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

Ashutosh Bajpai, Tamal Majumder, Akshay Nambi, Tanmoy Chakraborty


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.
Anthology ID:
2026.findings-acl.538
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11070–11093
Language:
URL:
https://aclanthology.org/2026.findings-acl.538/
DOI:
Bibkey:
Cite (ACL):
Ashutosh Bajpai, Tamal Majumder, Akshay Nambi, and Tanmoy Chakraborty. 2026. Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception. In Findings of the Association for Computational Linguistics: ACL 2026, pages 11070–11093, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception (Bajpai et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.538.pdf
Checklist:
 2026.findings-acl.538.checklist.pdf