Today at 1:00pm, join Dan Garrette and Miloš Stanojević at the #EMNLP2026# Google booth (D5) for a live demo of @GoogleDeepMind SL2T, bringing ASL-to-English translation to Gboard and Live Transcribe on Pixel 11. Read the blog:

Don't miss our interactive demo analyzing 16,000+ NLP paper limitations. Join Piyawat Lertvittayakumjorn at the #EMNLP2026# Google booth (#D5#) today at 10:30am to see how research trends have shifted and look up how your own paper was coded. Read the paper:

Don't miss your chance to explore research career pathways and student programs at Google during @emnlpmeeting. Stop by the #EMNLP2026# Google booth (#D5#) today at 4:15pm for a live Recruiting Q&A with Sunipa Dev and Nima Kalantari to ask your questions and connect with our team.

How well do LLMs understand Southeast Asian languages? Today at 10:30am, join Shubham Mittal at the #EMNLP2026# Google booth (#D5#) for a live demo of DEEPSEA, a benchmark to evaluate LLMs across 12 Southeast Asian languages. Read the paper:

How can positive alignment anchor autonomous AI agents to core values rather than brittle rubrics? Join @GoogleDeepMind researcher Verena Rieser today at 9:00am for the @emnlpmeeting Industry Keynote, and visit the #EMNLP2026# Google booth (D5) afterward to connect with our team.

Red Hat researchers, in collaboration with Purdue, developed VEX-Bench—a benchmark for assessing large language models (LLMs) in software supply chain vulnerability triage. Traditional tools often generate up to 70% false alerts. Discover the findings: #EMNLP2026#

🎉 Excited to share that our paper "VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities” has been accepted to EMNLP 2026! This work is a collaboration between @PurdueCS and multiple teams from @RedHat (AI Engineering, Ecosystem Engineering, and Product Security). Software supply chains are an increasingly important security challenge. While tools can identify vulnerable dependencies, determining whether a vulnerability is actually exploitable in a downstream application often requires substantial cross-repository reasoning and security expertise. In this work, we introduce VEX-Bench, a benchmark for evaluating LLM agents on this problem: - 75 real-world vulnerability cases mined from GitHub - Expert-labeled across Python, Java, and Go - Evaluation of 9 models across 3 agent harnesses - Going beyond binary “exploitable / not exploitable” decisions to evaluate the reasoning behind exploitability Our results show that frontier LLM agents can perform well on binary vulnerability assessment, but fine-grained exploitability reasoning remains significantly more challenging. This points to an important direction for AI-assisted software security: it’s not enough for an agent to identify that something is vulnerable. We need to understand why it is exploitable, whether it actually matters in context, and how confidently we can trust the assessment. 🙌 Huge thanks to all the co-authors and collaborators who made this possible! @tian_yi_zhang, Jiahao Shi, Yifeng Di, Ilan Pinto, Edward Tsien, Hongjiao Zhang, Ronit Dey, Ilona Shishov, Gal Netanel, Zvi Grinberg, Vladimir Belousov, Bat-Zion Rotman 📄 Paper: #EMNLP2026# #AI# #LLM# #LLMAgents# #Cybersecurity# #SoftwareSupplyChain# #OpenSource# #PurdueCS# #RedHat#

An agent gets tricked into paying the wrong address. Should its wallet let it? At EMNLP 2026, @0xDamian0x demoed how BNB Agent Studio puts owner-set rules between an AI’s payment request and a signature, alongside our research with AWS co-authors. We tested a “confused deputy” attack: give an agent a legitimate job, then slip in an attacker’s recipient or amount. Across six models, the paper’s single-turn tests found: 🔸 Baseline agents executed forbidden money actions in up to 87% of scenarios. 🔸 With the same tools and prompt behind a wallet policy layer, models still attempted forbidden actions at similar rates. 🔸 The wallet layer signed zero of those actions in the test harness. The model can still get fooled. Its payment permissions stay fixed. BNB Agent Studio keeps private keys out of the model’s context. Code handles signing and pricing, enforcing the owner’s spending caps and approved recipients. The demo walked through six commands to: 🔸 Create an agent and its wallet 🔸 Set up model access and test locally 🔸 Deploy and register an onchain identity The agent can then replenish its own inference credits within owner-set limits. Separate live checks on BNB Smart Chain testnet validated payment guardrails, escrow funding, and owner-controlled suspension. Get the architecture, test results, and limitations in the whitepaper 👇

This might be the first open-source memory architecture to cover associative recall. The rest stop at similarity search. (T-Mem, EMNLP 2026) Most memory systems retrieve by similarity. T-Mem predicts when a memory will matter, before you ask. → write: memories ship with a trigger at store time, basically "when will this come up again?" → read: at query time, triggers pull in memories by situation, even with zero keyword overlap. → architecture layer. plugs into any LLM without fine-tuning or model changes. On LoCoMo-Plus (strips keyword overlap, tests pure associative recall), mainstream systems drop 28 to 50 points. T-Mem drops 5.45. paper: code: (MIT)