Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning

• URL: http://arxiv.org/abs/2602.09598v1
• Date: Tue, 10 Feb 2026 09:50:24 GMT
• Title: Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning
• Abstract summary: In long-horizon tool-integrated reasoning trajectories, an early irrecoverable mistake can determine success or failure.<n>We propose Error-Localized Policy Optimization (ELPO) to localize the first irrecoverable step and leverage it for fine-grained credit assignment.<n>Our code will be publicly released soon.
• Score: 36.23268783033404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak step-level credit assignment. In long-horizon TIR trajectories, an early irrecoverable mistake can determine success or failure, making it crucial to localize the first irrecoverable step and leverage it for fine-grained credit assignment. We propose Error-Localized Policy Optimization (ELPO), which localizes the first irrecoverable step via binary-search rollout trees under a fixed rollout budget, converts the resulting tree into stable learning signals through hierarchical advantage attribution, and applies error-localized adaptive clipping to strengthen corrective updates on the critical step and its suffix. Across TIR benchmarks in math, science QA, and code execution, ELPO consistently outperforms strong Agentic RL baselines under comparable sampling budgets, with additional gains in Pass@K and Major@K scaling, rollout ranking quality, and tool-call efficiency. Our code will be publicly released soon.

Related papers

• HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning [95.29291773706224]
  Tool-Integrated Reasoning is a capability for LLM agents to solve complex tasks by interacting with external tools iteratively.<n>Existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally.<n>This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns.
  arXiv  Detail & Related papers  (2026-08-22T09:14:15Z)
• 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)
• ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments [45.577182866886126]
  We present ASAP, an agent-system co-design for HPO.<n>We show how ASAP integrates a diverse pool of inductive-biased generalizations and to select among their proposals each round.<n>We also show how ASAP re-architects the loop to reduce end-to-end wall-clock while preserving regret quality.
  arXiv  Detail & Related papers  (2026-06-23T22:00:26Z)
• Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning [2.384534878752428]
  We propose Uncertainty-Aware LLM-Guided Policy Shaping (ULPS), a framework that integrates a calibrated Large Language Model into the Reinforcement Learning training loop.<n>ULPS employs an A*-based oracle to synthesize optimal symbolic trajectories, which are used to fine-tune a BERT-based language model.<n>We observe consistent improvements in success rate, reward efficiency, and sample complexity over unguided, uncalibrated, and standard RL baselines.
  arXiv  Detail & Related papers  (2026-06-04T19:46:45Z)
• CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs [0.0]
  This work proposes CASS-RTL, a first-of-its-kind framework for discovering and leveraging LLMs' correctness-aware components.<n>We observe 10%-20% improvement in pass@1/5/10 accuracy on VerilogEval and 5% improvement on CVDP.
  arXiv  Detail & Related papers  (2026-06-04T04:02:51Z)
• Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards [73.44333771806282]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models.<n>We propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision.<n>CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors.
  arXiv  Detail & Related papers  (2026-05-14T08:22:21Z)
• $\ abla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space [71.23672814629448]
  $nabla$-Reasoner is an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop.<n>$nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark.
  arXiv  Detail & Related papers  (2026-03-05T08:42:54Z)
• Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning [59.76691952347156]
  Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs)<n>Most existing RL approaches rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions.<n>We propose Verifiable Prefix Policy Optimization (VPPO), which uses PRMs only to localize the first error during RL.
  arXiv  Detail & Related papers  (2026-01-26T21:38:20Z)
• Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization [13.475938754147625]
  Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks.<n>Agentic Reinforcement Learning (Agentic RL) optimize such models over full tool-interaction trajectories.<n>Two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence.<n>We propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO).
  arXiv  Detail & Related papers  (2025-12-08T11:59:25Z)
• The Peril of Preference: Why GRPO fails on Ordinal Rewards [0.8937905773981699]
  We introduce Correctness Relative Policy Optimization (CoRPO), a new formulation that solves this flaw.<n>CoRPO uses an adaptive baseline that enforces a minimum quality threshold, ensuring failed solutions are never positively reinforced.<n>We empirically validate CoRPO on a code verification task, where it demonstrates more stable convergence and better out-of-domain generalization.
  arXiv  Detail & Related papers  (2025-11-06T15:12:50Z)
• Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs [57.10533368622962]
  Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance.<n>This study introduces CorrectBench, a benchmark developed to evaluate the effectiveness of self-correction strategies.<n>Our findings reveal that: 1) Self-correction methods can improve accuracy, especially for complex reasoning tasks; 2) Mixing different self-correction strategies yields further improvements, though it reduces efficiency; and 3) Reasoning LLMs (e.g., DeepSeek-R1) have limited optimization under additional self-correction methods and have high time costs.
  arXiv  Detail & Related papers  (2025-10-17T02:40:19Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Accelerating RL for LLM Reasoning with Optimal Advantage Regression [52.0792918455501]
  We propose a novel two-stage policy optimization framework that directly approximates the optimal advantage function.<n>$A$*-PO achieves competitive performance across a wide range of mathematical reasoning benchmarks.<n>It reduces training time by up to 2$times$ and peak memory usage by over 30% compared to PPO, GRPO, and REBEL.
  arXiv  Detail & Related papers  (2025-05-27T03:58:50Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)

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.