paper-with-me

홈 › Papers

SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL

2026-09-24 · Yan Zhan, Shaobo Liu, Qiunan Liu, Yuanjun Shi, Siqi Xu, WeiYi Hou, Xiang Xu, Zekang Li, Weizhou Pan, Jiahong Yan hf

Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries. This output heterogeneity presents a structural failure mode in standard on-policy Reinforcement Learning (RL): algorithms like GRPO indiscriminately broadcast a homogeneous trajectory-level scalar advantage to all tokens. Consequently, gradient noise from summary generation leaks into tool-decision tokens, causing cross-segment credit misattribution and brittle optimization. In this work, we propose SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA). To enable scalable exploration without costly real APIs and stable training, we first construct the Schema-Guided LLM Simulator (SGLS) as foundational training infrastructure. Building on this, SLCA decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states. Supported by Hierarchical Rewards (HierR), SLCA routes execution advantages to tool tokens and preference advantages to summary tokens, eliminating advantage contamination (the dominant cross-segment credit misattribution channel) within each policy update. On a 7B backbone, SLCA-GRPO accelerates convergence and outperforms standard GRPO, ToolPO, and RLTR by +2.53 pp on in-domain evaluation, +1.36 pp on the Berkeley Function-Calling Leaderboard (BFCL), and +9.15 pp on τ^2-Bench under the same training budgets, achieving higher accuracy with reduced tool redundancy and costs.

📄 PDF Abstract BibTeX arXiv:2609.29050

Code (2)

SLCA-GRPO/SLCA-GRPO ★ 1
Tavish9/awesome-daily-AI-arxiv ★ 121

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation

2026-06-02 · Hyunwoong Kim, Seongeun Lee, Hannah Yun, Junhyun Park 외 arxiv

Group Relative Policy Optimization (GRPO) and its variants, originally developed for Large Language Models (LLMs), have recently been applied to Multimodal LLMs and produced strong results. However, their coarse-grained …

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation

2026-05-12 · Sijia Li, Yuchen Huang, Zifan Liu, Yanping Li 외 arxiv

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment i…

Reinforcement LearningMathematical Reasoning

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

2026-06-30 · Yuanda Xu, Zhengze Zhou, Hejian Sang, Xiaomin Li 외 hf

Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uni…

Reinforcement Learning

MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms

2021-04-06 · Kai Middlebrook, Shyam Sudhakaran, David Guy Brizan

In this work, we aim to improve the expressive capacity of waveform-based discriminative music networks by modeling both sequential (temporal) and hierarchical information in an efficient end-to-end architecture. We pres…

Music ModelingMusic Tagging

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

2026-06-17 · Yingyu Shan, Yuhang Guo, Zihao Cheng, Zeming Liu 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradien…

Reinforcement LearningKnowledge Distillation