CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG

• URL: http://arxiv.org/abs/2605.11611v2
• Date: Thu, 14 May 2026 03:20:26 GMT
• Title: CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
• Abstract summary: CuSearch is a curriculum rollout sampling framework built on Search-Depth Greedy Allocation.<n>We show that CuSearch consistently improves performance, achieving up to 11.8 exact-match points over standard GRPO on ZeroSearch.<n>These results establish per-trajectory search depth as a reliable, annotation-free proxy for retrieval supervision density in RLVR-based agentic RAG training.
• Score: 18.557095117884472
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for training agentic retrieval-augmented generation (RAG) systems from outcome-only supervision. Most existing methods optimize policies from uniformly sampled rollouts, implicitly treating all trajectories as equally informative. However, trajectories differ substantially in search depth and are therefore not equally informative: deeper-search trajectories contain more retrieval decision points and provide denser direct supervision for the retrieval sub-policy. Moreover, this heterogeneity grows over training as the within-batch depth distribution shifts toward higher values, yet uniform rollout sampling remains blind to this shift. To address this, we propose CuSearch, a curriculum rollout sampling framework built on Search-Depth Greedy Allocation (SDGA), a batch-level operator that reallocates a fixed update budget toward deeper-search trajectories. SDGA-Auto always targets the deepest available trajectories in the current batch, yielding an implicit training-aligned curriculum as the depth distribution shifts upward. SDGA-Phase explicitly advances the curriculum threshold as deeper trajectories become sufficiently abundant. Experiments across model types and retrieval frameworks show that CuSearch consistently improves performance, achieving up to 11.8 exact-match points over standard GRPO on ZeroSearch. These results establish per-trajectory search depth as a reliable, annotation-free proxy for retrieval supervision density in RLVR-based agentic RAG training.

Related papers

• RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection [88.56816599695391]
  Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time.<n>We propose RING (Retrieval-Internalized Generation), a holistic paradigm spanning both architecture and training.
  arXiv  Detail & Related papers  (2026-08-03T03:00:43Z)
• G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution [16.818086150132853]
  $textbfG-ReAct is a reasoning framework for deep search.<n>It organizes reasoning as $textbfstate evolution over a fixed-topology query graph.<n>G-ReAct supports both training and inference.
  arXiv  Detail & Related papers  (2026-08-02T15:43:37Z)
• Process Reward Informed Tree Rollout for Effective Multi-Turn RL [58.392997761968566]
  In long-horizon agentic tasks, a uniform rollout strategy can waste budget on uninformative dead-end attempts.<n>We propose Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn agent RL.<n>PATR uses task-appropriate process feedback to score partial trajectories, selectively branches from promising states, reuses shared prefixes, and conservatively stops paths to reduce wasted sampling.
  arXiv  Detail & Related papers  (2026-07-17T04:16:58Z)
• OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents [50.79529228477821]
  We introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning.<n>First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding.<n>Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction.
  arXiv  Detail & Related papers  (2026-05-06T17:50:38Z)
• IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning [8.584560411480647]
  We propose IG-Search, a reinforcement learning framework that introduces a step-level reward based on Information Gain (IG)<n>For each search step, IG measures how much the retrieved documents improve the model's confidence in the gold answer relative to a counterfactual baseline of random documents.<n> experiments demonstrate that IG-Search achieves an average EM of 0.430 with Qwen2.5-3B, outperforming the strongest trajectory-level baseline (MR-Search) by 1.6 points and the step-level method GiGPO by 0.9 points on average across benchmarks.
  arXiv  Detail & Related papers  (2026-04-16T15:22:47Z)
• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning [74.07254720088926]
  We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering.<n>We propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO.<n>Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%.
  arXiv  Detail & Related papers  (2026-04-15T07:39:08Z)
• Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training [80.20022221643414]
  Cycle-Consistent Search is a gold-supervision-free framework for training search agents.<n>We show that CCS achieves performance comparable to supervised baselines.<n>These results suggest that CCS provides a scalable training paradigm for training search agents in settings where gold supervision is unavailable.
  arXiv  Detail & Related papers  (2026-04-14T17:00:18Z)
• PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training [28.912613644535668]
  We present PRAISE, a framework for improving data efficiency and credit assignment in agentic search training.<n>Our method uses a single shared model for both search policy learning and prefix answer evaluation.<n>Experiments on multi-hop QA benchmarks show that PRAISE consistently improves performance over strong baselines.
  arXiv  Detail & Related papers  (2026-04-04T10:23:46Z)
• Hybrid Belief Reinforcement Learning for Efficient Coordinated Spatial Exploration [3.0222726254970174]
  Pure model-based approaches provide structured uncertainty estimates but lack adaptive policy learning.<n>This paper presents a hybrid belief-reinforcement learning framework to address this gap.<n>Results show 10.8% higher cumulative reward and 38% faster convergence over baselines.
  arXiv  Detail & Related papers  (2026-03-04T00:00:34Z)
• SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents [30.92763154920672]
  We introduce SRR-Judge, a framework for reliable step-level assessment of reasoning and search actions.<n>SRR-Judge provides fine-grained guidance for search-integrated reasoning and enables efficient post-training annotation.<n> Empirically, SRR-Judge delivers more reliable step-level evaluations than much larger models such as DeepSeek-V3.1.
  arXiv  Detail & Related papers  (2026-02-08T02:07:41Z)
• RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents [144.5598958575922]
  Re-TRAC is an agentic framework that performs cross-trajectory exploration.<n>We show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs.
  arXiv  Detail & Related papers  (2026-02-02T18:58:07Z)
• DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search [53.27052683356095]
  We present DeepSearch, a framework that integrates Monte Carlo Tree Search directly into RLVR training.<n>In contrast to existing methods that rely on tree search only at inference, DeepSearch embeds structured search into the training loop.<n>Our contributions include: (1) a global frontier selection strategy that prioritizes promising nodes across the search tree, (2) selection with entropy-based guidance that identifies confident paths for supervision, and (3) adaptive replay buffer training with solution caching for efficiency.
  arXiv  Detail & Related papers  (2025-09-29T20:00:29Z)
• ETS: Efficient Tree Search for Inference-Time Scaling [61.553681244572914]
  One promising approach for test-time compute scaling is search against a process reward model.<n> diversity of trajectories in the tree search process affects the accuracy of the search, since increasing diversity promotes more exploration.<n>We propose Efficient Tree Search (ETS), which promotes KV sharing by pruning redundant trajectories while maintaining necessary diverse trajectories.
  arXiv  Detail & Related papers  (2025-02-19T09:30:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.