5 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…
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo
Ojas Jain, Dhruv Kumar
We introduce LudoBench, a benchmark for evaluating LLM strategic reasoning in Ludo, a stochastic multi-agent board game whose dice mechanics, piece capture, safe-square navigation,…
Infinite Problem Generator: Verifiably Scaling Physics Reasoning Data with Agentic Workflows
Aditya Sharan, Sriram Hebbale, Dhruv Kumar
Training large language models for complex reasoning is bottlenecked by the scarcity of verifiable, high-quality data. In domains like physics, standard text augmentation often int…
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…
Multi-Agent Inverse Q-Learning from Demonstrations
Nathaniel Haynam, Adam Khoja, Dhruv Kumar +2
When reward functions are hand-designed, deep reinforcement learning algorithms often suffer from reward misspecification, causing them to learn suboptimal policies in terms of the…