Entity · paper

Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search

paperactiveprovisionalbridge-evidence-static-retrieval-utility-does-not-predict-causal-utility-in-multi-step-agentic-search-9efaed7c·1 events·first seen 4d ago

Aliases: Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search

Co-occurring entities

BM25 HotpotQA Observable Entity Relevance Counterfactual Trajectory Utility

More like this (12)

Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation Counterfactual Trajectory Utility Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging Contextual Retrieval Relaxing Faithfulness with Intervention-Only Causal Discovery Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale Long-context Reasoning Benchmarks Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Recent events (1)

6arXiv · cs.CL·4d ago·source ↗

Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search

A new arXiv paper demonstrates empirically that static retrieval relevance scores are nearly statistically independent from causal utility in multi-step agentic search (Spearman rho = -0.026 across 23,322 document observations). Using a ReAct-style agent over HotpotQA with counterfactual trajectory replays, the authors show that roughly a third of documents are causally load-bearing ('bridge documents') while appearing useless to a static reader. The mechanism is identified: bridge documents supply discriminative entities that redirect subsequent queries, meaning optimizing static RAG utility does not deliver agentic utility.

Evaluation and Benchmarking Agent and Tool Ecosystem BM25 HotpotQA Observable Entity Relevance +2 more