Ruohao Guo

CS PhD Student @ICatGT | Undergrad @UofIllinois

[Ruohao Guo @GuoOctavia]

Real-world LLM interactions are conversational, yet LLMs are far more vulnerable to multi-turn than single-turn attacks.

Introducing DialTree: RL + tree search for automated multi-turn attack discovery.
📊 81.5% avg ASR@1 across 12 LLMs
📈 +44.2% over prior SOTA

#ICLR2026 [1/6]

[Ruohao Guo @GuoOctavia]

@DeqingFu Interesting analyses!

[Yiyou Sun @YiyouSun]

“AI agents will outperform humans at almost all jobs by 2026–2027.” - The forecast is everywhere.
So we built the exam to test that claim, on real labor-market aligned work. On the hardest tier, top agents pass 2.6%.
Meet Agents' Last Exam (ALE), a rolling benchmark measuring whether agents can actually do real jobs. 🧵👇

[Ruohao Guo @GuoOctavia]

@ChenyuW64562111 @MIT_CSAIL @GoogleDeepMind Congrats 🎉

[Geyang Guo @CherylolGuo]

Knowledge is not evenly distributed across languages. For a given question, what if better information comes from another language?

🔥 We propose Language-Routed Policy Optimization (LRPO), an online reinforcement learning framework that lets LLMs explore and learn from cross-lingual generations during training.

#ICML2026

[Ruohao Guo @GuoOctavia]

[6/6] Huge thanks to my amazing coauthors—Afshin Oroojlooy, Roshan Sridhar, @migballesteros, @alan_ritter, @DanRothNLP —for an incredible collaboration at @Oracle
@OracleCloud and @ICatGT.

Website: https://t.co/jcG9TXtm5g
Paper: https://t.co/haK8ekyqEw

[Ruohao Guo @GuoOctavia]

Real-world LLM interactions are conversational, yet LLMs are far more vulnerable to multi-turn than single-turn attacks.

Introducing DialTree: RL + tree search for automated multi-turn attack discovery.
📊 81.5% avg ASR@1 across 12 LLMs
📈 +44.2% over prior SOTA

#ICLR2026 [1/6]

[Ruohao Guo @GuoOctavia]

[5/6] In addition, DialTree shows highest attack efficiency using fewest queries. Its branch expansion effectively increases trajectory diversity. More analyses are discussed in the paper.

[Yu Su @ysu_nlp]

Introducing @NeoCognition, the agent lab for specialized intelligence.

Everyone needs experts, but human expertise does not scale.

Backed by $40M seed funding, we build self-learning agents that specialize across domains to make expertise abundant.

[Ruohao Guo @GuoOctavia]

@ysu_nlp @NeoCognition Congrats! 🚀

[Ruohao Guo @GuoOctavia]

@nlpxuhui @MSFTResearch @MaartenSap Congrats! 🎉

[Ruohao Guo @GuoOctavia]

@jmin__cho @UNC Congratulations, Jaemin!

[Guanya Shi @GuanyaShi]

I’m so tired of writing rebuttals to this kind of “lack of novelty” review: “This paper trivially combines A, B, and C, so the algorithmic novelty is limited.”

Technically, most (if not all) robotics papers are convex combinations of existing ideas.

I still deeply appreciate A+B+C papers—especially when they deliver:

- New capabilities: the “trivial combination” unlocks behaviors we simply couldn’t achieve before

- Sensible & organic design: A+B+C is clearly the right composition—not some arbitrary A′+B+C′

- Nontrivial interactions: careful analysis of the dynamics, coupling, or failure modes between A, B, C

- Rehabilitating old ideas: A was dismissed for years, but paired with modern B/C, it suddenly works—and teaches us why

- System-level & "interface" insight: the contribution is not any single piece, but how the pieces talk to each other

- Scaling laws or regimes: identifying when/why A+B+C works (and when it doesn’t)

- Engineering clarity: making something actually work robustly in the real world is not “trivial”

- New problem formulations: sometimes the real novelty is in the reformulation—only under this view does A+B+C make sense.

Maybe worth keeping these in mind when reviewing the next A+B+C paper : )

[Yang Chen @ychenNLP]

We released Nemotron Cascade 2 30B A3B.

What makes this release especially meaningful to me is that it reflects a 1.5-year journey at NVIDIA around one core idea: improving AI math reasoning through self-improvement at test time.

Each project tackled a different part of that problem.

With AceMath (24 Q4), we built an external verifier model to identify the right solution during test-time scaling.

With AceReason (24 Q1-2), we scaled the reasoning capabilities of the model through RL so the model could spend more time reflecting while solving problems. Along the way, we found a general, simple and effective RL recipe that we’ve kept using since.

And now with Cascade 2 (25 Q1), we’ve pushed that effort further: the model can generate hypotheses, verify them, and refine them on its own. That self-improvement loop is what enabled IMO gold-level performance at 30B level.

From MATH500, to AIME, and now IMO Proof.

This team is THE BEST.

Technical report:
https://t.co/V0XZn2ypPg

[Ruohao Guo @GuoOctavia]

@hbXNov @kaiwei_chang @adityagrover_ @VioletNPeng @AnthropicAI Congrats! 🎉

[Ruohao Guo @GuoOctavia]

@WeiLin__Chen @Google Very interesting idea! Nice work!

[Yang Chen @ychenNLP]

🥈 Silver Medal at IOI 2025 & Outperforms DeepSeek-R1-0528 on LiveCodeBench.

Instead of mixing different tasks together, we scale *Cascade RL* to develop general LLMs in curriculum (RLFH -> Instruct -> Math -> Code -> SWE).
So many learnings, check out our report!👇

[Alan Ritter @alan_ritter]

At #NeurIPS2025 through Sunday. Come say hi and check out our posters on:

🔒Probabilistic reasoning for text anonymity estimation: Wednesday @ 11am
🤖 Efficient, self-improving agents: Friday @ 11am