6 papers
Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems
Kartikey Singh Bhandari, Aarya Wadhwani, Dhruv Kumar +1
LLM agents that persist across sessions accumulate stored memories whose validity varies enormously by content type, yet existing memory architectures treat all memories as equally…
Trust Regions Sell, But Who's Buying? Overlap Geometry as an Alternative Trust Region for Policy Optimization
Gaurish Trivedi, Alakh Sharma, Kartikey Singh Bhandari +4
Standard trust-region methods constrain policy updates via Kullback-Leibler (KL) divergence. However, KL controls only an average divergence and does not directly prevent rare, lar…
Actionable Advice from Reviews via Mixture of LoRA Experts: A Two-LLM Pipeline for Issue Extraction and Business Recommendations
Kartikey Singh Bhandari, Manav Ganesh, Yashwant Viswanathan +3
Customer reviews contain detailed, domain specific signals about service failures and user expectations, but converting this unstructured feedback into actionable business decision…
Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviews
Kartikey Singh Bhandari, Tanish Jain, Archit Agrawal +3
Customer reviews contain valuable signals about service quality, but converting large-scale review corpora into actionable business recommendations remains difficult. Standard sent…
Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning
Alakh Sharma, Gaurish Trivedi, Kartikey Singh Bhandari +4
Scalable multi-agent reinforcement learning (MARL) remains a central challenge for AI. Existing population-based methods, like Policy-Space Response Oracles, PSRO, require storing…
HAEPO: History-Aggregated Exploratory Policy Optimization
Gaurish Trivedi, Alakh Sharma, Kartikey Singh Bhandari +3
Exploration is essential in modern learning, from reinforcement learning environments with small neural policies to large language models (LLMs). Existing work, such as DPO, levera…