So excited to share that I received the SIGIR Early Career Research Award! 🥹 I still remember attending my first SIGIR, watching someone receive this award, and thinking, “There’s no way that could ever be me.” And now, here I am!😵 This truly means so much to me. Thank you to the @ACMSIGIR community for recognizing my contributions. #SIGIR2026 P.S. Get yourself a PhD supervisor who matches your award-celebration energy 😄 So cool to celebrate this moment together! @claclarke

📢 𝗔𝗔𝗔𝗜 𝟮𝟬𝟮𝟳 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀 𝗧𝗿𝘂𝘀𝘁𝘄𝗼𝗿𝘁𝗵𝘆 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗼𝗳 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀: 𝘼𝙣 𝘼𝙜𝙚𝙣𝙩 𝙊𝙥𝙚𝙧𝙖𝙩𝙞𝙣𝙜 𝙎𝙮𝙨𝙩𝙚𝙢 𝙋𝙚𝙧𝙨𝙥𝙚𝙘𝙩𝙞𝙫𝙚 📍 𝗣𝗮𝗹𝗮𝗶𝘀 𝗱𝗲𝘀 𝗖𝗼𝗻𝗴𝗿𝗲̀𝘀, 𝗠𝗼𝗻𝘁𝗿𝗲́𝗮𝗹, 𝗖𝗮𝗻𝗮𝗱𝗮 🇨🇦 🗓️ 𝗙𝗲𝗯𝗿𝘂𝗮𝗿𝘆 𝟮𝟮–𝟮𝟯, 𝟮𝟬𝟮𝟳 (one-day workshop, exact day TBA) AI agents now continuously evolve. How do we keep them trustworthy? 💡 𝗪𝗵𝘆 𝗮 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗽𝗿𝗼𝗯𝗹𝗲𝗺? Many failures come not from a broken model, but from a bad memory, an over-privileged tool, or an update that cannot be undone. Operating systems 🖥️ solved this long ago. We bring that lens to agents, making their evolution 𝘁𝗿𝗮𝗰𝗲𝗮𝗯𝗹𝗲, 𝗯𝗼𝘂𝗻𝗱𝗲𝗱, 𝗮𝗻𝗱 𝗿𝗲𝘃𝗲𝗿𝘀𝗶𝗯𝗹𝗲 🛡️ 📌 𝗧𝗼𝗽𝗶𝗰𝘀 🧠 𝗠𝗲𝗺𝗼𝗿𝘆 (File systems): provenance, isolation, rollback 🛠️ 𝗧𝗼𝗼𝗹𝘀 & 𝗦𝗸𝗶𝗹𝗹𝘀 (Permissions): least privilege, sandboxing, revocation 📈 𝗠𝗼𝗱𝗲𝗹𝘀 & 𝗣𝗼𝗹𝗶𝗰𝗶𝗲𝘀 (System updates): versioning, no silent alignment drift 🤝 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 (Process isolation): stop one failure from spreading 📊 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 (Logging): trace every failure to the change behind it 🎤 𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀 & 𝗣𝗮𝗻𝗲𝗹𝗶𝘀𝘁𝘀: @Yoshua_Bengio (UdeM, LawZero, Mila), @MengdiWang10 (Princeton), @du_yilun (Harvard), @hugo_larochelle (Mila), @ZheqingZhu (Pokee AI), and @yzhao010 (USC). ⏰ 𝗞𝗲𝘆 𝗗𝗮𝘁𝗲𝘀 & 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻 📝 Submission deadline: Nov 20, 2026 (AoE) 📬 Author notification: Dec 2, 2026 (AoE) - Full papers: 8 pages; Short / position papers: 4 pages - Double-blind review, AAAI format 🔗 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗪𝗲𝗯𝘀𝗶𝘁𝗲: trust4rsi-agent.github.io/AA… 📝 𝗣𝗮𝗽𝗲𝗿 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻: openreview.net/group?id=AAAI… 📢 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗲𝗱 𝗶𝗻 𝗯𝗲𝗰𝗼𝗺𝗶𝗻𝗴 𝗮 𝘄𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝘀𝗽𝗼𝗻𝘀𝗼𝗿? Contact us at trust4rsi.agent@gmail.com Happy to organize with @NegarEmpr, @HuaWenyue31539, @BangL93, and @lcharlin. Big thanks to the support and advisory from @StevenYuan666, Yankai Chen, Tianyu Shi, @BokwaiHo, @preslav_nakov, Steve Liu, @alex_pentland We look forward to seeing you in Montréal! 🇨🇦 #AAAI2027 #AIAgents #TrustworthyAI #AISafety #LLM #CallForPapers

