mlsanityData to 14 Oct 2026

Tool-Adaptive LLM Reranker

arXiv 2607.10555 ↗First posted 12 Jul 2026cs.IR cs.AI cs.CLcited by 0

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

Abstract (arXiv)

Generative Large Language Models (LLMs) have revolutionized information retrieval, yet their strictly parametric nature frequently leads to severe factual hallucinations when confronted with complex queries beyond their epistemic boundaries. While external tool-calling can mitigate this, indiscriminately invoking search tools for every document during reranking incurs prohibitive latency overheads, creating an intractable accuracy-efficiency dilemma. To address this challenge, we propose TALRanker, a novel framework that formalizes pointwise relevance scoring as an agentic Markov decision process. We optimize it via a two-stage training paradigm. An initial warm-up utilizes a language-preserving hybrid loss to prevent the catastrophic forgetting of native generative capacities. Subsequently, an asymmetric cost-aware reward equipped in reinforcement learning forces the policy to autonomously bypass tools for maximum efficiency when confident, while selectively retrieving external evidence to avert severe hallucination penalties when uncertain. Extensive evaluations demonstrate that TALRanker achieves state-of-the-art performance across standard and reasoning-intensive retrieval benchmarks, matching throughput with pointwise rerankers while outperforming parameter-heavy reasoning models.

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 31 of its 43 references that are in the map. First posted on arXiv 12 Jul 2026.

Builds on

31 of 43 references.

References · 31

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  5. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  6. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  9. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  10. 2020Overview of the TREC 2019 deep learning trackcited by 286
  11. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 251
  12. 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Rankingcited by 230
19 more
  1. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  2. 2021Overview of the TREC 2020 deep learning trackcited by 196
  3. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 158
  4. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  5. 2024TinyAgent: Function Calling at the Edgecited by 58
  6. 2025SMART: Self-Aware Agent for Tool Overuse Mitigationcited by 52
  7. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 47
  8. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  9. 2025ReasonRank: Empowering Passage Ranking with Strong Reasoning Abilitycited by 42
  10. 2024Efficient Tool Use with Chain-of-Abstraction Reasoningcited by 33
  11. 2024ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrievalcited by 19
  12. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 16
  13. 2025ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Rerankingcited by 11
  14. 2025Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Searchcited by 11
  15. 2025AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Rerankingcited by 8
  16. 2025Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Shortcited by 7
  17. 2025TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Rankingcited by 5
  18. 2025Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrievalcited by 5
  19. 2025Sample-efficient LLM Optimization with Reset Replaycited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
  2. 2026Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval
  3. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
  4. 2025REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
  5. 2025MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
  6. 2026Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
  7. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
  8. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers