Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL

• URL: http://arxiv.org/abs/2606.14211v1
• Date: Fri, 12 Jun 2026 07:47:15 GMT
• Title: Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
• Abstract summary: RefGRPO is a simple yet effective fix that augments standard RL algorithms with two key ingredients.<n>A free calibration bonus computed by contrasting the agent's own reflection with the actual outcome.<n>The resulting reflection turns the agent into its own verifier grounded in environment feedback.
• Score: 12.234169944475537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback -- even for questions they correctly answered -- and standard RL barely helps due to a credit-assignment mismatch. To close this gap, we propose RefGRPO, a simple yet effective fix that augments standard RL algorithms with two key ingredients: a free calibration bonus computed by contrasting the agent's own reflection with the actual outcome (requiring no additional reward model, LLM judge, or external annotation), and a dynamic schedule on its coefficient. Compared to standard RL baselines, our method simultaneously improves reflection calibration (e.g., reduces underconfidence rate $44.4\% \to 7.7\%$) and task accuracy (e.g., $75.1\% \to 76.5\%$) on text-to-SQL across five benchmarks. The resulting calibrated reflection turns the agent into its own verifier grounded in environment feedback, which further enables (i) better self-improvement that uses reflections as pseudo-rewards without outcome supervision, and (ii) more effective test-time selective prediction by committing only to rollouts flagged as correct.

Related papers

• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry [14.02751159295063]
  We propose PivoARL, a self-feedback retry framework for experience exploitation in large language model (LLM) agents.<n>PivoARL identifies the pivotal erroneous turn through structured reflection and performs local retry only from the corresponding pivotal state.<n>We show that PivoARL achieves significant improvements on Pass@2/3 across all tasks, with an average gain of about 11.5% over MetaRL.
  arXiv  Detail & Related papers  (2026-07-04T04:45:05Z)
• ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents [52.531681772560724]
  Supervised fine-tuning (SFT) is built mostly on successful trajectories and offers little signal for recovery after tool failures.<n>We introduce ReGRPO, a framework that learns reflection-guided correction in tool-using agents.<n> Experiments on GTA and GAIA show that, under the same backbone and tool suite, ReGRPO consistently outperforms strong open-source baselines.
  arXiv  Detail & Related papers  (2026-06-30T09:19:38Z)
• Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents [6.158612515104146]
  We introduce Helpfulness-Harmfulness metrics to measure the tradeoff between agent feedback and reviewer feedback.<n>We evaluate our approach on BFCL and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks.<n>Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o.
  arXiv  Detail & Related papers  (2026-04-29T22:09:47Z)
• Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders [74.55181072260713]
  Training with beam-search negatives consistently outperforms random negatives.<n>We introduce Windowed Partial AUC (WPAUC), which constrains the false positive rate (FPR) to a window to more directly align with Top-$K$ metrics.<n>Experiments on four real-world datasets validate the theory and deliver consistent state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-24T12:31:57Z)
• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation [50.696688705287755]
  We propose Mutual Information Self-Evaluation to overcome the sparse reward challenge in reinforcement learning.<n>MISE enables an agent to learn autonomously from dense internal rewards supplementing sparse extrinsic signals.<n>We prove that utilizing hindsight self-evaluation rewards is equivalent to minimizing an objective that combines mutual information with a KL divergence term between the policy and a proxy reward policy.
  arXiv  Detail & Related papers  (2026-04-13T15:18:51Z)
• Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning [47.963236269307735]
  Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.<n>Current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process.<n>We introduce ReRanking Preference Optimization (RRPO), a reinforcement learning framework that directly aligns reranking with the LLM's generation quality.
  arXiv  Detail & Related papers  (2026-04-02T14:19:47Z)
• RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback [54.39884046754265]
  RetroAgent is an online RL framework that enables agents to master complex interactive environments.<n>Our experiments show that RetroAgent achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-03-09T16:23:33Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty [59.97939500426759]
  This paper describes RLCR, an approach to training reasoning models that jointly improves accuracy and confidence estimation.<n>We show that across diverse datasets, RLCR substantially improves calibration with no loss in accuracy.<n>We also demonstrate that verbalized confidence can be leveraged at test time to improve accuracy and calibration.
  arXiv  Detail & Related papers  (2025-07-22T17:56:01Z)
• RLPR: Extrapolating RLVR to General Domains without Verifiers [103.14103272635893]
  We propose RLPR, a simple verifier-free framework that extrapolates RLVR to broader general domains.<n>We find that addressing the high variance of this noisy probability reward is crucial to make it work.<n>RLPR consistently improves reasoning capabilities in both areas for Gemma, Llama, and Qwen based models.
  arXiv  Detail & Related papers  (2025-06-23T02:56:36Z)
• CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control [26.21425058462886]
  Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. We present the first attempts to solve adaptive RAG from a representation perspective and develop an inherent control-based framework, termed name. Experiments show that name is superior to existing adaptive RAG methods on a diverse set of tasks.
  arXiv  Detail & Related papers  (2024-05-29T03:17:16Z)

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.