{"total":72,"rows":[{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99,"area":"lr"},{"id":"2506.00054","title":"Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers","created":"2025-05-28","cited_by_count":27,"area":"rag"},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2506.20051","title":"Controlled Retrieval-augmented Context Evaluation for Long-form RAG","created":"2025-06-24","cited_by_count":9,"area":"rag"},{"id":"2510.15253","title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","created":"2025-10-17","cited_by_count":9,"area":"rag"},{"id":"2502.18108","title":"Uncertainty Quantification in Retrieval Augmented Question Answering","created":"2025-02-25","cited_by_count":8,"area":"rag"},{"id":"2509.18868","title":"Memory in Large Language Models: Mechanisms, Evaluation and Evolution","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2509.20324","title":"RAG Security and Privacy: Formalizing the Threat Model and Attack Surface","created":"2025-09-24","cited_by_count":8,"area":"rag"},{"id":"2603.06604","title":"Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection","created":"2026-02-18","cited_by_count":8,"area":"alignment"},{"id":"2505.24449","title":"When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations","created":"2025-05-30","cited_by_count":7,"area":"mllm"},{"id":"2509.21359","title":"Influence Guided Context Selection for Effective Retrieval-Augmented Generation","created":"2025-09-21","cited_by_count":7,"area":"rag"},{"id":"2502.13497","title":"Towards Geo-Culturally Grounded LLM Generations","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2508.10467","title":"FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs","created":"2025-08-14","cited_by_count":5,"area":null},{"id":"2508.01290","title":"Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities","created":"2025-08-02","cited_by_count":4,"area":"rag"},{"id":"2512.06476","title":"Knowing What's Missing: Assessing Information Sufficiency in Question Answering","created":"2025-12-06","cited_by_count":3,"area":null},{"id":"2601.11037","title":"BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search","created":"2026-01-16","cited_by_count":3,"area":"agents"},{"id":"2607.09691","title":"What Context Does a Coding Agent Actually Need to Act?","created":"2026-06-19","cited_by_count":3,"area":"agents"},{"id":"2608.02009","title":"HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents","created":"2026-08-03","cited_by_count":3,"area":"rag"},{"id":"2510.00508","title":"Copy-Paste to Mitigate Large Language Model Hallucinations","created":"2025-10-01","cited_by_count":2,"area":"rag"},{"id":"2511.14010","title":"Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports","created":"2025-11-18","cited_by_count":2,"area":"agents"},{"id":"2602.20091","title":"How Retrieved Context Shapes Internal Representations in RAG","created":"2026-02-23","cited_by_count":2,"area":"rag"},{"id":"2603.01486","title":"Agentic Multi-Source Grounding for Enhanced Query Intent Understanding: A DoorDash Case Study","created":"2026-03-02","cited_by_count":2,"area":"agents"},{"id":"2604.05552","title":"Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2511.05706","title":"AdvisingWise: Supporting Academic Advising in Higher Education Settings Through a Human-in-the-Loop Multi-Agent Framework","created":"2025-11-07","cited_by_count":1,"area":"agents"},{"id":"2511.17906","title":"AnimAgents: Coordinating Multi-Stage Animation Pre-Production with Human-Multi-Agent Collaboration","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2604.06173","title":"Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2605.13052","title":"RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.26663","title":"Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.30790","title":"On the impact of retrieved content representations in RAG Pipelines","created":"2026-05-29","cited_by_count":1,"area":"rag"},{"id":"2606.04109","title":"Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.09005","title":"Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries","created":"2026-06-08","cited_by_count":1,"area":"rag"},{"id":"2608.17433","title":"Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations","created":"2026-08-18","cited_by_count":1,"area":"agents"},{"id":"2608.22228","title":"Prompt-Based Abstention Fails Under Misleading Context: A Controlled Study of Small Frozen RAG Models","created":"2026-08-23","cited_by_count":1,"area":"rag"},{"id":"2608.28018","title":"Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning","created":"2026-08-28","cited_by_count":1,"area":"lr"},{"id":"2609.26086","title":"CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2510.05363","title":"MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.16609","title":"Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods","created":"2025-10-18","cited_by_count":0,"area":"rag"},{"id":"2510.17764","title":"Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.26242","title":"Retrieval Augmented Generation-Enhanced Distributed LLM Agents for Generalizable Traffic Signal Control with Emergency Vehicles","created":"2025-10-30","cited_by_count":0,"area":"rag"},{"id":"2512.16553","title":"Needle in the Web: A Benchmark for Retrieving Targeted Web Pages in the Wild","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.10413","title":"LADFA: A Framework of Using Large Language Models and Retrieval-Augmented Generation for Personal Data Flow Analysis in Privacy Policies","created":"2026-01-15","cited_by_count":0,"area":"rag"},{"id":"2602.08294","title":"When Does Context Help? Error Dynamics of Contextual Information in Large Language Models","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.19008","title":"Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval","created":"2026-03-19","cited_by_count":0,"area":"rag"},{"id":"2603.29875","title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough","created":"2026-02-06","cited_by_count":0,"area":"rag"},{"id":"2605.02010","title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.29956","title":"Uncertainty Quantification for Multimodal Retrieval Augmented Generation","created":"2026-05-28","cited_by_count":0,"area":"mllm"},{"id":"2606.23937","title":"When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.00570","title":"Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation","created":"2026-07-01","cited_by_count":0,"area":"rag"},{"id":"2607.22625","title":"TokenMem: Faithful Knowledge Injection for Frozen LLMs","created":"2026-06-17","cited_by_count":0,"area":"rag"},{"id":"2607.27232","title":"Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.01565","title":"DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.16776","title":"GRIP: Grounded Reasoning via Information-Restricted Premises","created":"2026-08-17","cited_by_count":0,"area":"rag"},{"id":"2608.21558","title":"Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation","created":"2026-08-21","cited_by_count":0,"area":"rag"},{"id":"2608.23763","title":"TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.27020","title":"Representation Measurements Under Function-Preserving Reparameterizations","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.27661","title":"Knowing Before Answering: Decoding Language Models for Reliable RAG","created":"2026-08-27","cited_by_count":0,"area":"rag"},{"id":"2608.27768","title":"Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01687","title":"Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.08943","title":"Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.16818","title":"InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation","created":"2026-09-15","cited_by_count":0,"area":"rag"},{"id":"2609.17081","title":"EviScope: Paired Counterfactual Evidence Diagnostics for Faithful and Efficient Grounded Language Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.22537","title":"EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.24885","title":"The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.28876","title":"Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32269","title":"Before Answering: Evidence Sufficiency under Size-Matched Memory Construction","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34358","title":"FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35794","title":"Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention","created":"2026-09-17","cited_by_count":0,"area":"rag"},{"id":"2609.37469","title":"Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG","created":"2026-09-27","cited_by_count":0,"area":"rag"},{"id":"2609.37993","title":"BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals","created":"2026-09-29","cited_by_count":0,"area":"rag"},{"id":"2610.03190","title":"Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18497","title":"Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}