2606.11119v1 Jun 09, 2026 cs.LG

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Saiyong Yang
Saiyong Yang
Citations: 104
h-index: 5
Xingzhong Xu
Xingzhong Xu
Citations: 270
h-index: 2
Weijie Liu
Weijie Liu
Citations: 94
h-index: 4
Yun Qu
Yun Qu
Tsinghua University
Citations: 308
h-index: 11
Yixiu Mao
Yixiu Mao
Citations: 236
h-index: 9
Heming Zou
Heming Zou
Citations: 79
h-index: 6
Xiangyang Ji
Xiangyang Ji
Citations: 232
h-index: 10
Yuhang Jiang
Yuhang Jiang
Citations: 269
h-index: 10
Lizhou Cai
Lizhou Cai
Citations: 1
h-index: 1
Qi Wang
Qi Wang
Citations: 19
h-index: 2
Runsi Peng
Runsi Peng
Citations: 16
h-index: 1
Kaixuan Yang
Kaixuan Yang
Citations: 0
h-index: 0

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive policy optimization is often limited by insufficient reward contrast, arising when overly simple or complex prompts generate low-variance feedback and when outcome-only rewards assign the same terminal assessment to every decision in a multi-turn rollout. Past efforts have focused on allocating available rollout resources to promising prompts, yet they only leverage sample informativeness at the prompt level and neglect variation in prefix-level informativeness across turns within the same rollout. This work targets multi-turn agentic RL by modeling each ReAct-style thought-action-observation turn as a semantically distinct node, allowing budget allocation to extend from prompt roots to turn-level prefixes with further continuations, which naturally forms tree-structured rollouts. We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework that enhances reward contrast within a fixed sampling budget. Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards. A shared generalizable predictor estimates conditional success probability at these anchors from prefix histories to guide this allocation. The resulting adaptive tree structure enriches outcome-only feedback and amplifies the policy-update signal. Empirically, TRACE achieves competitive performance and efficiency gains on typical agentic benchmarks, e.g., improving Qwen3-14B Multi-Hop QA average accuracy by 2.8 points over competitive baselines at equal sampling cost.

1 Citations
0 Influential
5.5 Altmetric
28.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!