mlsanityData to 14 Oct 2026

R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling

arXiv 2604.20316 ↗First posted 22 Apr 2026cs.LGcited by 0

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 1 more
Abstract (arXiv)

Function calling empowers large language models (LLMs) to interface with external tools, yet existing RL-based approaches suffer from misalignment between reasoning processes and tool-call decisions. We propose R2IF, a reasoning-aware RL framework for interpretable function calling, adopting a composite reward integrating format/correctness constraints, Chain-of-Thought Effectiveness Reward (CER), and Specification-Modification-Value (SMV) reward, optimized via GRPO. Experiments on BFCL/ACEBench show R2IF outperforms baselines by up to 34.62% (Llama3.2-3B on BFCL) with positive Average CoT Effectiveness (0.05 for Llama3.2-3B), enhancing both function-calling accuracy and interpretability for reliable tool-augmented LLM deployment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 19 of its 20 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

19 of 20 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan
  2. 2023Let's Verify Step by Step31 May
  3. 2017Proximal Policy Optimization Algorithms20 Jul

Other references · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2024Qwen2 Technical Reportcited by 2,120
  7. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  8. 2024ToolACE: Winning the Points of LLM Function Callingcited by 216
  9. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 198
  10. 2025ACEBench: Who Wins the Match Point in Tool Usage?cited by 71
  11. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 68
  12. 2025Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?cited by 11
4 more
  1. 2025Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Modelscited by 8
  2. 2025Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Provingcited by 6
  3. 2025FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinementcited by 5
  4. 2024HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device Scenarioscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  2. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
  3. 2026Small Reasoning Models are Instruction Followers in Function Calling
  4. 2025From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR
  5. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
  6. 2026Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
  7. 2025Revisiting LLM Reasoning via Information Bottleneck
  8. 2025ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs