Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
Quick Answer
The paper introduces DivInit, a novel approach for diverse query initialization in agentic search, which improves performance by reducing query redundancy.
Quick Take
The paper introduces DivInit, a novel approach for diverse query initialization in agentic search, which improves performance by reducing query redundancy. Tested on five open-weight models across eight benchmarks, DivInit achieves average gains of five to seven points in multi-hop QA while maintaining matched computational costs. This method enhances the efficiency of parallel sampling by selecting diverse seeds from a single call rather than independent queries.
Key Points
- DivInit improves agentic search by addressing query redundancy in parallel sampling.
- Average performance gains of five to seven points on multi-hop QA benchmarks.
- Tested across five open-weight models and eight different benchmarks.
- Draws diverse candidates from a single call, enhancing query initialization.
- Code for DivInit is available on GitHub for further exploration.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2606. 17209v1 Announce Type: new Abstract: Test-time scaling for agentic search typically increases depth (i. e. , more turns and tokens per trajectory) or breadth (i. e. , more parallel rollouts). Here we focus on breadth scaling, showing that standard parallel sampling yields diminishing returns, tracing this to query redundancy at the first turn. When models issue similar first queries across rollouts, the threads retrieve overlapping evidence, and subsequent turns are conditioned on this shared retrieval.
We address this limitation with DivInit, a training-free intervention at the first turn. Rather than sampling k independent first queries, DivInit draws n candidates from a single call, picks k < n diverse seeds, and runs them as parallel trajectories. Across five open-weight models and eight benchmarks, DivInit consistently improves over standard parallel sampling, with average gains of five to seven points on multi-hop QA at matched compute. Code available at https://github.
com/cxcscmu/diverse-query-initialization
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.