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

• URL: http://arxiv.org/abs/2608.02110v1
• Date: Mon, 03 Aug 2026 12:09:50 GMT
• Title: IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations
• Abstract summary: IACM-RL is a comprehensive framework for robust tool invocation.<n>We introduce the DynamicIntent pipeline, synthesizing trajectories across 13 fine-grained fluctuation scenarios.<n>Second, IACM-RL deploys a BeliefState-based Self-Generated Context Manager.
• Score: 86.93902234336393
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories [36.7302669545557]
  Real-world applications provide no pre-defined tasks or verifiers, no faithful simulators, and limited budget for large-scale environment interaction.<n>We propose textbfAgentBrew, an offline training framework that learns effective tool-use policies from a single batch of raw interaction trajectories.<n>AgentBrew improves Qwen3-32B by +8.7 Acc / +9.7 Score on average, surpassing Qwen3-235B (+2.3 / +4.4) and outperforming rejection sampling.
  arXiv  Detail & Related papers  (2026-09-05T03:04:23Z)
• StructRL: Structured Action-Space Exploration for Flow-Based VLAs [81.43458629514139]
  Flow-based Vision-Language-Action models are now widely used for continuous robotic manipulation.<n>Online reinforcement learning is emerging as a key technique for adapting them to new tasks.<n>We show that effective robot exploration calls for structured noise: temporally smooth and scaled differently across action groups.
  arXiv  Detail & Related papers  (2026-08-15T09:31:29Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy [52.106797722292896]
  We present DCDP, a Dynamic Closed-Loop Diffusion Policy framework that integrates chunk-based action generation with real-time correction.<n>In dynamic PushT simulations, DCDP improves adaptability by 19% without retraining while requiring only 5% additional computation.
  arXiv  Detail & Related papers  (2026-03-02T15:04:18Z)
• LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks [4.6880826836662814]
  We introduce textbfLOGIGEN, a logic-driven framework that synthesizes verifiable training data.<n>On $2$-Bench, LOGIGEN-32B(RL) achieves a textbf79.5% success rate, substantially outperforming the base model.
  arXiv  Detail & Related papers  (2026-02-28T08:35:30Z)
• Mind the Gap: Learning Implicit Impedance in Visuomotor Policies via Intent-Execution Mismatch [7.078279704479455]
  We propose a Dual-State Conditioning framework that shifts the learning objective to "Intent Cloning" (master command)<n>By predicting the master intent, our policy learns to generate a "virtual equilibrium point", effectively realizing implicit impedance control.<n>This presents a minimalist behavior cloning framework for low-cost hardware, enabling force perception and dynamic compensation without relying on explicit force sensing.
  arXiv  Detail & Related papers  (2026-02-09T15:18:12Z)
• Internalizing LLM Reasoning via Discovery and Replay of Latent Actions [4.830503861275364]
  Internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute.<n>We propose STIR (Self-Distilled Tools for Internal Reasoning), a framework that reformulates reasoning enhancement as a dynamic latent trajectory control problem.
  arXiv  Detail & Related papers  (2026-02-04T08:44:57Z)
• V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks [6.820118518027692]
  V-CAGE is a closed-loop framework for generating semantically aligned manipulation datasets at scale.<n>We propose a context-aware instantiation mechanism that enforces geometric consistency during scene synthesis.<n>We also employ a hierarchical instruction decomposition module to bridge the gap between abstract intent and low-level control.
  arXiv  Detail & Related papers  (2026-01-21T16:41:51Z)
• BINDER: Instantly Adaptive Mobile Manipulation with Open-Vocabulary Commands [22.562483208861078]
  BINDER is a dual process framework that decouples strategic planning from continuous environment monitoring.<n>The two modules play complementary roles: the DRM performs strategic planning with structured 3D scene updates and guides what the IRM attends to.<n>BINDER achieves substantially higher success and efficiency than SoTA baselines, demonstrating its effectiveness for real world deployment.
  arXiv  Detail & Related papers  (2025-11-27T12:03:31Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.