BRANE maps queries to optimal retrieval pipeline configurations using LLM-derived features and per-configuration correctness predictors, improving the cost-quality Pareto frontier on three benchmarks.
InForty-second International Conference on Machine Learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
FS-Researcher achieves state-of-the-art report quality on deep research benchmarks by using a file-system-based dual-agent framework that scales test-time compute beyond context limits.
citing papers explorer
-
Natural Language Query to Configuration for Retrieval Agents
BRANE maps queries to optimal retrieval pipeline configurations using LLM-derived features and per-configuration correctness predictors, improving the cost-quality Pareto frontier on three benchmarks.
-
Towards Knowledgeable Deep Research: Framework and Benchmark
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
-
FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
FS-Researcher achieves state-of-the-art report quality on deep research benchmarks by using a file-system-based dual-agent framework that scales test-time compute beyond context limits.