Ehsan Kamalloo

Research Scientist @ServiceNowRSRCH

[Ehsan Kamalloo @ehsk0]

📢REALM returns for year 2 to dig into the questions that actually matter now that agents are everywhere: reliability, safety, long-horizon planning, multi-agent systems & more.

We'd love to see your work! Submit by 📅 Jul 17.

Join us Oct 29 at #EMNLP2026 in Budapest!
#AIagents

[Akhil Arora @aroraakhilcs]

AI agents like @openclaw 🦞 are everywhere, answering emails, managing calendars, doing our chores for us

📣 REALM is back for year 2! Workshop for Research on Agent Language Models at #EMNLP2026, Budapest 🇭🇺

Stellar lineup ⬇️

📅 Submit by July 17, 23:59 AoE
#LLMAgents #NLProc

[Maryam Hashemzadeh @MaryamHashemz]

So excited to co-organize the Research on Agent Language Models (REALM) workshop at #EMNLP2026! 🚀 We are looking forward to some fantastic discussions and an amazing program.

📅 Deadline: July 17
🌐 Details: https://t.co/eNLPATrDRq

[Nikolai Rozanov @ai_nikolai]

We have an amazing line-up of speakers for the 2nd Edition of the Agent workshop (and amazing organisers too).

Submission is now open. See the post below.

@Cote_Marc @ManlingLi_ @gneubig @vishrav @mariabrbic @b_roziere @PerouzT

[Nicolas Gontier @nicogontier]

The second edition of our agent workshop is now accepting submissions!
Check out our website for the full details!
https://t.co/smN8aiLksL

[Kusha Sareen @KushaSareen]

Can LLMs adapt continually without losing base skills?

Fast-Slow Training (FST) pairs "slow" weights with "fast" context.

FST vs. RL:
• 3x more sample-efficient
• Higher performance ceiling
• Less KL drift (better plasticity)
• Continual learning: succeeds where RL stalls

[Rafael Pardinas @muchomuchacho]

Our first vLLM V0→V1 run on PipelineRL looked broken.

@ehsk0 and I almost reached for an objective-side correction. That would have been the wrong fix.

The real problem: four mismatches in the rollout backend.

🧵

[Alexandre Lacoste @alex_lacoste_]

Research institutions weren't built for a world where AI can generate papers for $15, conferences get 20k+ submissions, and a handful of closed labs are pulling ahead fast.
I wrote about what the research community could do about it, and proposed a concrete system to help.
The Research Commons: multi-blind coordination, anonymous channels, roles for requesters/executors/reproducers/reviewers, and attribution that actually reflects who did what.
https://t.co/FNAgQLYmn1

[ServiceNow AI Research @ServiceNowRSRCH]

(1/8)
🚀 Introducing Super Apriel: One Checkpoint, Many Speeds

Train once → serve at any speed-quality tradeoff

We release:
✓ 15B supernets with 4 mixers/layer
✓ Training code (Fast-LLM)
✓ vLLM serving extension

🧵 How it works ↓

[Rafael Pardinas @muchomuchacho]

Cross-domain RL training works and PipelineRL now supports it natively. We also incorporate adaptive domain sampling to keep the sampling proportions on target throughout training. Evidence from our recent paper: https://t.co/TjytyYQrP2
code: https://t.co/Zs8x9D7l94

[Rafael Pardinas @muchomuchacho]

Better reasoning does not have to mean longer reasoning.

Apriel OpenReasoner: fully reproducible multi-domain RL post-training using public datasets. 30-50% shorter traces, no quality trade-off.

@ServiceNowRSRCH @ehsk0 @dvazquezcv @alexandredrouin

[Patrice Bechard @patricebechard]

What if we didn't need MCP servers after all?
What if we didn't need browser-use agents either?
What if... Claude Code was enough?

In our latest paper, we test exactly this: Can simple terminal agents outperform web agents and tool-based agents on real enterprise tasks?

[Rafael Pardinas @muchomuchacho]

Really cool to see PipelineRL's in-flight weight updates being picked up! We're spreading it across our research teams to train models to reason and to make reasoning more efficient.

[Sasha Rush @srush_nlp]

We agree.

https://t.co/KQk6jtUfXe

[Xiangru (Edward) Jian @EdwardJian2]

🚀 Announcing CUA-Suite, a computer-use agent (CUA) training and evaluation ecosystem based on the largest open expert video corpus for desktop CUAs – VideoCUA. 55 hours of human demonstrations across 87 professional apps — 2.5× bigger than the previous largest dataset.

🌐 https://t.co/KBXTC8dYfP

[Jimmy Lin @lintool]

Congratulations Dr. Thakur for successfully defending his Ph.D. earlier today! Well deserved given his foundational contributions to benchmarks, data, and evaluation... and as his handle @beirmug suggests, there will be celebratory beers tonight! 🍻

[Alexandre Lacoste @alex_lacoste_]

We're sitting on a gold mine of data for evaluation and post-training.

Hundreds of agentic benchmarks, rich structured environments, verifiable signal.

Most of it is sitting idle. Not because nobody wants it, but because the engineering to use it is brutal. 🧵

[ServiceNow AI Research @ServiceNowRSRCH]

🎙️ Today at NVIDIA GTC 2026 — @alex_lacoste_ presents From Benchmark Silos to an Interoperable AI Evaluation Ecosystem!

Catch it here 👇 https://t.co/EcrTdZpn84

10am, Marriott - Ballroom Salon III (L2)

#NVIDIAgtc #AIResearch #ServiceNow

[ServiceNow AI Research @ServiceNowRSRCH]

🎙️ Exciting news: @alex_lacoste_ is presenting at NVIDIA GTC 2026!!

Topic: the fragmented world of agent benchmarks is creating a growing integration tax, and CUBE is the proposed fix.
CUBE = a universal benchmarking protocol built on MCP + Gym. Already validated with NVIDIA's NeMo tools.

📅 March 19 · 10:00 a.m. 🔗 https://t.co/EcrTdZpn84

#NVIDIAgtc #AgenticAI #AIResearch #ServiceNow

[Emiliano Penaloza @emilianopp_]

Remember all the self-distillation papers that came out last week. Well, we also propose it 😅, but…
But alongside something better 😎 π-Distill

We show that with this method, you can distill closed-source frontier models even tho their traces are hidden 🔒.

Both our methods can reach and even surpass the performance of the industry-standard SFT + RL with access to reasoning traces 🤯.

🔬And we spent ~100,000 hours GPU hours on a comprehensive analysis, not because the method is finicky, but because we wanted to understand why it works so well.

🧵
1/10

[Rafael Pardinas @muchomuchacho]

PipelineRL got accepted to TMLR 🎉
~2x faster on-policy RL training through in-flight weight updates. Making LLM agents training fly at @ServiceNowRSRCH

@alexpiche_ @DBahdanau @ehsk0
Paper: https://t.co/asqq5RLiIx
Code: https://t.co/3EsVmCabyx