PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning

arXiv:2605.09287 · cs.AI · Submitted 2026-05-10 · Read on arXiv

cs.AI

Submitted: 2026-05-10

Updated: 2026-10-05

Comments: NeurIPS 2026

Code: https://github.com/novdream/PiCA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Credit assignment — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• ZeroSearch: Incentivize the Search Capability of LLMs without Searching
• WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
• MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization
• WebDancer: Towards Autonomous Information Seeking Agency
• TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
• Corrective Retrieval Augmented Generation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems