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

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only…

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively…

We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term…

Although numerous strategies have recently been proposed to enhance the autonomous interaction capabilities of multimodal agents in graphical user interface (GUI), their reliability remains limited when faced with complex or out-of-domain…

Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…

Capturing and simulating intelligent adaptive behaviours within spatially explicit individual-based models remains an ongoing challenge for researchers. While an ever-increasing abundance of real-world behavioural data are collected, few…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological…

Modern neuroscience has accumulated extensive evidence on perception, memory, prediction, valuation, and consciousness, yet still lacks an explicit operational architecture capable of integrating these phenomena within a unified…

Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning and autonomous evolution. Existing methods rely on…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient. However, when input images exhibit low entropy and sparse, the inherent characteristics of diffusion models…

Animals behave adaptively in the environment with multiply competing goals. Understanding of the mechanisms underlying such goal-directed behavior remains a challenge for neuroscience as well for adaptive system research. To address this…

Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with…

Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative…

An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as…

Realizing endogenous narrative evolution in LLM-based multi-agent systems is hindered by the inherent stochasticity of generative emergence. In particular, long-horizon simulations suffer from social memory stacking, where conflicting…

Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations, where retrieved memory carries miscorrelated evidence and…