arXiv:2606. 11245v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI).
arXiv:2606. 29824v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging.
arXiv:2606. 10532v1 Announce Type: new Abstract: Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks.
The article reports that large language models can predict and collaboratively modulate human memory search during a semantic fluency task. By tracking and forecasting participants’ semantic retrieval patterns, the models outperform other humans in following these mental trajectories. This suggests that AI can serve as a cognitive tool to extend human abilities in open‑ended conceptual exploration and creative ideation.
The study investigates how large language models (LLMs) can assist humans in semantic memory search tasks. By using the semantic fluency task (SFT), the researchers evaluate whether LLMs can follow and enhance human mental trajectories during generative semantic retrieval. Results show that an LLM’s ability to track and predict human memory trajectories in this task surpasses that of other humans.
While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interaction, yet current agents lack the necessary persistent procedural memory.
arXiv:2608. 12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related information is represented, how partial cues recover broader associations, how new information is written or updated, and how memory-related states can be perturbed.
AgenticRag‑R1 is a reinforcement‑learning framework that integrates reasoning, retrieval, and memory through a stack and fine‑grained action space. It uses hierarchical action‑aware rewards and an information‑aware trajectory rejection strategy to support long‑horizon learning. Experiments on multi‑hop, open‑domain, and agentic reasoning benchmarks show that AgenticRag‑R1 outperforms strong baselines and produces robust, interpretable, memory‑aware reasoning behaviors.
arXiv:2607. 01224v1 Announce Type: new Abstract: Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory.
The paper introduces NeuroCognition, a benchmark based on three neuropsychological tests—Raven's Progressive Matrices, Spatial Working Memory, and the Wisconsin Card Sorting Test—to evaluate foundational cognitive abilities in large language models (LLMs). It finds that while LLMs excel on text tasks, their performance drops on image-based and more complex tasks, and they fail different parts of the same tasks compared to humans. NeuroCognition correlates with standard general-capability benchmarks yet measures distinct cognitive skills, highlighting where LLMs align with or diverge from human-like intelligence.
arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.
arXiv:2602. 17229v2 Announce Type: replace Abstract: The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics.
arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.