Fantastic, systematic work on inter-agent influence just accepted to NeurIPS'26 - congrats to lead @ChandlerDSmith , @prpaskov as well as senior author @lrhammond and the others

Right now we learn how AI agents behave together after the fact, through hacks, logs, and headlines. Soon agents will interact with other agents on our behalf. Commerce will rely on those exchanges. How easily can agents persuade, deceive, and coerce each other? Better to find out in evaluations than in the logs. We started measuring. NeurIPS 2026, paper coming soon With @ChandlerDSmith Qi Guo @tilli_cecilia @SophiaHatz4 @DavidDAfrica @lrhammond @casdewitt @philiptorr

Super excited about co-hosting the AI4GOOD workshop at @NeurIPSConf in Paris - there will be a dedicated multi-agent security/safety track as well in collaboration with @krawiecka_kl @swapneel_mehta and others - the submission deadline is approaching fast!

🚨 8 days left to submit to the Trustworthy AI for Good (AI4GOOD) Workshop at #NeurIPS2026 in Paris We’re still accepting submissions. Join us in bridging AI safety, social good, and real-world impact, so that more capable models actually help society at scale. Our workshop is non-archival, and we will recognize outstanding papers and top reviewers with awards. Deadline: August 29, 2026 (AoE) More details and submission → trustworthy-ai-for-good.gith… 📧 Sponsorship & questions: zjingchen@cs.toronto.edu Let's bridge trustworthy AI and real-world impact. We hope to see you all in Paris. @TerryJCZhang @ChanglingXavier @_agirlyengineer @ozzaney0101, He (Shawn) Shuang, Jerick Shi, Prakhar Gupta, Kexin Li (Cassie), Wenjun (Wendy) Qiu @ZhijingJin @radamihalcea @MilindTambe_AI @david_lie @casdewitt @VectorInst @JinesisLab @EuroSafeAI @MPI_IS @UofTCompSci @TorontoSRI @CIFAR_News @ELLISInst_Tue @UMichCSE @michigan_AI @Harvard @ETH_en @CarnegieMellon @UniofOxford @NeurIPSConf @UofT

Proud to help launch Orbit v0 — a framework for multi-agent evaluations based on @AISecurityInst's Inspect, starting with security but built for safety and capability research too. Huge team effort, and excited to see where this goes. Hugecongrats to @BenHagag20 @wlanderson0 who have been developing this as part of my @MATSprogram, and @csrijac for mentoring. Stoked @coop_ai will be stewarding this going forward.

Work with @wlanderson0, @casdewitt, Sarah Scheffler as part of @matsprogram. We’re presenting ‘Architecture Matters for Multi-Agent Security’ at @icmlconf this week in Seoul, come find us!

Highly recommend @sumeetrm and @CharlieLondon02's upcoming talk on long-horizon reasoning in LLMs - this has been an exciting ride

Honoured to serve as Area Chair at NeurIPS 2026. @NeurIPSConf

New mini experiment + blogpost + trajectories! tldr; we boost performance of RLM(GPT-5.2) to double the best performing number (38.7% --> 65.6%) on LongCoT-mini without any training! An example of the mismanaged geniuses hypothesis (MGH) we (@zli11010, @lateinteraction) proposed earlier this month. The LongCoT benchmark showed that frontier LMs and RLMs struggled to solve difficult compositional reasoning tasks. The paper generally attributes this to the RLMs inability to perform task decomposition, but we argue this is more our fault in how we prompt them; this capability is fully available to GPT-5.2 with an RLM harness! Building on @raw_works's insightful blogpost and @sumeetrm / @CharlieLondon02 et al.'s incredibly useful benchmark, where they originally found RLMs to be incapable of solving the MATH and CS splits altogether. We did not train anything since the release of the initial benchmark. To be fully transparent, these results are not meant to be added to their leaderboard either; benchmarks measure isolated capabilities, and we focus on showing (through different, rather specific prompting) that the capabilities required to solve these tasks are available to the models without additional training! It also has implications about how we would go about training these systems. Full blog below, it's a nice read :)

LLMs will supposedly solve climate change and cure cancer, but in fact they can't even do multi-turn reasoning tasks effectively (SOTA models are < 10% on this benchmark). Interestingly, this work directly compares how much extra performance you get when you add an agentic harness (figure 7): a lot for simple optimization problems, 0% for math and chemistry.

How can we test the "intrinsic" long-horizon reasoning capability of a model? We made a neat template-based problem construction, where each subproblem is easy, but their composition primarily makes any problem hard. Also avoids test saturation by scalable problem difficulty!

Proud to release LongCoT, a hard benchmark for long-horizon reasoning capabilities - measuring reasoning over hundreds of thousands of tokens. 🥳 Project led by my student @sumeetrm in collaboration with many others; excited about kicking off Oxford Witt Lab's collaboration with Ruben Glatt @Livermore_Lab

Training multi-agent teams is hard. #AgentFlow comes to the rescue. We introduce Flow-GRPO, an efficient method to train multi-agent teams. Improves planning and tool use. Selected as an #ICLR2026 Oral (top 1%)🚀

New work led by @aaronrose227 showing how to do interpretability in multi-agent settings

While we cannot always detect steganography directly, sometimes the effects of sharing information secretly can be observed relative to the subsequent behaviour of the agents - an important decision-theoretic approach to steganography detection in CoT settings pioneered by @usmananwar391 @j_piskorz_

The Red Team at @AISecurityInst is hiring! We work with frontier AI companies to red team their misuse safeguards, control measures, and alignment techniques. As the stakes rise, we need much stronger red teaming and many more talented researchers working within gov 🧵