Retrieval-augmented generation agents development is hindered by the lack of process-level supervision to effectively guide agentic capabilities like task decomposition, retriever invocation, and stepwise decision-making. While reinforcement learning offers a potential solution, it suffers from sparse rewards and the limited reasoning capabilities of large language models (LLMs). Meanwhile, existing data synthesis methods only produce chain-of-thought rationales and fail to model environmental interactions. In this paper, we propose EviPath, an evidence-anchored reasoning path synthesis paradigm for RAG agent development. EviPath comprises: (i) Abductive Subtask Planning, which decomposes the problem into sub-questions and iteratively plans an optimal solution path based on the dependencies between them; (ii) Faithful Sub-question Answering, which uses supporting evidence to construct a proxy environment to generate reasoning thoughts and answers for each sub-question; and (iii) Conversational Fine-Tuning, which formats the complete agent-environment interaction trajectory into a dialogue format suitable for Supervised Fine-Tuning. EviPath allows LLMs to learn complex reasoning and tool-use capabilities directly from synthesized data. Extensive experiments on widely-used question-answering benchmarks show that an 8B parameter model trained with EviPath-synthesized data significantly and consistently outperforms state-of-the-art baselines with a double-digit absolute EM gain of 14.7% in open-domain question answering. Retrieval-augmented generation (RAG) agents, powered by large language models (LLMs) (Guo et al., 2025), can autonomously gather external knowledge and answer complex, multi-hop questions. Compared to vanilla RAG systems (Lewis et al., 2020), RAG agents minimize the need for human intervention, and adapt readily to downstream applications like math problem solving (Zhu et al., 2025), code generation (Zhang et al., 2023), and financial analysis (Wang et al., 2025c). Despite their promise, RAG agents are hard to develop since ground truth reasoning trajectories are unavailable. Mainstream multi-hop question answering datasets Y ang et al. (2018); Ho et al. (2020); Trivedi et al. (2022) provide final answers and supporting facts, while lacking step-wise supervision that is crucial to equip LLMs with agentic behaviors like question decomposition, search query reformulation, and plan refinement.

Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks. We term agents with memory mechanisms as memory agents. In this paper, based on classic theories from memory science and cognitive science, we identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and selective forgetting. Existing benchmarks either rely on limited context lengths or are tailored for static, long-context settings like book-based QA, which do not reflect the interactive, multi-turn nature of memory agents that incrementally accumulate information. Moreover, no existing benchmarks cover all four competencies. We introduce MemoryAgentBench, a new benchmark specifically designed for memory agents. Our benchmark transforms existing long-context datasets and incorporates newly constructed datasets into a multi-turn format, effectively simulating the incremental information processing characteristic of memory agents. By carefully selecting and curating datasets, our benchmark provides comprehensive coverage of the four core memory competencies outlined above, thereby offering a systematic and challenging testbed for assessing memory quality. We evaluate a diverse set of memory agents, ranging from simple context-based and retrieval-augmented generation (RAG) systems to advanced agents with external memory modules and tool integration. Empirical results reveal that current methods fall short of mastering all four competencies, underscoring the need for further research into comprehensive memory mechanisms for LLM agents.

In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge "little semantics" (domain-specific KOS structures) with "big semantics" (broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.

This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and retrieval-augmentation strategy. We introduce an iterative approach where the search engine generates retrieval results for these RAG agents and gathers feedback on the quality of the retrieved documents during an offline phase. This feedback is then used to iteratively optimize the search engine using a novel expectation-maximization algorithm, with the goal of maximizing each agent's utility function. Additionally, we adapt this approach to an online setting, allowing the search engine to refine its behavior based on real-time individual agents feedback to better serve the results for each of them. Experiments on diverse datasets from the Knowledge-Intensive Language Tasks (KILT) benchmark demonstrates that our approach significantly on average outperforms competitive baselines across 18 RAG models. We also demonstrate that our method effectively ``personalizes'' the retrieval process for each RAG agent based on the collected feedback. Finally, we provide a comprehensive ablation study to explore various aspects of our method.

Timeline Analysis (TA) plays a crucial role in Timeline Forensics (TF) within the field of Digital Forensics (DF). It focuses on examining and analyzing time-based digital artefacts, such as timestamps derived from event logs, file metadata, and other relevant data, to correlate events linked to cyber incidents and reconstruct their chronological sequence. Traditional tools often struggle to efficiently handle the large volume and variety of data generated during DF investigations and Incident Response (IR) processes. This paper introduces a novel framework, GenDFIR, which combines Rule-Based Artificial Intelligence (R-BAI) algorithms with Large Language Models (LLMs) to enhance and automate the TA process. The proposed approach consists of two key stages: (1) R-BAI is used to identify and select anomalous digital artefacts based on predefined rules. (2) The selected artefacts are then transformed into embeddings for processing by an LLM with the assistance of a Retrieval-Augmented Generation (RAG) agent. The LLM uses its capabilities to perform automated TA on the artefacts and predict potential incident outcomes. To validate the framework, we evaluated its performance, efficiency, and reliability. Several metrics were applied to simulated cyber incident scenarios, which were presented as forensic case documents. Our findings demonstrate the significant potential of integrating R-BAI and LLMs for TA. This innovative approach underscores the power of Generative AI (GenAI), particularly LLMs, and opens up new possibilities for advanced threat detection and incident reconstruction, marking a significant advancement in the field.

The Electron Ion Collider (EIC): The EIC is the next generation large-scale scientific project that is anticipated to become operational within the next decade [1]. The EIC User group is a fast-evolving community consisting of more than 1,400 physicists from over 38 countries around the world. Book keeping has been a significant challenge in such large collaborative experiments; specifically, in the case of large-scale physics experiments, one faces significant challenges in coordinating information curation between numerous working groups within the collaboration. New collaborators in such a large-scale experiment often feel overwhelmed when they start. For example, when conducting experiments and collecting data, the institutions involved in the collaboration need to comprehend and review a vast amount of documentation during their respective shifts, which can be daunting for the beginner. In this context, having a virtual assistant available to support shift takers would be immensely beneficial. Fine tuning of Large Language Models (LLMs): Fine-tuning an LLM involves refining its abilities and performance in specific tasks or domains by training it further in domain-specific datasets after pretraining, improving effectiveness without retraining the entire model [10, 12]. However, conventional fine-tuning requires substantial computational power and time, posing challenges, especially for extensive models such as GPT-3 (175-B parameters)[3] and Meta LLaMA2 (13-B parameters) [13]. Despite the advent of Low-Rank Adaptation (LoRA) which enables efficient fine-tuning, even on consumer-grade GPUs, fine-tuning remains computationally intensive.