When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL

• URL: http://arxiv.org/abs/2605.28918v1
• Date: Wed, 27 May 2026 17:57:43 GMT
• Title: When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
• Abstract summary: We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test.<n>Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding.<n>We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision.
• Score: 10.399451281089318
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test. Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding -- plus a rarer weak-shaping case. We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision. Refinement improves DoorKey-8x8 from 2.3% to 97.6% and KeyCorridor from 31.2% to 86.7% with high seed-to-seed variance. Controls show these gains are not from retrying or extra training: metrics-only re-prompting yields large drops, while a static-vocabulary control recovers much of the gap (87.6%; 70.7%), showing the taxonomy prompt is a major mechanism and dynamic labels provide only partially isolated incremental evidence. Budget-matched and Best-of-3 comparisons separate refinement from selection and training-time effects. Component-removal tests, sensitivity analyses, and an audit against author labels provide converging evidence for the debugging interpretation while revealing calibration limits. Continuous-control results show the boundary: success-based diagnostics can misfire in dense-reward locomotion, and return-trend feedback removes one false-positive mechanism without robust gains. The low-call protocol is a cost contrast with population-based reward search, not a benchmark comparison. In four crossed-variance-design environments, point estimates suggest larger gains when LLM reward-function variance dominates but bootstrap intervals are wide. The method is bounded to sparse structured tasks with reliable interfaces under PPO; fields like event_text may help, hurt, or be neutral.

Related papers

• Verifier-Induced Support Reshaping in On-Policy Optimization [27.782412748608255]
  We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce.<n>We call this verifier-induced support reshaping and define effective rewardable support as successful trajectories reachable within a fixed rollout budget.
  arXiv  Detail & Related papers  (2026-07-31T19:05:43Z)
• Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results [10.526208975530054]
  We study inference-time feed-forward network (FFN) intervention for improving structured outputs without retraining model weights.<n>Amplitude Gating (AG) is a non-destructive alternative that preserves pretrained FFN weight directions and modulates only activation magnitudes during generation.<n>These results identify tool-structured inference as the most credible first target for safe FFN-level inference optimization.
  arXiv  Detail & Related papers  (2026-07-13T07:28:55Z)
• When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion [0.0]
  Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling.<n>We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$.<n>The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups.
  arXiv  Detail & Related papers  (2026-07-12T17:17:18Z)
• Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models [0.0]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models.<n>We systematically compare five reward conditions applied to Qwen2.5-0.5B fine-tuned with Group Relative Policy Optimization (GRPO) on GSM8K.<n>Our results demonstrate that reward derivation is a first-order design decision for RLVR, with process-level supervision substantially improving both accuracy and trace fidelity in small language models.
  arXiv  Detail & Related papers  (2026-07-03T02:16:06Z)
• Leveraging Error Diversity in Group Rollouts for Reinforcement Learning [61.10980882949414]
  Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness.<n>We propose Error Diversity Advantage Shaping (EDAS) to modulate the advantage signal for incorrect rollouts based on intra-group error diversity.<n>EDAS operates as a simple post-hoc adjustment that can be seamlessly integrated into any RLVR algorithm.
  arXiv  Detail & Related papers  (2026-05-17T08:52:31Z)
• DISA: Offline Importance Sampling for Distribution-Matching LLM-RL [56.9445657766829]
  We introduce DISA, which moves this calibration problem outside the RL loop.<n> DISA draws proposal trajectories offline, estimates the partition function via importance sampling, and freezes the resulting partition-function estimate.<n>On two open-weight backbones across six math and three code benchmarks, DISA matches or exceeds the online-coupled distribution-matching baseline Flow.
  arXiv  Detail & Related papers  (2026-05-17T07:14:44Z)
• AIS: Adaptive Importance Sampling for Quantized RL [21.387834718338496]
  Reinforcement learning for large language models (LLMs) is dominated by the cost of rollout generation.<n>This introduces a rollout-training mismatch that biases the policy gradient and can cause training to collapse outright on reasoning benchmarks.<n>We show that the mismatch is nonstationary and acts as a double-edged sword: early in training it provides an exploration bonus, exposing the gradient to trajectories the trainer would otherwise under-sample.<n>We propose Adaptive Importance Sampling (AIS), a correction framework that adjusts the strength of its intervention on a per-batch basis.
  arXiv  Detail & Related papers  (2026-05-13T03:36:57Z)
• Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
  Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
  arXiv  Detail & Related papers  (2026-04-27T09:00:30Z)
• Fragile Reasoning: A Mechanistic Analysis of LLM Sensitivity to Meaning-Preserving Perturbations [2.7946918847372277]
  Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations.<n>We systematically evaluate three open-weight LLMs, Mistral-7B, Llama-3-8B, and Qwen2.5-7B, on 677 GSM8K problems paired with semantically equivalent variants.<n>All three models exhibit substantial answer-flip rates (28.8%-45.1%), with number paraphrasing consistently more disruptive than name swaps.
  arXiv  Detail & Related papers  (2026-04-02T05:30:20Z)
• Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models [68.45272703833209]
  We show that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure.<n>We introduce a three-tiered diagnostic framework that applies increasing adversarial pressure to quantify these vulnerabilities.<n>We release PRM-BiasBench and a diagnostic toolkit to enable robustness evaluation before deployment.
  arXiv  Detail & Related papers  (2026-02-20T23:38:03Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing [21.946965363578087]
  Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks.<n>Prior work shows RLVR works with few prompts, but prompt selection is often based only on training-accuracy variance.<n>We argue that an effective minibatch should provide both (i) a reliable positive anchor and (ii) explicit negative learning signals from rare failures.
  arXiv  Detail & Related papers  (2026-02-03T12:17:25Z)
• 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)

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.