Related papers: ANNEAL: Adapting LLM Agents via Governed Symbolic …

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

This paper introduces MeLA, a Metacognitive LLM-Driven Architecture that presents a new paradigm for Automatic Heuristic Design (AHD). Traditional evolutionary methods operate directly on heuristic code; in contrast, MeLA evolves the…

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…

Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment…

Large-scale telecom and datacenter infrastructures rely on multi-layered service and resource models, where failures propagate across physical and logical components and affect multiple customers. Traditional approaches to root cause…

Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it…

Artificial neural networks (ANNs) exhibit a narrow scope of expertise on stationary independent data. However, the data in the real world is continuous and dynamic, and ANNs must adapt to novel scenarios while also retaining the learned…

Legal reasoning requires not only high accuracy but also the ability to justify decisions through verifiable and contestable arguments. However, existing Large Language Model (LLM) approaches, such as Chain-of-Thought (CoT) and…

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…

Standard Retrieval-Augmented Generation (RAG) architectures fail in high-stakes financial domains due to two fundamental limitations: the inherent arithmetic incompetence of Large Language Models (LLMs) and the distributional semantic…

Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that…

Large language models (LLMs) can be adapted either through numerical updates that alter model parameters or symbolic manipulations that work on discrete prompts or logical constraints. While numerical fine-tuning excels at injecting new…

In modern biomedical and econometric studies, longitudinal processes are often characterized by complex time-varying associations and abrupt regime shifts that are shared across correlated outcomes. Standard functional data analysis (FDA)…

The rapid evolution of agentic AI marks a new phase in artificial intelligence, where Large Language Models (LLMs) no longer merely respond but act, reason, and adapt. This survey traces the paradigm shift in building agentic AI: from…

Post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs), yet existing paradigms often reach a performance bottleneck due to the…

Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing paradigm, which treats models as black boxes and relies on…

The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…

MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However,…

Automated Program Repair (APR) aims to automatically generate correct patches for buggy programs. Recent approaches leveraging large language models (LLMs) have shown promise but face limitations. Most rely solely on static analysis,…

Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as…