cs.AINov 16, 2026

Procedure without Judgment: What Small Language Models Learn under an Exact Verifier

Authors: Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar

Organizations: Anna University, Tiruchirappalli, India · Central University of Karnataka, Kalaburagi, India · NIT Tiruchirappalli, Tiruchirappalli, India · Jawaharlal Nehru University, New Delhi, India

Abstract

When an authorization policy blocks an agent's tool call, the audit log should name the facts that forced the decision and nothing more. For an executable policy over an enumerable context space this minimal sufficient reason can be computed exactly, so an explanation is scored against ground truth rather than a proxy for it. We use that exactness to ask what a model can learn from a verifier that has no error in it. The explainer sees one request and one decision, never the policy, and has thirty turns in which it may call the policy on altered requests and ask whether a candidate set of facts is sufficient. Frontier models find the exact reason about half the time with the tools alone, and one sentence telling them to shrink the answer lifts Haiku 4.5 from 58% to 75%. A 4B model fine-tuned on 2000 traces of the deletion algorithm reaches 92% on the policy it was trained on. Teacher kind is what moves this: at matched data size the algorithm-taught student leads the frontier-taught one in all three training seeds, and the two arms never overlap. What the student learns is a fixed schedule of sufficiency checks, and the schedule does not travel. On three public policies it never saw, its answers stay sufficient (94%) and stop being minimal (48%), while Haiku under the same sentence is exact on all 47 episodes. Reinforcement learning from the exact reward leaves held-out accuracy where it was and inverts the strategy, from probing the policy to spending the entire budget on sufficiency checks. The oracle made the effect of training legible, but it did not make training better.

Explore similar work

CardsList
  1. LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

    Nov 2, 2026Sreehari Sankar, Debargha Ganguly, Vikash Singh +17Tool Access Control for LLM AgentsLLM Guardrails

  2. Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process Oracle

    Nov 16, 2026Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R. +2Reward HackingReinforcement Learning with Verifiable Rewards