{"total":40,"items":[{"citing_arxiv_id":"2605.21965","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents","primary_cat":"cs.CL","submitted_at":"2026-05-21T03:55:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SpecHop accelerates multi-hop LLM tool use via continuous multi-threaded speculation with asynchronous verification, approaching oracle latency gains and reducing latency up to 40% on retrieval tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17617","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GraphMind: From Operational Traces to Self-Evolving Workflow Automation","primary_cat":"cs.AI","submitted_at":"2026-05-17T19:22:22+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17352","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:45:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AMATA is an adaptive multi-agent trajectory alignment system that improves factual consistency in knowledge-intensive QA via intra-trajectory preference learning and inter-agent dependency optimization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11611","ref_index":13,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG","primary_cat":"cs.AI","submitted_at":"2026-05-12T06:42:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CuSearch reallocates rollout budget in RLVR toward deeper-search trajectories as a proxy for retrieval supervision density, yielding up to 11.8 exact-match gains over uniform GRPO sampling on ZeroSearch.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"that is, when buckets strictly above the current target bucket can already satisfy the full selection budget. Once advanced, the phase never decreases, which prevents oscillation and enforces a monotonic progression of the search-depth curriculum. C.3.2 Concrete Examples When Smax = 5, the target allocations and priorities for each phase are as follows. At phase 0, target lens= [0,K, 0, 0, 0, 0],priorities= [6, 1, 2, 3, 4, 5]. (13) At phase 1, target lens= [0, 0,K, 0, 0, 0],priorities= [6, 5, 1, 2, 3, 4]. (14) At phase 2, target lens= [0, 0, 0,K, 0, 0],priorities= [6, 5, 4, 1, 2, 3]. (15) At phase 3, target lens= [0, 0, 0, 0,K, 0],priorities= [6, 5, 4, 3, 1, 2]. (16) At phase 4, target lens= [0, 0, 0, 0, 0,K],priorities= [6, 5, 4, 3, 2, 1]. (17) Note that at phase 4, the target allocation and priority ordering coincide with SDGA-Auto,"},{"citing_arxiv_id":"2605.10530","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery","primary_cat":"cs.IR","submitted_at":"2026-05-11T13:14:54+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PDR is a user-context-aware framework for LLM research agents that improves report relevance over static baselines, supported by a new dataset and hybrid evaluation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[33] Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, and Emad Barsoum. 2025. Agent laboratory: Using llm agents as research assistants.arXiv preprint arXiv:2501.04227(2025). [34] Aditi Singh, Abul Ehtesham, Saket Kumar, and Tala Talaei Khoei. 2025. Agen- tic retrieval-augmented generation: A survey on agentic rag.arXiv preprint arXiv:2501.09136(2025). [35] Jiabin Tang, Lianghao Xia, Zhonghang Li, and Chao Huang. 2025. AI-Researcher: Autonomous Scientific Innovation.arXiv preprint arXiv:2505.18705(2025). [36] Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. 2008. Ar- netminer: extraction and mining of academic social networks. InProceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data"},{"citing_arxiv_id":"2605.06285","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG","primary_cat":"cs.CL","submitted_at":"2026-05-07T13:56:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LatentRAG performs agentic RAG by generating latent tokens for thoughts and subqueries in one forward pass, matching explicit methods' accuracy on seven benchmarks while reducing latency by ~90%.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"substantial latency in thought and subquery generation, whereas LatentRAG substantially reduces the time spent in these two stages, leading to the observed efficiency gains. Detailed stage-wise latency breakdowns are provided in Appendix E.5. decomposed and effectively solved step by step [21, 22]. Although agentic RAG methods demonstrate strong performance on tasks with complex questions [15, 23], they incur substantial latency due to the additional multi-step interactions [24, 25]. To identify the latency bottlenecks of agentic RAG, we measure the average inference time across different stages for both naive single-step RAG and agentic RAG methods. As shown in Fig. 1, on multi-hop question answering (QA) datasets, the total inference time of a representative agentic RAG"},{"citing_arxiv_id":"2605.05806","ref_index":31,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Retrieval from Within: An Intrinsic Capability of Attention-Based Models","primary_cat":"cs.LG","submitted_at":"2026-05-07T07:42:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Marie-Catherine de Marneffe, and Ivan Vladimir Meza Ruiz (eds.),Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3715-3734, Seattle, United States, July 2022. Association for Computational Linguistics. doi: 10.18653/v1/2022.naacl-main.272. URL https:// aclanthology.org/2022.naacl-main.272/. [31] Aditi Singh, Abul Ehtesham, Saket Kumar, Tala Talaei Khoei, and Athanasios V . Vasilakos. Agentic retrieval-augmented generation: A survey on agentic rag, 2026. URL https://arxiv. org/abs/2501.09136. [32] Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus. End-to-end mem- ory networks. