Abstract
The emergence of Large Language Models (LLMs) has ushered in a transformative paradigm in artificial intelligence, Agentic AI, where intelligent agents exhibit goal-directed autonomy, contextual reasoning, and dynamic multi-agent coordination. This paper provides a systematic review and comparative analysis of leading Agentic AI frameworks, including CrewAI, LangGraph, AutoGen, Semantic Kernel, Agno, Google ADK, and MetaGPT, evaluating their architectural principles, communication mechanisms, memory management, safety guardrails, and alignment with service-oriented computing paradigms. Furthermore, we identify key limitations, emerging trends, and open challenges in the field. To address the issue of agent communication, we conduct an in-depth analysis of protocols such as the Contract Net Protocol (CNP), Agent-to-Agent (A2A), Agent Network Protocol (ANP), and Agora. Our findings not only establish a foundational taxonomy for Agentic AI systems but also propose future research directions to enhance scalability, robustness, and interoperability. This work serves as a comprehensive reference for researchers and practitioners working to advance the next generation of autonomous AI systems.

Abstract
AI agentic programming is an emerging paradigm in which large language models (LLMs) autonomously plan, execute, and interact with external tools like compilers, debuggers, and version control systems to iteratively perform complex software development tasks. Unlike conventional code generation tools, agentic systems are capable of decomposing high-level goals, coordinating multi-step processes, and adapting their behavior based on intermediate feedback. These capabilities are transforming the software development practice. As this emerging field evolves rapidly, there is a need to define its scope, consolidate its technical foundations, and identify open research challenges. This survey provides a comprehensive and timely review of AI agentic programming. We introduce a taxonomy of agent behaviors and system architectures, and examine core techniques including planning, memory and context management, tool integration, and execution monitoring. We also analyze existing benchmarks and evaluation methodologies used to assess coding agent performance. Our study identifies several key challenges, including limitations in handling long context, a lack of persistent memory across tasks, and concerns around safety, alignment with user intent, and collaboration with human developers. We discuss emerging opportunities to improve the reliability, adaptability, and transparency of agentic systems. By synthesizing recent advances and outlining future directions, this survey aims to provide a foundation for research and development in building the next generation of intelligent and trustworthy AI coding agents.

Abstract
We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence on costly interactions with external search engines. To this end, we first quantify the intrinsic search capability of LLMs via structured prompting and repeated sampling, which we term Self-Search. Our results reveal that LLMs exhibit strong scaling behavior with respect to the inference budget, achieving high pass@k on question-answering benchmarks, including the challenging BrowseComp task. Building on these observations, we introduce Self-Search RL (SSRL), which enhances LLMs' Self-Search capability through format-based and rule-based rewards. SSRL enables models to iteratively refine their knowledge utilization internally, without requiring access to external tools. Empirical evaluations demonstrate that SSRL-trained policy models provide a cost-effective and stable environment for search-driven RL training, reducing reliance on external search engines and facilitating robust sim-to-real transfer. We draw the following conclusions: 1) LLMs possess world knowledge that can be effectively elicited to achieve high performance; 2) SSRL demonstrates the potential of leveraging internal knowledge to reduce hallucination; 3) SSRL-trained models integrate seamlessly with external search engines without additional effort. Our findings highlight the potential of LLMs to support more scalable RL agent training.

Abstract
We present Dual-Feedback Actor (DFA), a reinforcement learning algorithm that fuses both individual rewards and pairwise preferences (if available) into a single update rule. DFA uses the policy's log-probabilities directly to model the preference probability, avoiding a separate reward-modeling step. Preferences can be provided by human-annotators (at state-level or trajectory-level) or be synthesized online from Q-values stored in an off-policy replay buffer. Under a Bradley-Terry model, we prove that minimizing DFA's preference loss recovers the entropy-regularized Soft Actor-Critic (SAC) policy. Our simulation results show that DFA trained on generated preferences matches or exceeds SAC on six control environments and demonstrates a more stable training process. With only a semi-synthetic preference dataset under Bradley-Terry model, our algorithm outperforms reward-modeling reinforcement learning from human feedback (RLHF) baselines in a stochastic GridWorld and approaches the performance of an oracle with true rewards.

Abstract
Training highly recurrent networks in continuous action spaces is a technical challenge: gradient-based methods suffer from exploding or vanishing gradients, while purely evolutionary searches converge slowly in high-dimensional weight spaces. We introduce a hybrid, derivative-free optimization framework that implements reinforcement learning by coupling global evolutionary exploration with local direct search exploitation. The method, termed ENOMAD (Evolutionary Nonlinear Optimization with Mesh Adaptive Direct search), is benchmarked on a suite of food-foraging tasks instantiated in the fully mapped neural connectome of the nematode \emph{Caenorhabditis elegans}. Crucially, ENOMAD leverages biologically derived weight priors, letting it refine--rather than rebuild--the organism's native circuitry. Two algorithmic variants of the method are introduced, which lead to either small distributed adjustments of many weights, or larger changes on a limited number of weights. Both variants significantly exceed the performance of the untrained connectome (in what can be interpreted as an example of transfer learning) and of existing training strategies. These findings demonstrate that integrating evolutionary search with nonlinear optimization provides an efficient, biologically grounded strategy for specializing natural recurrent networks towards a specified set of tasks.

Abstract
The Traveling Salesman Problem (TSP) is a classic NP-hard combinatorial optimization task with numerous practical applications. Classic heuristic solvers can attain near-optimal performance for small problem instances, but become computationally intractable for larger problems. Real-world logistics problems such as dynamically re-routing last-mile deliveries demand a solver with fast inference time, which has led researchers to investigate specialized neural network solvers. However, neural networks struggle to generalize beyond the synthetic data they were trained on. In particular, we show that there exist TSP distributions that are realistic in practice, which also consistently lead to poor worst-case performance for existing neural approaches. To address this issue of distribution robustness, we present Combinatorial Optimization with Generative Sampling (COGS), where training data is sampled from a generative TSP model. We show that COGS provides better data coverage and interpolation in the space of TSP training distributions. We also present TSPLib50, a dataset of realistically distributed TSP samples, which tests real-world generalization ability without conflating this issue with instance size. We evaluate our method on various synthetic datasets as well as TSPLib50, and compare to state-of-the-art neural baselines. We demonstrate that COGS improves distribution robustness, with most performance gains coming from worst-case scenarios.