Akshara Prabhakar

@aksh_555

applied scientist @SFResearch | prev @princeton_nlp, @surathkal_nitk

bay area

aksh555.github.io

Replies Reposts Media

Pinned
Akshara Prabhakar
@aksh_555
Nov 29, 2025
Excited for #NeurIPS next week! I’ll be presenting our APIGen-MT (D&B track paper) on Thursday, 4:30-7:30, and will also be at the @SFResearch booth with the awesome folks from our research team. Looking forward to chatting about LLM post-training and agents! ✨☕️
Ming Zhu and 2 others
Akshara Prabhakar
@aksh_555
Oct 25, 2025
Thanks for sharing our work @omarsar0! 😄 See the agent in action 👇
00:00
elvis
@omarsar0
Oct 21, 2025
People are sleeping on Deep Agents. Start using them now. This is a fun paper showcasing how to put together advanced deep agents for enterprise use cases. Uses the best techniques: task decomposition, planning, specialized subagents, MCP for NL2SQL, file analysis, and more.
Akshara Prabhakar
@aksh_555
Oct 25, 2025
🚀🤖 Check out Enterprise Deep Research — transparent, steerable & modular. Intervene your deep research agent process mid-run, stay aligned in real time!
Weiran Yao
@iscreamnearby
Oct 25, 2025
Stop restarting your long-running agents. Enterprise Deep Research (EDR) lets you steer mid-run—like driving a car. It can save you hours or even days of work. Open-source, enterprise-ready, built by @SFResearch. Try it & drop your use case below 👇 🤖GitHub:
00:00
Akshara Prabhakar
@aksh_555
Aug 1, 2025
🤖 𝘋𝘰𝘪𝘯𝘨 𝘵𝘩𝘦 𝘵𝘢𝘴𝘬 ≠ 𝘶𝘯𝘥𝘦𝘳𝘴𝘵𝘢𝘯𝘥𝘪𝘯𝘨 𝘵𝘩𝘦 𝘶𝘴𝘦𝘳 ✅ Agents complete tasks ❌ But rarely listen, adapt or align Check out our intern @qiancheng1231's 𝐔𝐬𝐞𝐫𝐁𝐞𝐧𝐜𝐡, a benchmark showing even top LLMs align with <𝟑𝟎% of user preferences! ⬇️
Cheng Qian
@qiancheng1231
Aug 1, 2025
🤝 Can LLM agents really understand us? We introduce UserBench: a user-centric gym environment for benchmarking how well agents align with nuanced human intent, not just follow commands. 📄 arxiv.org/pdf/2507.22034 💻 github.com/SalesforceAIRe…
Akshara Prabhakar
@aksh_555
May 8, 2025
🚀 Just dropped APIGen-MT-5k — 5K high-quality multi-turn agent interactions, generated with our APIGen-MT framework! Built for training & evaluating AI agents.
Salesforce AI Research
@SFResearch
May 8, 2025
Introducing APIGen-MT: Our agentic pipeline for multi-turn synthetic data generation that produces high-quality training data for tuning AI agents! Try our open-sourced dataset today! 📊 Paper: bit.ly/44tORzx 🤗 Dataset: bit.ly/3GHuQM5 We used APIGen-MT to
1