Archiki Prasad

@ArchikiPrasad

Research Scientist @GoogleDeepMind | Ph.D. from @unccs | @Apple AI/ML Scholar | Prev (intern): GDM, @AIatMeta (FAIR), @allenai_org

New York City, NY

archiki.github.io

Joined December 2016

1,067 Following

2,367 Followers

Replies Reposts Media

Pinned
Archiki Prasad
@ArchikiPrasad
Sep 30
✨Couldn’t think of a better time to share that I joined @GoogleDeepMind over the summer. So happy to share this latest release and super excited about the ongoing work + more to follow! ☀️
Sundar Pichai
@sundarpichai
Sep 30
Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon! It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from
12
Archiki Prasad
@ArchikiPrasad
May 21
What makes a good token-level learning signal for LLM reasoning? In ✨AVSD ✨, we condition on multiple types of privileged information (e.g., ground truth answer, partial solutions) as dense teachers: leveraging what different teacher views agree on, while retaining useful
Duy Nguyen
@duynguyen772
May 21
Sparse binary rewards bottleneck LLM RL, motivating the use of privileged information in self-distillation as dense teachers. How can we use and balance multiple types of privileged info: leveraging stable cross-view info, while preserving view-specific info? Current on-policy
Archiki Prasad
@ArchikiPrasad
May 13
🚨Excited to share ✨Agent-BRACE✨, our new work on belief state modeling for LLM agents in long-horizon tasks! 🔸Most agents either suffer from growing context window or compress history into summaries, however, they do not explicitly track what the agent does not know.
Joykirat
@joykiratsingh
May 13
🚨Excited to announce Agent-BRACE! LLM agents in long-horizon POMDPs either blow up their context with raw history or summarize it, discarding uncertainty by collapsing belief into a point estimate. Agent-BRACE decouples the agent into belief state + policy models, jointly
1
Archiki Prasad
@ArchikiPrasad
May 7
🎉 Excited to share that our work on intrinsic dimensionality of reasoning has been accepted to #ICML2026 as a ✨spotlight✨ (top 2.2%)! We analyze the effectiveness of teaching a model how to reason via the lens of intrinsic dimensionality (the minimum effective capacity a
Archiki Prasad
@ArchikiPrasad
Feb 11
🚨Excited to share our new work viewing reasoning strategies as teaching tools: for fixed target model, which CoT strategies best support learning and generalization? ✨Our answer is intrinsic dimensionality (minimum effective capacity a model needs to solve the task). Somewhat
3
Archiki Prasad
@ArchikiPrasad
Apr 10
🎉 Excited to share that PRInTS has been accepted to #ACL2026 (Main Conference)! PRInTS is a generative PRM that improves agents on long-horizon info-seeking tasks, yielding +9.3% (absolute) gain in avg. accuracy across GAIA, FRAMES & WebWalker! More details in the thread 🧵⬇️
Archiki Prasad
@ArchikiPrasad
Nov 25, 2025
🚨 Excited to announce ✨PRInTS✨, a generative Process Reward Model (PRM) that improves agent’s long-horizon info-seeking via info-gain scoring + summarization. PRInTS guides open + specialized agents with major boosts 👉+9.3% avg. w/ Qwen3-32B across GAIA, FRAMES &

Archiki Prasad

Archiki Prasad’s posts