IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations

2026-08-03

AI Summary

This work addresses the challenges of intent drift and infinite API loops in long-horizon tool-augmented interactions, where dynamic user intentions frequently shift. To tackle these issues, the authors propose the IACM-RL framework, which leverages a newly constructed DynamicIntent dataset and introduces a belief-state-based context manager equipped with a structured staleness tagging mechanism to identify outdated constraints. The framework further incorporates hierarchical intent-aware rewards, multiple auxiliary losses, and reinforcement learning to enable autonomous, intent-sensitive context updates. Experimental results demonstrate that IACM-RL significantly outperforms existing baselines on DynamicIntent, BFCL-V3, and 𝜏²-Bench, effectively mitigating infinite loops and stale context problems while enhancing out-of-domain generalization.

Abstract

Executing long-horizon tool invocations in real-world environments is severely challenged by dynamic user intent noise. Existing methods attempt robustness via implicit history scanning or text compression, yet predominantly assume perfect instructions in simplistic scenarios. Inevitably, under fluctuating contexts, obsolete constraints dilute model attention, triggering catastrophic intent deviation and infinite API loops. To resolve this, we propose IACM-RL, a comprehensive framework for robust tool invocation. First, we introduce the DynamicIntent pipeline, synthesizing trajectories across 13 fine-grained fluctuation scenarios, paired with a five-dimensional diagnostic metric suite. Second, IACM-RL deploys a BeliefState-based Self-Generated Context Manager that proactively tracks shifting goals and isolates overwritten parameters using structural stale flags. To autonomously internalize this state-tracking capability, we optimize the policy using a hierarchical intent-driven reward alongside three auxiliary losses (action calibration, CM extraction, and state distillation). Experiments on DynamicIntent, BFCL-V3, and $\mathrmτ^2$-Bench demonstrate that IACM-RL significantly outperforms baselines, reducing infinite loops and stale context errors while enhancing out-of-domain generalization.

Problem

• dynamic intent fluctuations
• tool invocation
• intent deviation
• infinite API loops
• stale context

Innovation

• Intent-Aware Context Management
• Reinforcement Learning
• Dynamic Intent Fluctuations
• BeliefState Tracking
• Tool Invocation