mlsanityData to 14 Oct 2026

CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting

arXiv 2608.20771 ↗First posted 21 Aug 2026cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often causes critical evidence loss or noise inclusion, while over-confidence induced by progressive RL leads to hallucinated answers and redundant searches. To build highly reliable agents, we introduce Conformal Prediction (CP) and propose Conformalized Agentic Search (CAS). This framework establishes reliability guarantees on both the retrieval and training sides: on the retrieval side, an Adaptive Prediction Set (APS), a specific CP realization, translates statistical coverage into dynamic document truncation to construct prediction sets that are adaptive in size; on the training side, Adaptive Conformal Inference (ACI), a dynamic CP algorithm, dynamically constructs prediction sets with controllable coverage to quantify answer confidence, which is then used to penalize low-confidence trajectories within the Group Relative Policy Optimization (GRPO) objective, ensuring the model learns only from reliable ones. Experiments across single-hop and multi-hop QA datasets demonstrate that our framework significantly improves reasoning accuracy while drastically reducing redundant tool invocations, establishing a highly reliable and efficient agent paradigm. Our code is available at https://github.com/S1llyBird/CAS.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 34 of its 43 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

34 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026DynaWeb: Model-Based Reinforcement Learning of Web Agents29 Jan
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG15 Jan

Other references · 32

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  9. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  11. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  12. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
20 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  3. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  4. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  5. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  6. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  7. 2020Classification with Valid and Adaptive Coveragecited by 396
  8. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 375
  9. 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolutioncited by 263
  10. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  11. 2023Conformal Language Modelingcited by 170
  12. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
  13. 2025Beyond Binary Rewards: Training LMs to Reason About Their Uncertaintycited by 117
  14. 2024Taming Overconfidence in LLMs: Reward Calibration in RLHFcited by 112
  15. 2025ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learningcited by 26
  16. 2025CP-Router: An Uncertainty-Aware Router Between LLM and LRMcited by 20
  17. 2025The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucinationcited by 14
  18. 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaborationcited by 11
  19. 2025Conformal Object Detection by Sequential Risk Controlcited by 3
  20. 2025Filtering with Confidence: When Data Augmentation Meets Conformal Predictioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
  2. 2026BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search
  3. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
  4. 2026MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG
  5. 2026Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training
  6. 2025Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
  7. 2026CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
  8. 2026Agentic-R: Learning to Retrieve for Agentic Search