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R."},{"citing_arxiv_id":"2605.05538","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases","primary_cat":"cs.AI","submitted_at":"2026-05-07T00:39:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AgenticRAG equips an LLM with iterative retrieval and navigation tools, delivering 49.6% recall@1 on BRIGHT, 0.96 factuality on WixQA, and 92% correctness on FinanceBench.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05409","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Agentic Retrieval-Augmented Generation for Financial Document Question Answering","primary_cat":"cs.AI","submitted_at":"2026-05-06T19:59:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FinAgent-RAG achieves 76.81-78.46% execution accuracy on financial QA benchmarks by combining contrastive retrieval, program-of-thought code generation, and adaptive strategy routing, outperforming baselines by 5.62-9.32 points.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04496","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States","primary_cat":"cs.CL","submitted_at":"2026-05-06T04:55:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03213","ref_index":97,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","primary_cat":"cs.CR","submitted_at":"2026-05-04T23:09:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"literature suggests that these properties make it relevant to agentic deployments that span newer Arm server and edge environments. Research systems such as virtCCA, OpenCCA, SHELTER, CubeVisor, ACAI, CAGE, and GuaranTEE col- lectively show that ARM CCA can support multi-realm coordination, accelerator integration, and on-device attested inference [94], [95], [96], [97], [98], [99], [100], [101], [102]. Recent platform-level analyses and systems work fur- ther clarify this design point by comparing CCA against TrustZone, formalizing attestation semantics, and extending realm primitives toward container-oriented isolation [103], [104], [52], [105]. On the accelerator confidentiality scope axis, ARM CCA does not natively extend its realm attestation"},{"citing_arxiv_id":"2604.27859","ref_index":78,"ref_count":3,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","primary_cat":"cs.AI","submitted_at":"2026-04-30T13:43:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00043","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms","primary_cat":"cs.DB","submitted_at":"2026-04-29T06:18:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SiriusHelper deploys an LLM agent with intent routing, DeepSearch multi-hop retrieval, and automated SOP distillation to outperform alternatives and reduce ticket volume by 20.8% on Tencent's big data platform.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24219","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Adaptive ToR: Complexity-Aware Tree-Based Retrieval for Pareto-Optimal Multi-Intent NLU","primary_cat":"cs.AI","submitted_at":"2026-04-27T09:24:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Adaptive ToR uses a query complexity classifier to route multi-intent queries to either fast single-step or deeper hierarchical retrieval, improving accuracy by 9.7% and cutting latency by 37.6% on NLU benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22661","ref_index":82,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines","primary_cat":"cs.IR","submitted_at":"2026-04-24T15:36:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"QPP methods can select query variants that boost end-to-end RAG quality over the original query, though retrieval-optimized variants often fail to produce the best generated answers, revealing a utility gap.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22571","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling","primary_cat":"physics.comp-ph","submitted_at":"2026-04-24T14:03:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22217","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow","primary_cat":"cs.SE","submitted_at":"2026-04-24T04:49:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Publication date: October 2025. RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow 0:27 [40] Noah Shinn, Shunyu Yao, and Karthik Narasimhan. 2023. Reflexion: Language Agents with Verbal Reinforcement Learning.arXiv preprint arXiv:2303.11366(2023). https://arxiv.org/abs/2303.11366 [41] Aditi Singh, Abul Ehtesham, Saket Kumar, and Tala Talaei Khoei. 2025. Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG.arXiv preprint arXiv:2501.09136(2025). doi:10.48550/arXiv.2501.09136 [42] Abhishek Soni and Sarah Nadi. 2019. Analyzing comment-induced updates on Stack Overflow. In2019 IEEE/ACM 16th International Conference on Mining Software Repositories (MSR)."},{"citing_arxiv_id":"2604.20144","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"An Agentic Approach to Metadata Reasoning","primary_cat":"cs.DB","submitted_at":"2026-04-22T03:14:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Metadata Reasoner uses agentic LLM reasoning on metadata to select sufficient and minimal data sources, achieving 83.16% F1 on KramaBench and 85.5% F1 on noisy synthetic benchmarks while avoiding low-quality tables 99% of the time.