# interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification arXiv: https://arxiv.org/abs/2602.11202 · HTML: https://mlsanity.com/paper/2602.11202/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. - Builds on 22 of its 51 references that are in the map. - First posted on arXiv 5 Feb 2026. ## Placed in - LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/) ## Builds on (most cited first, 22 of 22) - [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022) - [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024) - [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022) - [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024) - [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025) - [AgentRx: Diagnosing AI Agent Failures from Execution Trajectories](https://mlsanity.com/paper/2602.02475/) (2026) - [Efficiently Scaling LLM Reasoning with Certaindex](https://mlsanity.com/paper/2412.20993/) (2024) - [Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models](https://mlsanity.com/paper/2506.04210/) (2025) - [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025) - [Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression](https://mlsanity.com/paper/2508.05337/) (2025) - [Entropy After for reasoning model early exiting](https://mlsanity.com/paper/2509.26522/) (2025) - [Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning](https://mlsanity.com/paper/2510.08146/) (2025) - [Early Stopping Chain-of-thoughts in Large Language Models](https://mlsanity.com/paper/2509.14004/) (2025) - [Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics](https://mlsanity.com/paper/2510.17797/) (2025) - [Think Clearly: Improving Reasoning via Redundant Token Pruning](https://mlsanity.com/paper/2507.08806/) (2025) - [Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.10103/) (2025) - [VeruSAGE: A Study of Agent-Based Verification for Rust Systems](https://mlsanity.com/paper/2512.18436/) (2025) - [Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models](https://mlsanity.com/paper/2508.15202/) (2025) - [Towards Verified Code Reasoning by LLMs](https://mlsanity.com/paper/2509.26546/) (2025) - [Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction](https://mlsanity.com/paper/2512.18605/) (2025) ## Built on by (most cited first, 2 of 2) - [CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing](https://mlsanity.com/paper/2608.07424/) (2026) - [SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning](https://mlsanity.com/paper/2610.11223/) (2026) ## Abstract (arXiv) Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctness. Existing approaches either verify only the final answer, which misses early errors, or rely on branch-and-verify strategies that explore multiple trajectories. We introduce interwhen, a single-trajectory verification framework that steers model behavior by providing feedback on intermediate reasoning traces. It addresses two key challenges. First, given a set of verifiers, obtaining verifiable states from the reasoning trace typically requires prompt engineering or external task decomposition into fixed steps. Instead, we propose a monitoring system that periodically polls the reasoning trace and forks inference of the reasoning model to recover intermediate states. Verifiers are run asynchronously alongside generation, adding negligible overhead on correct executions and intervening only when violations occur. Second, beyond math and code, a central challenge for process verification is the scarcity of verifiers. interwhen addresses this through automatic verifier synthesis from natural-language policy documents. Given a policy, it can generate code-based verifiers, including provably correct verifiers in Lean and z3. Together, these contributions yield a plug-and-play test-time verification system that can improve task completion and policy compliance of any reasoning agent. On reasoning benchmarks where policies encode mathematical or logical constraints, interwhen achieves near-perfect accuracy for reasoning models using a fraction of the tokens of baselines. On agentic benchmarks with policy-based verifier generation, it enables improvements in task quality for SLMs without any finetuning, e.g., task completion rate of Qwen3-30B jumps from 32% to 87% on the telecom domain in tau2-bench. Code at https://github.com/microsoft/interwhen.