Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception

• URL: http://arxiv.org/abs/2604.17475v1
• Date: Sun, 19 Apr 2026 15:06:30 GMT
• Title: Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception
• Abstract summary: 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.
• Score: 18.565166776233223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these deficits. In this work, we propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA), a supervision-free framework that bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs. SPECTRA enforces Soft Structured Multi-turn Rollouts, a topological constraint that directs agents to explicitly sequence tool derived evidence before synthesis, effectively grounding reasoning in visual observations. We employ a multi-objective reward signal that simultaneously maximizes task correctness, rollout structure, and tool utility, enabling agent to self-discover robust behaviors without human preference labels. We further introduce Tool Instrumental Utility (TIU), a novel metric to quantify tool efficacy in the absence of ground truth. Extensive evaluations across composite and out-of-distribution (MMMU-Pro) benchmarks demonstrate that SPECTRA boosts agentic trajectories, improving task accuracy by up to 5% and tool efficiency by 9%, enabling more efficient multimodal agents that learn effectively from environmental interaction alone.

Related papers

• From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents [90.3279207163486]
  EvoSOP is a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset.<n>We show that EvoSOP significantly boosts task success rates while substantially reducing the number of interaction rounds.
  arXiv  Detail & Related papers  (2026-07-08T12:09:49Z)
• PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents [57.69188221227875]
  We propose a Privileged trAce Co-Training framework for multi-turn tool-use agents.<n>The key idea is to use expert traces only as training-time optimization signals rather than rollout-time hints.<n>We show that PACT consistently improves over strong SFT- and RL-based baselines.
  arXiv  Detail & Related papers  (2026-06-15T04:46:23Z)
• ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution [49.30293260493709]
  Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools.<n>Existing methods relying on static embedding retrieval or parameter memorization struggle to align user intent with tool semantics.<n>We present Tool Omni, a unified agentic framework that enables LLMs for open-world tool use by proactive retrieval and grounded execution.
  arXiv  Detail & Related papers  (2026-04-15T12:26:10Z)
• Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models [27.250148827297604]
  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.
  arXiv  Detail & Related papers  (2026-04-09T17:59:57Z)
• AutoTool: Efficient Tool Selection for Large Language Model Agents [10.061664247482488]
  Large Language Model (LLM) agents have emerged as powerful tools for automating complex tasks by leveraging the reasoning and decision-making abilities of LLMs.<n>However, a major bottleneck lies in the high inference cost of tool selection, especially in approaches like ReAct that repeatedly invoke the LLM to determine which tool to use at each step.<n>We propose AutoTool, a novel graph-based framework that bypasses repeated LLM inference by exploiting a key empirical observation: tool usage inertia.
  arXiv  Detail & Related papers  (2025-11-18T16:41:48Z)
• Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning [68.89572566071575]
  Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools.<n>We propose Tool-Light, a framework designed to encourage LLMs to perform TIR efficiently and accurately.<n> Experimental results on 10 datasets demonstrate the effectiveness of Tool-Light.
  arXiv  Detail & Related papers  (2025-09-27T12:53:37Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• 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)
• TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use [72.32614703504122]
  Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments.<n>Standard supervised fine-tuning approach, which relies on large-scale datasets, often overlooks task-specific characteristics in tool use.<n>We propose TL-Training, a task-feature-based framework that mitigates the effects of suboptimal training data.
  arXiv  Detail & Related papers  (2024-12-20T02:21:36Z)

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.