HiDiffTIR is proposed, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR that consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-integrated LLM agents.
Abstract
Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has become the dominant paradigm for enabling this capability. However, existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally, ignoring the varying difficulty and learning value across trajectories and reasoning steps. This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns. To address this limitation, we propose HiDiffTIR, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR. HiDiffTIR performs difficulty-aware credit assignment at both trajectory and turn levels, enabling the policy to focus on more informative trajectories and harder reasoning steps. Notably, this fine-grained optimization is achieved without additional supervision, relying solely on group-level statistics derived from standard RL rollouts. Extensive experiments on three tool-using benchmarks demonstrate that HiDiffTIR consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-integrated LLM agents.
Group Planning-aware Policy Optimization (PlanPO) is proposed, a simple yet effective RL method for learning generalizable planning abilities beyond task-specific high-quality behavior patterns that enables agents to actively learn generalizable and deliberate behaviors spanning interaction planning and textual generation from high-quality rollouts, without degenerating into vanilla length minimization.
D. Liang, Liyuan He, Xuan Feng et al.· 0 citations
Recent methods using Reinforcement Learning (RL) have improved Tool-Integrated Reasoning (TIR) by training large language models to learn end-to-end policies for multi-step tool usage, enabling them to solve complex tasks more effectively. Despite these advances, existing methods often suffer from overthinking at both the action and reasoning levels: models tend to invoke tools redundantly and generate excessively long reasoning trajectories, resulting in high computational cost. To address this, in this paper, we propose LightTIR, a dual-penalty reward framework, to achieve efficient TIR. For action efficiency, LightTIR estimates the marginal utility of each tool call through prefix-aligned counterfactual trajectories, encouraging calls that contribute meaningful information while penalizing low-utility or redundant invocations. For reasoning efficiency, LightTIR introduces a length-aware regularization term, adaptively penalizing intermediate reasoning steps that exceed the minimal effective trajectory required for correct prediction. Extensive experiments demonstrate that LightTIR can reduce redundancy and trajectory expansion while maintaining answer correctness, achieving more efficient RL-based TIR. Code is available at https://github.com/ekventitas/LightTIR.
Yichen Xiao, Siyu Gong, Linan Yue· Proceedings of the 32nd ACM...· 0 citations
Across both tasks, the proposed LLM-based hierarchical framework consistently outperforms direct task-specific control and optimization, end-to-end reinforcement learning, rule-based and RL-based hierarchical coordination, and prompting-only LLM coordinators, demonstrating the value of heterogeneous-context reasoning, hierarchical execution, and continuation-aware policy learning.
Changhong He, Jinda Gao, Xinkuan Liu et al.· 0 citations
Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) and related algorithms have demonstrated strong performance with outcome-level rewards. However, these methods depend solely on the final answer, without feedback regarding which intermediate steps contribute to success or failure. As task complexity and reasoning trajectory length increase, such sparse final-answer rewards become increasingly insufficient. To address this limitation, we introduce ConsensusBench, a novel dataset designed to provide rule-based process-level signals. We posit that a correct final answer relies on a small set of intermediate conclusions throughout the reasoning process, which can be seen as a verifiable sub-outcome. We identify these sub-outcomes by filtering correct trajectories from N rollouts and clustering semantically equivalent intermediate statements. We call these clustered statements as Consensus Nodes. By integrating a rule-based process reward derived from these nodes into GRPO-style algorithms, we develop a new reinforcement learning signal named ConsensusPR. It directly reduces the reward sparsity of outcome reward across long reasoning trajectories. To facilitate systematic process-level evaluation, we introduce three metrics to our benchmark: Final Answer Accuracy (Acc), Node Coverage Rate (NCR), and Tokens per Node (TPN). Experiments across AIME 2024, AIME 2025, GSM8K, MATH-500, and our ConsensusBench demonstrate that the proposed method consistently surpasses GRPO-style approaches, highlighting the practical value of consensus nodes in guiding reasoning.
Shi-Qi Yan, Chao-Hong Tan, Qian Chen et al.· 0 citations
This work proposes Multi-Branch Policy Optimization (MBPO), a tree-based framework that constructs reasoning trees at vision-language decision boundaries, enabling sibling branches to explore diverse visual hypotheses and assigning segment-level credit through branch-relative advantages.
Shuai Lyu, Yu-Ning Gong, Rui-Ling Gao et al.· 0 citations
TurnSight is proposed, a turn-level hindsight self-distillation framework that derives supervision directly from execution-conditioned hindsight and selects reliable supervision through cross-horizon directional agreement.
Changle Qu, Sun-Hao Dai, Hengyi Cai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
