I work on Intelligent Agents and Language-Guided Robots.
Here I document,key insights and engineering breakthroughs at the intersection of Agentic AI, Multi-Agent Systems, Reinforcement learning, post-training techniques for LLMs, efficient LLM deployment, and real-world robotic grounding. Rooted in hands-on development of agent architectures, I document the technical challenges and solutions behind building intelligent, autonomous, goal-driven agents. If you're working on designing agents that reason, collaborate, and act in dynamic environments. I hope this space offers practical, research-informed perspectives drawn from the frontlines of agentic AI engineering.
I am also Research Staff at UCL in Robotics under Prof. Simon Julier where I work on language-guided robotic agents.
If you enjoyed my notes, why not drop a β here? After all, a π§ from paleolithic times would appreciate some feedback!
Blog Posts
-
General Agents as World Models β July 2, 2025
| Tags: Agents
β
π View PDF
-
Small LLMs as Agents β July 2, 2025
| Tags: Agents
β
π View PDF
-
Misinterpretability of Illusion in the Reasoning of LRMs β June 16, 2025
| Tags: LLMs
β
π View PDF
-
Model Agnostic Meta Learning β June 10, 2025
| Tags: Deep Learning
-
Reasoning via Internal Rewards β June 2, 2025
| Tags: LLMs
-
Faithful CoT β May 12, 2025
| Tags: LLMs
-
Much Ado About Proofing β DeepSeek Prover-V2 β My Review β May 03, 2025
| Tags: LLMs
-
Why Do Multi-Agent LLM Systems Fail β Lessons for Fin-Agents β April 30, 2025
| Tags: Agents
-
Agentic Self-Awareness β April 15, 2025
| Tags: Agents
-
Investigation of R1 Zero-like Training β April 1, 2025
| Tags: RL Training
-
Future of Agents β January 6, 2025
| Tags: Agents
-
LLM Powered Autonomous Agents β December 3, 2024
| Tags: Agents
-
Scaling Laws Summary β December 1, 2024
| Tags: Scaling Law
-
Quantization of LLMs β October 15, 2024
| Tags: LLMs
-
Curated List of RAG Papers β October 14, 2024
| Tags: Generative AI
-
Pareto Alignment via Preference Adaptation for LLMs β October 13, 2024
| Tags: AI Alignment
-
Evaluatorβs Reading List β October 12, 2024
| Tags: AI Alignment
-
Intriguing Properties of NNs β October 10, 2024
| Tags: Deep Learning
-
Beyond Preferences in AI Alignment β October 9, 2024
| Tags: AI Alignment