Negar Arabzadeh

Postdoc @UCBerkeley @BerkeleySky |👩🏻‍💻Prev @google, @MSFTResearch, @SpotifyResearch | 📚@UWaterloo | Interested in Information Retrieval

[Negar Arabzadeh @NegarEmpr]

1/ Thrilled to introduce T³: a corpus for RAG over reasoning tasks, built from thinking traces.
We show that surprisingly RAG can improve reasoning— with the right corpus.
Rag with Transformed Thinking Traces T³ gain by up to 43.9% on AIME 2025-2026.
🔗 https://t.co/9GPxKnszte 🧵

[Sajad Ebrahimi @sadjadeb]

Excited to announce that our paper “From Noise to Order: Learning to Rank via Denoising Diffusion” has been accepted to #ICTIR2026! 🎉📚

📄Paper: https://t.co/7yIdF2VBJ1
💻 Code: https://t.co/JR5xpDLtQc

[Negar Arabzadeh @NegarEmpr]

@ChuanMg @UWaterloo @claclarke Thanks Dr. Meng 🫢

[Negar Arabzadeh @NegarEmpr]

Grateful that my PhD thesis was recognized as one of the top dissertations in the 2026 Faculty of Mathematics Doctoral Prize at the @UWaterloo ! 🎉

And it is always especially nice to hear kind words from your PhD supervisor @claclarke . I guess that feeling never really goes away, even after you graduate. 😊

https://t.co/P6huzVj0Y9

[Negar Arabzadeh @NegarEmpr]

@sewon__min @UWaterloo @claclarke Thank you Sewon!

[Negar Arabzadeh @NegarEmpr]

@tetsuyasakai @UWaterloo @claclarke Thanks Tetsuya 😀

[Negar Arabzadeh @NegarEmpr]

@claclarke @UWaterloo Thank you Charlie !

[Negar Arabzadeh @NegarEmpr]

@ebrahim_bagheri Thanks Ebrahim!☺️

[Negar Arabzadeh @NegarEmpr]

@YichuanM @UWaterloo @claclarke Thanks Yichuan!

[Negar Arabzadeh @NegarEmpr]

@TEKnologyy @melissapan @icmlconf Thanks Danny!

[Negar Arabzadeh @NegarEmpr]

Happy to share that our @icmlconf paper "Measuring Agents in Production" received an Oral Presentation spot! 🌟
https://t.co/Gwiy1LFP1S
See you all in Seoul! 🇰🇷

[Melissa Pan @melissapan]

Excited to share: MAP has been accepted as 🌟 ICML Spotlight 🌟

We hope MAP can provide data-driven insights that help the communities to work on various under-explored research directions around agent systems!

Huge thanks & congrats to my amazing co-authors. See you all at Seoul! 🫡

[Melissa Pan @melissapan]

Excited to share that MAP has been selected for ✨ICML Oral✨

We look forward to sharing the insights in the paper with the community

And much much appreciations to everyone who participated in our study ❤️ MAP won’t be possible without your contribution to open science

[Negar Arabzadeh @NegarEmpr]

@YichuanM Congrats!!!

[Negar Arabzadeh @NegarEmpr]

There are two layers of contamination control: (1) the trace corpus was built before AIME 2025 and 2026 were released, and (2) we additionally ran full decontamination against all eval benchmarks using a 13-gram Jaccard similarity.
On AIME 2025–2026 specifically, we see up to +56% relative gain on Gemini-2.5-Flash (53.3 → 83.3) and+7.6% on GPT-5.

[Negar Arabzadeh @NegarEmpr]

1/ Thrilled to introduce T³: a corpus for RAG over reasoning tasks, built from thinking traces.
We show that surprisingly RAG can improve reasoning— with the right corpus.
Rag with Transformed Thinking Traces T³ gain by up to 43.9% on AIME 2025-2026.
🔗 https://t.co/9GPxKnszte 🧵

[Negar Arabzadeh @NegarEmpr]

6/ Code, corpora, prompts — all open:
🔗 https://t.co/0IOwa8U2T1
Transformed corpora available on Hugging Face.
Thanks to my amazing coauthors @wenjie_ma , @sewon__min , and @matei_zaharia 🙏

[Negar Arabzadeh @NegarEmpr]

5/ Interestingly, RAG over T³ can be cheaper than No RAG.
Retrieved reasoning shifts work from expensive output tokens to cheap input tokens — the model thinks less and reads more.
Think less. Retrieve thinking. 🧠