Excited to be co-organizing our Trust4RSI-Agent Workshop at #AAAI2027 ! A Workshop on Trustworthy Evolution of AI Agents! 🚀 🥳We have an amazing lineup of speakers and panelists: @Yoshua_Bengio , @MengdiWang10 , @du_yilun , @hugo_larochelle , @ZheqingZhu , and @__yuezhao__ ! 📝 Submission deadline: November 20, 2026 📬 Author notification: December 2, 2026 📍 February 22–23, 2027 · Montréal, Canada 🌐 trust4rsi-agent.github.io/AA… Please share with colleagues working in this space and looking forward to your submissions! Happy to be organizing this alongside @Haolun_Wu0203 @HuaWenyue31539 @BangL93 @lcharlin! #AAAI2027 #AIAgents

Had a great time presenting DeepScholar-Bench at #COLM2026 today! Lots of interesting conversations and interactions! 🤩 If you’re building a deep research system, give our benchmark a try! @COLM_conf has been such an engaging and fun conference so far! 🙌

Today at #COLM2026 I will present DeepScholar-Bench and how we can evaluate AI-generated research synthesis! 📍 Imperial Ballroom, Poster #72 🕚 Today, 11 AM–1 PM Come stop by! Would love to chat!

Agent Swarms are scaling to 1000+ agents, and your message board gets congested. Who builds search for them? #COLM2026 📍Lifelong Agent workshop (Friday)

I'll be BARTing over to #COLM2026 this week 🚇😄 Around all week and happy to chat about search agents & deep research systems! 📄 Thu: DeepScholar-Bench arxiv.org/abs/2508.20033 📄 Fri: Multi-Agent Transactive Memory @ Lifelong Agents Workshop arxiv.org/abs/2606.19911

For IR folks: @xueguang_ma and I quickly tested Jev as a pointwise/pairwise/setwise/listwise reranker on the classic DL19 and DL20, reranking the top 100 BM25 results. It is pretty good and cheap.

Quick intro video on 💰HarnessTax💰 is out!! I also shared some thoughts on what it means for our community to be aware of such cost in coding agents at the end!

Could long-context architectures “find all contradictions” in a science literature? Not yet! 🧵 We study a new class of "high-complexity” tasks whose difficulty scales quadratically with corpus size (as opposed to linearly), reversing common LCLM decisions! (block-sparse attention, hybrid models…)

Impressive paper showing how much the first retrieval step matters for deep research agents. It helps to improve GPT-5.5 from 83.1% to 90.5% on BrowseComp-Plus with the same retriever and the same agent loop. It seems that the gain comes from the opening context. The authors propose Question's Gambit which runs once, before the agent starts searching. It splits the question into clues, turns each clue into complementary searches, pools the results, and reranks them. The agent then starts its loop with that ranked set already in context. The same change lifts GPT-5.4-mini from 68.1% to 79.0% and DeepSeek-v4-pro from 71.4% to 76.9%, and roughly halves calibration error for GPT-5.5. It costs between 2.3 and 5.3 extra tool calls per question. In an error analysis, only 3 of the 79 remaining GPT-5.5 errors come from the gold document never being retrieved. The other 76 happen later, when the agent previews, opens or uses the evidence. Paper: arxiv.org/abs/2609.14412 Chat with Paper: academy.dair.ai/papers/quest…

Thanks @omarsar0 for sharing our paper before we even got the chance to! 🙏 Loved your framing so much we borrowed it for our thread "same retriever, same agent loop, just a better opening move. ♛ "

jev for semantic operators is a great example of how LLM data processing at scale requires rethinking across the stack, model architecture and learning algs included new work and many more thoughts on this coming soon 👀 in the meantime, check out lotus, star and stay tuned (link below)

Two papers you should read from the information retrieval community about scaling up agent swarms:

We pretrained a 2.3B MoE (360M active) Hybrid Mamba-2 that lands within a few points of Llama-3.2-3B using <1% of its pretraining FLOPs. No dedicated cluster. The run hopped between H100s, A100s, V100s (yes, V100s) and TPU v5p/v6e on a single codebase. Meet Rigel 🧵

Cool blogpost from Melissa and team on how much the harness matters for coding agents. On the two benchmarks tested, switching harnesses often changed costs much more than success rates, and the default harness of model providers do not necessarily give results that are pareto optimal!

So we found out that your Claude model might not neccesarily need Claude Code 👀