AtlasNav: Mitigating Evidence Blindness with Persistent Corpus Navigation

arXiv:2608.24764 · cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.AI

Submitted: 2026-08-25

Updated: 2026-09-30

Comments: 29 pages, 7 figures. Code, data, and trajectories have been released

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Evidence Blindness — 42× in this paper
• Accuracy — 41× in this paper · explained in 1 episode
• Benchmark — 31× in this paper · explained in 2 episodes
• RAG — 8× in this paper · explained in 3 episodes
• Direct Corpus Interaction — 7× in this paper
• Agentic Search — 6× in this paper
• Aggregation — 6× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Amortization — 2× in this paper
• Calibration — 2× in this paper · explained in 9 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Agent Memory — 1× in this paper
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper
• Continual Learning — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 21 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
• Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
• EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge
• Toward a Theory of Hierarchical Memory for Language Agents
• Directory-Aware Query and Maintenance in Vector Databases
• From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space
• Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
• FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models
• Towards Retrieving Interaction Spaces for Agentic Search

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems