My lab and collaborators had 4 papers on everything from multi objective alignment, reasoning during mid training, multimodal synthetic data, and generating RL tasks accepted to #ICML2026! Come hang out with us in Seoul and we can talk about the exciting follow-ups! Papers at pearls.ucsd.edu

My former MS student Chris Cui (now PhD student with @rajammanabrolu.bsky.social)motivates Text Adventure Games as testbeds for reasoning. Provides a new benchmark suite of text games. Observes that Zork still kicks LLM’s butts despite training on walkthroughs arxiv.org/abs/2504.14128

TALES: Text Adventure Learning Environment Suite

Reasoning is an essential skill to enable Large Language Models (LLMs) to interact with the world. As tasks become more complex, they demand increasingly sophisticated and diverse reasoning capabiliti...

arxiv.org

My entire PEARLS Lab, and many NVIDIA colleagues, will be at #neurips2025 to chat about their latest. Some papers accepted to the conf are already outdated so just reach out to. Thread 🧵

I am extremely honored and humbled to have been awarded a Test-of-Time award for my 2005 paper "From Linear Story Generation to Branching Story Graphs" with R. Michael Young

Mark Riedl@markriedl.bsky.social · 9mo ago

On my way to the 21st AAAI conference on AI and Interactive Digital Entertainment aiide.org Easily one of my favorite conferences. Full of fun, passionate people Stay tuned for some news

I've done a few versions of this talk but this is the first that's been recorded publicly, thanks to IVADO Montreal A good overview of things my lab has been up to in the last year or so at least in balancing safety/capabilities of (embodied) AI Agents www.youtube.com/watch?v=S-kV...

Navigating the Safety-Capability Spectrum when Teaching Agents with Feedback -Prithviraj Ammanabrolu

YouTube video by IVADO

youtube.com

🔥Excited to share our new work: "A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning"! We study what actually works for agentic multi-turn RL with varying 🌎Environment, 🤖Policy, and ⭐Reward. We conduct various ablations and empirical analysis on 🧩TextWorld, 🧙ALFWorld, and 🧑‍💻SWE-Gym.

I'll be at #CoLM2025 and the IVADO agents workshop right before in Montreal. My students will be presenting two papers in the main conf. I'll also do a ws keynote where I'll talk about some of our latest. Come by and say hi next week!

I'm probably mostly going to stop posting on this site. There's close to no engagement and it's not worth the effort to cross post for the amount of time that takes. Find me elsewhere / email me

I recently left Mosaic/Databricks Research. It's been a ride building out the RL team from <4 ppl to 20+ across two companies & acquisition +figuring out RL as a Service in prod. Mosaic had insane talent density Some "relaxation" while I put out Prof fires for a smol bit then new adventures!

If you work in the intersection of NLP and games/narrative, then this workshop is for you! wordplay-workshop.github.io/cfp/ Organized by the amazing @laramartin.net and @rajammanabrolu.bsky.social (among others)

The thing that feels so off about the core tech world is that every convo is very transactional. Maybe true elsewhere too. "Oh you're an expert in RL, can you answer questions about my new startup?" Every single (Bay) party. No I do not want to consult. I just wanna hang out.

Of all the labeling startups out there to acquihire, this was... an interesting choice. Says a lot actually

. @bosungkim.bsky.social will be at #CVPR2025 in Nashville this week to present this and just generally talk about scaling memory for embodied agents! Catch her at the poster sessions and also the Foundation Models meets Embodied Agents Workshop on Wed

Prithviraj "Raj" Ammanabrolu@rajammanabrolu.bsky.social · last yr.

"Foundation" models for embodied agents are all the rage but how to actually do complex looong context reasoning? Can we scale Beyond Needle(s) in the (Embodied) Haystack? ∞-THOR is an infinite len sim framework + guide on (new) architectures/training methods for VLA models

I've heard this personally from multiple PMs at AI companies. Students are one of the biggest demographics and they need to "break in" and have even more usage to improve their metrics. Classic corporate economic incentives

Mark Riedl@markriedl.bsky.social · last yr.

