Related papers: Prism: An Evolutionary Memory Substrate for Multi-…

Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify…

Recent advances in Multi-Agent Reinforcement Learning have prompted the modeling of intricate interactions between agents in simulated environments. In particular, the predator-prey dynamics have captured substantial interest and various…

Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…

Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We introduce an Agentic Retrieval System that leverages large language models (LLMs) in a…

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel…

Serving large language models (LLMs) is expensive, especially for providers hosting many models, making cost reduction essential. The unique workload patterns of serving multiple LLMs (i.e., multi-LLM serving) create new opportunities and…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…

This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that compactly encodes large classes of tensor programs by symbolically representing some…

Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods discard useful…

Taking inspiration from developmental learning, we present a novel reinforcement learning architecture which hierarchically learns and represents self-generated skills in an end-to-end way. With this architecture, an agent focuses only on…

Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision mechanistic interpretability has been hindered by the lack…

In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as…

Memory is fundamental to large language model (LLM)-based agents, but existing surveys emphasize application-level use (e.g., personalized dialogue), while overlooking the atomic operations governing memory dynamics. This work categorizes…

Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired…

User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embeddings to semantic memory. While existing memory mechanisms…

Real-world applications of reinforcement learning for recommendation and experimentation faces a practical challenge: the relative reward of different bandit arms can evolve over the lifetime of the learning agent. To deal with these…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex…

Agent based modelling (ABM) is a computational approach to modelling complex systems by specifying the behaviour of autonomous decision-making components or agents in the system and allowing the system dynamics to emerge from their…