arXiv Machine Learning
CASI: Credit Assignment via Set Intervention for Agentic Retrieval
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 30
Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment o...
arXiv AI
5d ago
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
The paper introduces ProAS, a Progress‑Aware Advantage Shaping framework designed to improve critic‑free reinforcement learning for large language model agents. ProAS uses a dynamic Agentic Reference Graph to provide fine‑grained credit assignment through Masking Unreasonable Incentives and Asymmetric Penalty Redistribution, avoiding the uniform advantage broadcast that can reinforce invalid actions. Experiments on Qwen2.5‑1.5B‑Instruct and Qwen2.5‑7B‑Instruct show that ProAS raises baseline success rates to 91.9% and 94.3% on ALFWorld and 66.7% and 70.8% on WebShop, while speeding up training convergence up to 2.44× and remaining robust to imperfect reference graphs.
Hugging Face Trending Papers
6d ago
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fundamental uniform cr...
arXiv Machine Learning
5d ago
Contextual Credit Policy Optimization
arXiv:2610.19103v1 Announce Type: new Abstract: Group-based reinforcement learning enables large language model agents to learn from sparse outcome rewards in long-horizon tasks. Recent methods deriv...
arXiv AI
Jul 28
Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
arXiv:2607. 22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group.
arXiv AI
Aug 26
Contrastive Branch Policy Optimization
Contrastive Branch Policy Optimization (CBPO) is a reinforcement learning method that separates the allocation of a fixed rollout budget from the translation of branch outcomes into token-level credit. It uses generation entropy to screen branch positions, path- and node-level decay to distribute the budget, and Contrastive Branch Value (CBV) to estimate local decision sensitivity without changing reward signs. CBPO partitions trajectories into non-overlapping credit segments, preventing duplicated gradients and enabling fine-grained credit assignment using only outcome rewards.