Batu El retweeted
The recent breakthrough in Navier-Stokes has garnered a lot of attention to the new possibilities that emerge when agents work together.
We have been interested in this question for a while. How can a team of agents achieve more than agents working alone?
I'm excited to finally share our new work, "Self-Organizing Agent Teams Learn to Reason Together" 🧵
Batu El retweeted
Can we describe the evolution of opinions in a multi-agent system as a dynamical system?
Check out our latest collaboration, led by one and only @elb4tu
Batu El retweeted
Our new work on “Physics of Agents” arxiv.org/abs/2608.16578 lead by Batu El and Jinhee Paeng in collab w/ @james_y_zou
The outcome of many interacting agents seems hard to reason about. Yet we were able to study the opinion dynamics of 10,000 different LLM agent communities as they communicated with each other to solve both objective and subjective questions.
Remarkably, we could account for their opinion dynamics through a simple Ising model that involved minimizing an energy function corresponding to social pressure to conform. Our dynamics could explain the build up of consensus, polarization, and societal correction of initially incorrect majorities.
Lots more to do on statistical mechanics of interacting agent dynamics!
Batu El retweeted
4/ Some agent communities reach consensus. Others become more polarized over time.
And we can predict these dynamics!
We developed an Ising-type model and fit it to data of agent behavior. The model predicts the community's future. Generalizes to new social graphs + questions!
Batu El retweeted
3/ Each community is a social network of agents with different personas.
They discuss questions ranging from math problems to statements like: “Nuclear power is essential for clean energy.”
Agents talk with their neighbors and update their opinions across multiple rounds.
Batu El retweeted
2/ We studied >10,000 communities of LLM agents that talk to each other and update opinions over time.
We show that collective behavior of interacting AI agents can be modeled and predicted using stat mech.
arxiv.org/pdf/2608.16578
Led by @elb4tu w/ great collaborators
Batu El retweeted
New work I'm very excited about: Physics of Agents!🤖
As AI agents become more prevalent, they'll interact and influence one another.
Can we predict the collective behavior that emerges?
Surprisingly, their dynamics follow compact, predictive laws of statistical physics🧵
Batu El retweeted
can AI write engaging news that people can trust?
introducing ✨Data2Story: a data journalist agent.
give it raw data, it generate a verifiable, multimodal article.
🔍verifiable: every claim is evidence-grounded, traces back to data, code, or a cited source.
🔮multimodal: the article is a generative UI — images, videos, audio, interactive charts.
not just readable, but trustworthy and playable. 🧵1/N
Batu El retweeted
Want to hear about the hot takes from thought leaders in the field? ‼️
Coming next, we have a very very exciting panel with @profjoeyg @KarandikarSagar and Martin Mass 🎙️
@james_y_zou's talk is on, an exciting look at how AI agents are starting to function as collaborative scientists, not just assistants, especially for biomedical discovery and healthcare research.
@CAISconf @Stanford @StanfordHAI
Batu El retweeted
Very excited about our workshop on AI Agents for Discovery in the Wild 🐾🦒🐅, happening *tomorrow*, Tuesday, May 26th 9am-5pm, as part of CAIS '26 in San Jose.
We were blown away by all of the excellent submissions we got…(1/n)
Batu El retweeted
Scaling evaluations—not just compute—is critical for AI-driven science.
SimpleTES introduces a new framework to scale discovery loops, finding new SOTA solutions across 21 open science problems.
Including:
• >2× faster LASSO algorithm
• more efficient quantum routing
+ more!
Great work led by @haotian_yeee and wonderful collaborators!
🚀 Today, we’re excited to introduce SimpleTES for scaling the scientific discovery loop.
🧵 I always ask myself: what are we actually scaling in scientific discovery?
Most LLM discovery methods focus on test-time scaling generation — more tokens, more agents, more turns.
But science advances through the evaluation-driven loops: propose → evaluate → refine → repeat.
SimleTES captures this idea, discovering SOTA solutions across 21 scientific problems!
Key discoveries:
🏎️ 2.17x faster lasso solver than glmnet — the gold-standard LASSO solver, engineered for decades.
⚛️ 24.5% fewer quantum routing overhead on IBM Q20 — superior than previous standard library LightSABRE.
📐 0.380868 on Erdős Minimum Overlap — outperforming previous solutions from mixed-frontier ensembles or humans.
🧬 0.74 on Tabula Muris (scRNA-seq denoising) — new SOTA, generalizing to unseen tissue types without retraining.
#LLM #AI4Science #ScalingLaws #SimpleTES #MachineLearning
Batu El retweeted
🚀 Today, we’re excited to introduce SimpleTES for scaling the scientific discovery loop.
🧵 I always ask myself: what are we actually scaling in scientific discovery?
Most LLM discovery methods focus on test-time scaling generation — more tokens, more agents, more turns.
But science advances through the evaluation-driven loops: propose → evaluate → refine → repeat.
SimleTES captures this idea, discovering SOTA solutions across 21 scientific problems!
Key discoveries:
🏎️ 2.17x faster lasso solver than glmnet — the gold-standard LASSO solver, engineered for decades.
⚛️ 24.5% fewer quantum routing overhead on IBM Q20 — superior than previous standard library LightSABRE.
📐 0.380868 on Erdős Minimum Overlap — outperforming previous solutions from mixed-frontier ensembles or humans.
🧬 0.74 on Tabula Muris (scRNA-seq denoising) — new SOTA, generalizing to unseen tissue types without retraining.
#LLM #AI4Science #ScalingLaws #SimpleTES #MachineLearning
Batu El retweeted
We built TERMS-Bench, a three-tier benchmark for LLM agents in real-world economic negotiation. No LLM-as-judge, no outcome rubrics: the environment itself is the verifier.
🏆Among frontier models, @AnthropicAI Claude Opus 4.6 #1, @Zai_org GLM 5.1 #2.
✨Surprisingly strong: @GoogleDeepMind @googlegemma Gemma 4 31B — best open-weight, holds up as negotiations get harder.
🔗 terms-bench.github.io
Batu El retweeted
Excited to share our work “Multi-Agent Teams Hold Experts Back” was accepted to #ICML2026 🚀
Thank you to wonderful collaborators @james_y_zou @elb4tu @CaoHancheng Carmelo di Nolfo @sun_yanchao and Meng Cao for making my first PhD project such a fun experience!
3/ We argue that as AI systems become more capable of shaping how people think, decide, and act, cognitive security needs to be treated as a priority in AI development.
🔗cstf.dev/blog/ai-development…
4/ I also wrote a companion blog post sharing my own perspective on the opportunities and risks of influencing intelligent agents. It's meant to complement the paper
📎 ellabs.ai/#/blog (my personal website)