Retrieval-augmented generation (RAG) has become a trans-formative approach for enhancing large language models (LLMs) by grounding their outputs in external knowledge sources. Yet, a critical question persists: how can vast volumes of external knowledge be managed effectively within the input constraints of LLMs? Traditional methods address this by chunking external documents into smaller, fixed-size segments. While this approach alleviates input limitations, it often fragments context, resulting in incomplete retrieval and diminished coherence in generation. To overcome these shortcomings, two advanced techniques--late chunking and contextual retrieval--have been introduced, both aiming to preserve global context. Despite their potential, their comparative strengths and limitations remain unclear. This study presents a rigorous analysis of late chunking and contextual retrieval, evaluating their effectiveness and efficiency in optimizing RAG systems. Our results indicate that contextual retrieval preserves semantic coherence more effectively but requires greater computational resources. In contrast, late chunking offers higher efficiency but tends to sacrifice relevance and completeness.

The increasing complexity and scale of modern telecommunications networks demand intelligent automation to enhance efficiency, adaptability, and resilience. Agentic AI has emerged as a key paradigm for intelligent communications and networking, enabling AI-driven agents to perceive, reason, decide, and act within dynamic networking environments. However, effective decision-making in telecom applications, such as network planning, management, and resource allocation, requires integrating retrieval mechanisms that support multi-hop reasoning, historical cross-referencing, and compliance with evolving 3GPP standards. This article presents a forward-looking perspective on generative information retrieval-inspired intelligent communications and networking, emphasizing the role of knowledge acquisition, processing, and retrieval in agentic AI for telecom systems. We first provide a comprehensive review of generative information retrieval strategies, including traditional retrieval, hybrid retrieval, semantic retrieval, knowledge-based retrieval, and agentic contextual retrieval. We then analyze their advantages, limitations, and suitability for various networking scenarios. Next, we present a survey about their applications in communications and networking. Additionally, we introduce an agentic contextual retrieval framework to enhance telecom-specific planning by integrating multi-source retrieval, structured reasoning, and self-reflective validation. Experimental results demonstrate that our framework significantly improves answer accuracy, explanation consistency, and retrieval efficiency compared to traditional and semantic retrieval methods. Finally, we outline future research directions.

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language processing tasks, such as text generation and semantic understanding. However, their performance on numerical reasoning tasks, such as basic arithmetic, numerical retrieval, and magnitude comparison, remains surprisingly poor. This gap arises from their reliance on surface-level statistical patterns rather than understanding numbers as continuous magnitudes. Existing benchmarks primarily focus on either linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios. To bridge this gap, we propose NumericBench, a comprehensive benchmark to evaluate six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and logical reasoning. NumericBench includes datasets ranging from synthetic number lists to the crawled real-world data, addressing challenges like long contexts, noise, and multi-step reasoning. Extensive experiments on state-of-the-art LLMs, including GPT-4 and DeepSeek, reveal persistent weaknesses in numerical reasoning, highlighting the urgent need to improve numerically-aware language modeling. The benchmark is released in: https://github.com/TreeAI-Lab/NumericBench.

With the advent of large language models (LLMs), there has been a great deal of interest in applying them to solve difficult programming tasks. Recent work has demonstrated their potential at program optimization, a key challenge in programming languages research. We propose a blackbox adaptation method called Retrieval Augmented Search (RAS) that performs beam search over candidate optimizations; at each step, it retrieves in-context examples from a given training dataset of slow-fast program pairs to guide the LLM. Critically, we find that performing contextual retrieval based on an LLM-generated natural language description significantly outperforms retrieval based on the source code. In addition, we propose a method called AEGIS for improving interpretability by decomposing training examples into "atomic edits" that are significantly more incremental in nature. We show that RAS performs 1.8$\times$ better than prior state-of-the-art blackbox adaptation strategies, and that AEGIS performs 1.37$\times$ better while performing significantly smaller edits.

Semantic memory refers to our knowledge of facts and relationships between concepts. A successful semantic memory depends on inferring relationships between items that are not explicitly taught. Recent mathematical modeling of episodic memory argues that episodic recall relies on retrieval of a gradually-changing representation of temporal context. We show that retrieved context enables the development of a global memory space that reflects relationships between all items that have been previously learned. When newly-learned information is integrated into this structure, it is placed in some relationship to all other items, even if that relationship has not been explicitly learned. We demonstrate this effect for global semantic structures shaped topologically as a ring, and as a two-dimensional sheet. We also examined the utility of this learning algorithm for learning a more realistic semantic space by training it on a large pool of synonym pairs. Retrieved context enabled the model to "infer" relationships between synonym pairs that had not yet been presented.

Semantic memory refers to our knowledge of facts and relationships between concepts. A successful semantic memory depends on inferring relationships between items that are not explicitly taught. Recent mathematical modeling of episodic memory argues that episodic recall relies on retrieval of a gradually-changing representation of temporal context. We show that retrieved context enables the development of a global memory space that reflects relationships between all items that have been previously learned. When newly-learned information is integrated into this structure, it is placed in some relationship to all other items, even if that relationship has not been explicitly learned. We demonstrate this effect for global semantic structures shaped topologically as a ring, and as a two-dimensional sheet. We also examined the utility of this learning algorithm for learning a more realistic semantic space by training it on a large pool of synonym pairs. Retrieved context enabled the model to "infer" relationships between synonym pairs that had not yet been presented.

Semantic memory refers to our knowledge of facts and relationships between concepts. Asuccessful semantic memory depends on inferring relationships between items that are not explicitly taught. Recent mathematical modeling of episodic memory argues that episodic recall relies on retrieval of a gradually-changing representation oftemporal context. We show that retrieved context enables the development of a global memory space that reflects relationships between all items that have been previously learned. When newly-learned information is integrated into this structure, it is placed in some relationship to all other items, even if that relationship has not been explicitly learned. We demonstrate this effect for global semantic structures shaped topologically as a ring, and as a two-dimensional sheet. We also examined the utility of this learning algorithm for learning a more realistic semantic space by training it on a large pool of synonym pairs. Retrieved context enabled the model to "infer" relationships between synonym pairs that had not yet been presented.