We are seeking emergency reviewers for the May cycle. Please indicate your availability (ASAP) if you caβ¦.
0
16
0
Very important benchmark about the safety of computer use agents. Validates our findings in SafeArena ( that agents can complete harmful tasks - now with reasoning models and on OS tasks. We need safer digital agents asap before more productization.
π¨Excited to release OS-Harm! π¨. The safety of computer use agents has been largely overlooked. We created a new safety benchmark based on OSWorld for measuring 3 broad categories of harm:.1. deliberate user misuse,.2. prompt injections,.3. model misbehavior.
0
7
25
RT @maksym_andr: π¨Excited to release OS-Harm! π¨. The safety of computer use agents has been largely overlooked. We created a new safety bβ¦.
0
27
0
RT @hanseok_oh: Life update: I am joining as visiting researcher at @Mila_Quebec π¨π¦. I returned to academia to deepen my understanding of hβ¦.
0
4
0