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

Robust imitation learning for robot manipulation requires comprehensive 3D perception, yet many existing methods struggle in cluttered environments. Fixed camera view approaches are vulnerable to perspective changes, and 3D point cloud…

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in…

Practical deployment of multi-agent systems (MAS) demands strong performance at test time, motivating methods that guide search during inference and selectively spend compute to improve quality. We present the Multi-Agent System Process…

Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, yet they predominantly rely on frozen agents or static fine-tuning pipelines. To address this limitation, our primary contribution is ATLAS…

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory…

Retrieval-augmented generation (RAG) systems commonly improve robustness via query-time adaptations such as query expansion and iterative retrieval. While effective, these approaches are inherently stateless: adaptations are recomputed for…

Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for progressive…

Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large…

We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two…

A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit…

Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-world deployment requires continuous adaptation to emerging…

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…

In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either…

Motivation: Developing high-performing bioinformatics models typically requires repeated cycles of hypothesis formulation, architectural redesign, and empirical validation, making progress slow, labor-intensive, and difficult to reproduce.…

Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory…

AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural…

The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous,…

Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…