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19689","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding","primary_cat":"cs.AI","submitted_at":"2026-04-21T17:11:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A-MAR decomposes art queries into reasoning plans to condition retrieval, leading to improved explanation quality and multi-step reasoning on art benchmarks compared to baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14896","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Toward Agentic RAG for Ukrainian","primary_cat":"cs.AI","submitted_at":"2026-04-16T11:40:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Agentic RAG for Ukrainian improves answer accuracy via retries but is still limited by document and page retrieval quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14572","ref_index":1,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG","primary_cat":"cs.IR","submitted_at":"2026-04-16T03:05:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Corpus2Skill converts document corpora into navigable hierarchical skill directories for LLM agents, improving QA and RAG quality on single-domain enterprise data but not on open-domain or tabular corpora.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14518","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Mind DeepResearch Technical Report","primary_cat":"cs.AI","submitted_at":"2026-04-16T01:20:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MindDR combines a Planning Agent, DeepSearch Agent, and Report Agent with SFT cold-start, Search-RL, Report-RL, and preference alignment to reach competitive scores on research benchmarks using 30B-scale models.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"arXiv:2501.09136, 2025. URLhttps://arxiv.org/abs/2501.09136. [29] Zhengwei Tao, Jialong Wu, Wenbiao Yin, Junkai Zhang, Baixuan Li, Haiyang Shen, Kuan Li, Liwen Zhang, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, and Jingren Zhou. Webshaper: Agentically data synthesizing via information-seeking formalization, 2025. URL https://arxiv.org/abs/2507.15061. [30] Alibaba NLP Team. Webweaver: Dual-agent framework for open-ended deep research.arXiv preprint arXiv:2509.13312, 2025. URLhttps://arxiv.org/abs/2509.13312. [31] Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, et al. Kimi k2: Open agentic intelligence.arXiv preprint arXiv:2507."},{"citing_arxiv_id":"2605.18770","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Agentic GraphRAG: Navigating Unstructured Financial Data with Collaborative AI","primary_cat":"cs.IR","submitted_at":"2026-04-15T16:16:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Agentic GraphRAG constructs a Neo4j graph via deterministic structured ingestion plus LLM extraction from notices, then deploys modular agents with tool access and reflection to outperform vector-RAG baselines on Swiss commercial gazette data across entity resolution, answer quality, and multi-turn ","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13017","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"PAL: Personal Adaptive Learner","primary_cat":"cs.AI","submitted_at":"2026-04-14T17:54:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"PAL is an AI platform that converts lecture videos into real-time adaptive interactive learning with dynamic questions and tailored end-of-session summaries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11094","ref_index":47,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning","primary_cat":"cs.SE","submitted_at":"2026-04-13T07:12:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"E2E-REME outperforms nine LLMs in accuracy and efficiency for end-to-end microservice remediation by using experience-simulation reinforcement fine-tuning on a new benchmark called MicroRemed.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"To comprehensively evaluate the end-to-end microservice re- mediation capability of current LLMs, we examine a total of nine representative models, encompassing both closed-source and open- source variants. For fairness and consistency, all LLMs are executed within the ThinkRemed framework. Closed-Source LLMs:Qwen3-Plus, Qwen3-Max, and Qwen3- Flash [47]. Open-Source LLMs:QwQ-32B, Qwen3-Next-80B-A3V, Qwen3- 235B-A22B, DeepSeek-V3.2-Exp [ 21], Kimi-K2 [ 45], and GLM- 4.5 [49]. FSE Companion '26, July 5-9, 2026, Montreal, QC, Canada Lingzhe Zhang et al. LLM Backbone Train-Ticket Online-Boutique Simple-Micro Accuracy(%) Latency (s) Accuracy(%) Latency (s) Accuracy(%) Latency (s) Easy Med Hard Easy Med Hard Easy Med Hard Easy Med Hard Easy Med Hard Easy Med Hard"},{"citing_arxiv_id":"2605.18762","ref_index":98,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation","primary_cat":"cs.IR","submitted_at":"2026-04-10T08:26:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ALDEN boosts private data extraction rates from RAG systems by combining active learning for query diversification with dynamic estimation of the underlying knowledge-base topic distribution.