AI companies in the US gave access to their systems to students for free during college exams China disabled access to AI systems during nationwide college exams www.theverge.com/news/682737/... Feel free to draw your own conclusions

Tis the era of bringing back every AI benchmark ever but this time by the LLM people and for the LLMs

Had a fun little visit to Cambridge LTL where I talked about a bunch of my lab's latest papers including some still not public with the key takeaway that "RL can absolutely learn new things and is not just resurfacing knowledge" talks.cam.ac.uk/show/archive...

Interesting tidbit from UCSD's Victor Shih on a podcast talking about Chinese AGI efforts is that Deepseek is good at Chinese govt doc understanding cause that's what affects stock prices most and DS is a hedge fund. www.youtube.com/watch?v=b1Te...

Xi Jinping’s paranoid approach to AGI, debt crisis, & Politburo politics — Victor Shih

YouTube video by Dwarkesh Patel

youtu.be

Looks like Gemini gets AIR 6 in #JEE2025 with a score of 323 Only 5 highschoolers in all India do better than an LLM in the single most important exam of their to get into the IITs The legacy edu selection systems are now worse than useless

I get prepping for worst case scenarios but a lot of AI Safety debates I somehow end up these days in boil down to "assume you have Machine God in a box, now tell me how to align it" I could rant for hours but seriously y'all this isn't productive

"Foundation" models for embodied agents are all the rage but how to actually do complex looong context reasoning? Can we scale Beyond Needle(s) in the (Embodied) Haystack? ∞-THOR is an infinite len sim framework + guide on (new) architectures/training methods for VLA models

I'm presenting today on AI Agents vs Agency Law at the 12th Governance of Emerging Technologies and Science Conference events.asucollegeoflaw.com/gets/ If agency law were to be applied to AI Agents (mostly in ecommerce settings), where does current AI align with the laws and where does it not?

I like the Ultra Scale Playbook from Huggingface and give it to my MS/first year PhD students to read as a prereq huggingface.co/spaces/nanot... Is there a "RLSys" version of this on scaling RL+LLM training? If not + there's OSS community interest, I'll prob write one?

that's what's hot

George Porter@georgemporter.bsky.social · last yr.

NSF sending out it's "NeTS May 2025 Newsletter" email to everyone

We now have a whole YouTube video explaining our MINDcraft paper, check it out! youtu.be/MeEcxh9St24

Mindcraft Research Paper!

YouTube video by Emergent Garden

youtu.be

Prithviraj "Raj" Ammanabrolu@rajammanabrolu.bsky.social · last yr.

The future of embodied AI revolves around *collaborative* multi agent scenarios that need natural language communication, task delegation, resource sharing, and more ⛏️ Here are MINDcraft and MineCollab, a simulator and benchmark purpose built to enable research in this area!

The part of the Prof job I'm enjoying by far the most right now is teaching actually

This is reasonably written and echoes many of my own fears. The upside of AI is too huge to pass up but also there's a high chance that the vast majority of humanity is on track to becoming economically obsolete without really any transition plan www.theguardian.com/books/2025/m...

What's with these arguments over whether X or Y or whatever was the first LLM RL library? These all came in the last 3 months We wrote multiturn RL4LMs like 3+ years ago github.com/allenai/RL4LMs There were other simple versions even before. ML ppl approaching goldfish memory

GitHub - allenai/RL4LMs: A modular RL library to fine-tune language models to human preferences

A modular RL library to fine-tune language models to human preferences - allenai/RL4LMs

github.com

Cool looking paper from @markriedl.bsky.social's lab arxiv.org/abs/2505.03547 making significant improvements over our arxiv.org/abs/2001.10161 from 5+ years ago

Yeah this is actual unironic advice for any 1st years: you seriously need to go get beers or otherwise hangout socially with more senior grad students (no one else will really know) and hopefully get ensconced enough that someone will tell you “hey just fyi Dr. GoodPubs is low-key a total sociopath”

Some progress! Looks like o3/4 get about 16% on the human written portion of TALES compared to previous SoTA of 13%

Prithviraj "Raj" Ammanabrolu@rajammanabrolu.bsky.social · last yr.

Text games are some of the most cognitively complex tasks out there requiring thousands of perfectly executed actions to complete SOTA LLM agents are ok at synthetically (procedurally) generated tasks, but get at most *13%* on human made ones 👨‍💻github.com/microsoft/tale-suite