Where Search Agents Go Off the Rails: Graph-Grounded Step-Level Verification
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- GraphCheck: Multipath Fact-Checking with Entity-Relationship Graphs
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
- Stop-RAG: Value-Based Retrieval Control for Iterative RAG
- Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration
- GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems
- Can Large Language Models Really Improve by Self-critiquing Their Own Plans?
- SmartSearch: Process Reward-Guided Query Refinement for Search Agents
- AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents