Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models

• URL: http://arxiv.org/abs/2604.08545v1
• Date: Thu, 09 Apr 2026 17:59:57 GMT
• Title: Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
• Abstract summary: HDPO is a framework that reframes tool efficiency from a competing scalar objective to a strictly conditional one.<n>Our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.
• Score: 27.250148827297604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advent of agentic multimodal models has empowered systems to actively interact with external environments. However, current agents suffer from a profound meta-cognitive deficit: they struggle to arbitrate between leveraging internal knowledge and querying external utilities. Consequently, they frequently fall prey to blind tool invocation, resorting to reflexive tool execution even when queries are resolvable from the raw visual context. This pathological behavior precipitates severe latency bottlenecks and injects extraneous noise that derails sound reasoning. Existing reinforcement learning protocols attempt to mitigate this via a scalarized reward that penalizes tool usage. Yet, this coupled formulation creates an irreconcilable optimization dilemma: an aggressive penalty suppresses essential tool use, whereas a mild penalty is entirely subsumed by the variance of the accuracy reward during advantage normalization, rendering it impotent against tool overuse. To transcend this bottleneck, we propose HDPO, a framework that reframes tool efficiency from a competing scalar objective to a strictly conditional one. By eschewing reward scalarization, HDPO maintains two orthogonal optimization channels: an accuracy channel that maximizes task correctness, and an efficiency channel that enforces execution economy exclusively within accurate trajectories via conditional advantage estimation. This decoupled architecture naturally induces a cognitive curriculum-compelling the agent to first master task resolution before refining its self-reliance. Extensive evaluations demonstrate that our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.

Related papers

• Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools [65.7098588070281]
  We propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability.<n>BEE incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism.<n>BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks.
  arXiv  Detail & Related papers  (2026-07-13T05:32:00Z)
• Tool-Adaptive LLM Reranker [6.360159778061184]
  TALRanker is a novel framework that formalizes pointwise relevance scoring as an agentic Markov decision process.<n>It achieves state-of-the-art performance across standard and reasoning-intensive retrieval benchmarks.
  arXiv  Detail & Related papers  (2026-07-12T04:04:59Z)
• TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents [54.08846865906602]
  We characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents.<n>We propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools.
  arXiv  Detail & Related papers  (2026-06-04T07:15:43Z)
• Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception [18.565166776233223]
  Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration.<n>We propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA)<n>SPECTRA bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs.
  arXiv  Detail & Related papers  (2026-04-19T15:06:30Z)
• AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents [50.481033105867205]
  We introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories.<n>The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement.<n>It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity.
  arXiv  Detail & Related papers  (2026-03-15T16:13:58Z)
• U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation [9.680511155102623]
  We propose Contrastive AttenuatioN (U-CAN), a precision unlearning framework that operates on low-rank adapters.<n>U-CAN quantifies risk by contrasting activations and focuses on neurons with asymmetric responses that are highly sensitive to the forgetting set but suppressed on the retention set.<n>Unlike binary pruning, which often fragments network structure, U-CAN develop adaptive soft attenuation with a differentiable decay function.
  arXiv  Detail & Related papers  (2026-02-26T07:36:11Z)
• ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation [72.78362530982109]
  ARTIS, Agentic Risk-Aware Test-Time Scaling via Iterative Simulation, is a framework that decouples exploration from commitment.<n>We show that naive LLM-based simulators struggle to capture rare but high-impact failure modes.<n>We introduce a risk-aware tool simulator that emphasizes fidelity on failure-inducing actions.
  arXiv  Detail & Related papers  (2026-02-02T06:33:22Z)
• Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning [58.432996881401415]
  Recent work augments large language models (LLMs) with external tools to enable agentic reasoning.<n>We propose Sponge Tool Attack (STA), which disrupts agentic reasoning solely by rewriting the input prompt.<n>STA generates benign-looking prompt rewrites from the original one with high semantic fidelity.
  arXiv  Detail & Related papers  (2026-01-24T19:36:51Z)
• CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning [4.765206163164323]
  CLEANER exploits intrinsic self-correction capabilities to eliminate error-contaminated context during data collection.<n>Similarity-Aware Adaptive Rollback mechanism autonomously constructs clean, purified trajectories.<n>Results show average accuracy gains of 6%, 3%, and 5% over baselines.
  arXiv  Detail & Related papers  (2026-01-21T16:14:30Z)
• Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models [29.56923793047279]
  We introduce Dynamic Outlier Truncation (DOT), a training-time intervention that selectively suppresses redundant tokens.<n>DOT targets only the extreme tail of response lengths within fully correct rollout groups while preserving long-horizon reasoning capabilities.<n>Our method reduces inference token usage by 78% while simultaneously increasing accuracy compared to the initial policy.
  arXiv  Detail & Related papers  (2026-01-07T14:31:07Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models [13.32858759983739]
  Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating text inconsistent with visual inputs.<n>Existing inference-time interventions to mitigate this issue present a challenging trade-off.<n>We present Residual-Update Directed DEcoding Regulation (RUDDER), a framework that steers LVLMs towards visually-grounded generation.
  arXiv  Detail & Related papers  (2025-11-13T13:29:38Z)
• OFMU: Optimization-Driven Framework for Machine Unlearning [5.100622189286672]
  Large language models increasingly require the ability to unlearn specific knowledge, such as user requests, copyrighted materials, or outdated information.<n>We propose OFMU, a penalty-based bi-level optimization framework that explicitly prioritizes forgetting while preserving retention.<n>We show that OFMU consistently outperforms existing unlearning methods in both efficacy and retained utility.
  arXiv  Detail & Related papers  (2025-09-26T15:31:32Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Acting Less is Reasoning More! Teaching Model to Act Efficiently [87.28134636548705]
  Tool-integrated reasoning augments large language models with the ability to invoke external tools to solve tasks.<n>Current approaches typically optimize only for final correctness without considering the efficiency or necessity of external tool use.<n>We propose a framework that encourages models to produce accurate answers with minimal tool calls.<n>Our approach reduces tool calls by up to 68.3% and improves tool productivity by up to 215.4%, while maintaining comparable answer accuracy.
  arXiv  Detail & Related papers  (2025-04-21T05:40:05Z)

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.