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09747","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying","primary_cat":"cs.CR","submitted_at":"2026-04-10T07:22:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07784","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Automotive Engineering-Centric Agentic AI Workflow Framework","primary_cat":"cs.AI","submitted_at":"2026-04-09T04:22:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"The paper presents the Agentic Engineering Intelligence (AEI) framework for modeling automotive engineering workflows as sequential decision processes with AI agent support.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18760","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"DOTRAG: Retrieval-Time Reasoning Along Paths","primary_cat":"cs.IR","submitted_at":"2026-04-06T22:38:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09868","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards","primary_cat":"cs.IR","submitted_at":"2026-01-31T17:00:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Graph RAG that embeds structural and lexical features from ETSI standards improves retrieval performance over vanilla vector methods on a custom Q&A dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.15170","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval","primary_cat":"cs.CV","submitted_at":"2026-01-21T16:47:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Large-scale profiling of recent AI literature shows growth in safety, multimodal reasoning, and agent studies alongside stabilization in neural machine translation and graph methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.12538","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Agentic Reasoning for Large Language Models","primary_cat":"cs.AI","submitted_at":"2026-01-18T18:58:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"API calling, and workflow-based agents dynamically orchestrate sub-tasks and verifiable actions [5, 6, 7]. Conceptually, this parallels the shift from static, one-shot inference to sequential decision-making under uncertainty. Unlike simple input-output mapping, this paradigm requires agents to plan over long horizons, navigate partial observability, and actively improve through feedback [8, 9, 10]. 2 Agentic Reasoning for Large Language Models Definition of Agentic Reasoning Agentic reasoningpositions reasoning as the central mechanism of intelligent agents, spanningfounda- tionalcapabilities(planning,tooluse,andsearch),self-evolvingadaptation(feedback,andmemory-driven adaptation), andcollective coordination(multi-agent collaboration), realizable through eitherin-context"},{"citing_arxiv_id":"2511.20857","ref_index":190,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","primary_cat":"cs.CL","submitted_at":"2025-11-25T21:08:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.07328","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training","primary_cat":"cs.LG","submitted_at":"2025-11-10T17:31:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Q-RAG trains embedders via RL for multi-step retrieval and reports state-of-the-art results on BabiLong and RULER benchmarks for contexts up to 10M tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.20505","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA","primary_cat":"cs.CL","submitted_at":"2025-10-23T12:48:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.09093","ref_index":2,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Exploiting Web Search Tools of AI Agents for Data Exfiltration","primary_cat":"cs.CR","submitted_at":"2025-10-10T07:39:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Indirect prompt injection attacks remain effective on LLMs using web search tools, allowing data exfiltration and exposing ongoing weaknesses in current model defenses.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.07794","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation","primary_cat":"cs.CL","submitted_at":"2025-10-09T05:13:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.24621","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FreeRet: MLLMs as Training-Free Retrievers","primary_cat":"cs.CV","submitted_at":"2025-09-29T11:28:42+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.08480","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging","primary_cat":"cs.IR","submitted_at":"2025-07-11T10:44:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Language composition in training data creates opposing effects on CLIR and mono-IR performance for Korean-English retrieval, which model merging can partially resolve.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2504.19678","ref_index":56,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","primary_cat":"cs.AI","submitted_at":"2025-04-28T11:08:22+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"their limitations, specifically, issues of autonomy and self- improvement that LLM-based agents aim to overcome. The paper provides an extensive review of current practices across six key domains: requirement engineering, code generation, autonomous decision-making, software design, test generation, and software maintenance. B. Agent Architectures and Evaluation Frameworks Singh et al. [56] delves into Agentic Retrieval-Augmented Generation (Agentic RAG), a sophisticated evolution of tra- ditional Retrieval-Augmented Generation systems that en- hances the capabilities of large language models (LLMs). While LLMs have transformed AI through human-like text generation and language understanding, their dependence on static training data often results in outdated or imprecise"}],"limit":50,"offset":0}