# R2V Agent: Teaching SLMs When to Ask for Help

arXiv: https://arxiv.org/abs/2605.16604 · HTML: https://mlsanity.com/paper/2605.16604/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 20 of 20)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [Algorithms for CVaR Optimization in MDPs](https://mlsanity.com/paper/1406.3339/) (2014)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress](https://mlsanity.com/paper/2511.08325/) (2025)
- [CREAM: Consistency Regularized Self-Rewarding Language Models](https://mlsanity.com/paper/2410.12735/) (2024)
- [Prompt Perturbation Consistency Learning for Robust Language Models](https://mlsanity.com/paper/2402.15833/) (2024)

## Built on by (most cited first, 2 of 2)

- [The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents](https://mlsanity.com/paper/2608.24358/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Efficient agentic systems should incur expensive frontier-model costs only on decisions where a cheaper local model is likely to fail. Existing LLM cascades usually route whole queries before execution, but task difficulty shifts mid-trajectory - after flaky tool calls, truncated observations, or compounding local errors - making pre-execution routing brittle. We introduce R2V-Agent, a risk-calibrated SLM-LLM routing framework for interactive agents. R2V combines four components: a distilled small language model (SLM) policy, a stronger teacher LLM, a lightweight process verifier that scores candidate actions at each step, and a calibrated step-level router. The router is our central contribution: after the SLM is trained, it estimates residual failure risk at each step and escalates only when teacher intervention is warranted. To make the routing problem well-defined, we first train a stable local SLM using a standard offline pipeline: behavioral cloning (BC) on teacher trajectories, followed by verifier-guided Direct Preference Optimization (DPO) with consistency regularization. The router is then trained on this fixed policy's residual failures using Brier-calibrated probability estimation and a Conditional Value-at-Risk (CVaR)-constrained objective that penalizes worst-case failures across perturbation seeds. Across HumanEval+, TextWorld, and TerminalBench with four SLM backbones, R2V improves the reliability-cost frontier: it achieves 94.3% HumanEval+ success with 0.60% LLM escalation, recovers TextWorld from 64.6% SLM-only success to 98.2% at 41.7% escalation, and reaches 93.3% TerminalBench success at 33.9% LLM calls, roughly half the heuristic-router cost.