Escaping the Verifier: Learning to Reason via Demonstrations

• URL: http://arxiv.org/abs/2511.21667v2
• Date: Tue, 02 Dec 2025 23:50:30 GMT
• Title: Escaping the Verifier: Learning to Reason via Demonstrations
• Abstract summary: RARO learns strong reasoning capabilities from only expert demonstrations via Inverse Reinforcement Learning.<n>Our method sets up an adversarial interaction between a policy (generator) and a relativistic critic (discriminator)
• Score: 0.4679031868857941
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations that remain under-utilized for reasoning-focused training. We introduce RARO (Relativistic Adversarial Reasoning Optimization) that learns strong reasoning capabilities from only expert demonstrations via Inverse Reinforcement Learning. Our method sets up an adversarial interaction between a policy (generator) and a relativistic critic (discriminator): the policy learns to mimic expert answers, while the critic learns to compare and distinguish between policy and expert answers. Our method trains both the policy and the critic jointly and continuously via RL, and we identify the key stabilization techniques required for robust learning. Empirically, RARO significantly outperforms strong verifier-free baselines on all of our evaluation tasks -- Countdown, DeepMath, and Poetry Writing -- and enjoys the same robust scaling trends as RL on verifiable tasks. These results demonstrate that our method effectively elicits strong reasoning performance from expert demonstrations alone, enabling robust reasoning learning even when task-specific verifiers are unavailable.

Related papers

• ProCeedRL: Process Critic with Exploratory Demonstration Reinforcement Learning for LLM Agentic Reasoning [13.041618832271737]
  Reinforcement Learning (RL) significantly enhances the reasoning abilities of large language models.<n>Applying it to multi-turn agentic tasks remains challenging due to the long-horizon nature of interactions.<n>We propose ProCeedRL: Process Critic with Explorative Demonstration RL.
  arXiv  Detail & Related papers  (2026-04-02T13:10:06Z)
• Native Reasoning Models: Training Language Models to Reason on Unverifiable Data [16.065264121785294]
  We introduce NRT (Native Reasoning Training), a novel framework that cultivates complex reasoning.<n>NRT reframes the training problem by treating the reasoning process as a latent variable.<n>NRT achieves state-of-the-art performance among verifier-free methods.
  arXiv  Detail & Related papers  (2026-02-12T04:15:46Z)
• Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning [50.20267980386502]
  We learn a dense, token-level reward model for process supervision directly from expert demonstrations.<n>The learned reasoning reward serves two complementary roles: (i) it provides step-level feedback to optimise a reasoning policy during training; and (ii) it functions at inference as a critic to rerank sampled traces under fixed compute budgets.
  arXiv  Detail & Related papers  (2025-10-02T09:55:26Z)
• Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs [7.501387372794562]
  Deliberate-to-Intuitive reasoning framework (D2I) improves understanding and reasoning ability of multimodal language models.<n>Our method sets deliberate reasoning strategies to enhance modality alignment only through the rule-based format reward during training.<n>While evaluating, the reasoning style shifts to intuitive, which removes deliberate reasoning strategies during training and implicitly reflects the model's acquired abilities in the response.
  arXiv  Detail & Related papers  (2025-07-09T16:25:44Z)
• Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning [87.7836502955847]
  We propose a novel self-rewarding reinforcement learning framework to enhance Large Language Model (LLM) reasoning.<n>Our key insight is that correct responses often exhibit consistent trajectory patterns in terms of model likelihood.<n>We introduce CoVo, an intrinsic reward mechanism that integrates Consistency and Volatility via a robust vector-space aggregation strategy.
  arXiv  Detail & Related papers  (2025-06-10T12:40:39Z)
• Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models [3.102576158218633]
  Reasoning-based language models have demonstrated strong performance across various domains.<n>Recent research has shown that reasoning also offers significant benefits for safety and guardrail applications.<n>Our study focuses on two key dimensions: data efficiency and inference efficiency.
  arXiv  Detail & Related papers  (2025-05-26T15:01:37Z)
• Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training [86.70255651945602]
  We introduce a novel inference-time steering methodology called Reinforcing Cognitive Experts (RICE)<n>RICE aims to improve reasoning performance without additional training or complexs.<n> Empirical evaluations with leading MoE-based LRMs demonstrate noticeable and consistent improvements in reasoning accuracy, cognitive efficiency, and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-05-20T17:59:16Z)
• ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [53.80183105328448]
  Refine via Intrinsic Self-Verification (ReVISE) is an efficient framework that enables LLMs to self-correct their outputs through self-verification.<n>Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
  arXiv  Detail & Related papers  (2025-02-20T13:50:02Z)
• Safety Reasoning with Guidelines [63.15719512614899]
  Refusal Training (RT) struggles to generalize against various Out-of-Distribution (OOD) jailbreaking attacks.<n>We propose training model to perform safety reasoning for each query.
  arXiv  Detail & Related papers  (2025-02-06T13:01:44Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning [20.263419567168388]
  Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. Inspired by how humans handle such situations, we propose to use self-explanation to recognize valuable high-level relational features. Our main contribution is to propose the Self-Explanation for RL from Demonstrations (SERLfD) framework, which can overcome the limitations of traditional RLfD works.
  arXiv  Detail & Related papers  (2021-10-11T13:59:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.