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

arXiv:2604.17475v1 Announce Type: cross 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

• Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
• Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs
• Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision
• RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
• S-GRPO: Unified Post-Training for Large Vision-Language Models

Source: arXiv cs.CL | 2026-04-21