{"ID":5675993,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-04T20:51:25.697068714Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01465","arxiv_id":"2607.01465","title":"Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows","abstract":"Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means hitting the right endpoint with the right nested arguments in the right order -- this objective mismatch shows up as silent failures: dropped required fields, hallucinated tools, or early stops after a single read. We ask whether Reinforcement Learning with Verifiable Rewards (RLVR), applied directly in the target environment, closes the gap. As a proof of concept we build a suite of five synthetic environments emulating the Jira REST v3 and Confluence v2 APIs at schema fidelity; rewards are computed entirely from the tool-call trace, with no live API, no learned judge, and no human label in the loop. Scoring prompted Qwen3-1.7B and Qwen3.5-4B on the same checkers that drive GRPO training, we find that on the four scenarios whose rewards are non-degenerate the RL-trained policy lifts average reward from a 4B-baseline range of 0.35--0.92 to 0.95--1.00, with the largest single gain on Confluence page creation ($0.35 \\rightarrow 1.00$). We position this as a preliminary step toward outcome-optimised small models for niche enterprise APIs, and foreground two limitations a workshop reader should weigh: hand-crafting verifiable rewards does not scale beyond the handful of endpoints reported here, and one of our five scenarios (ticket-transition) has a saturating reward shape that the prompted 4B already maxes out.","short_abstract":"Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means hitting the right endpoint with the right nested arguments in the right order -- this objective mismatch shows up as silent failures: dropped required fields, hallucin...","url_abs":"https://arxiv.org/abs/2607.01465","url_pdf":"https://arxiv.org/pdf/2607.01465v1","authors":"[\"Karthikeya Aditya Vissa\",\"Sankalp Mane\",\"Ananya Mantravadi\",\"Harshit Rajgarhia\",\"Abhishek Mukherji\"]","published":"2026-07-01T20:55:07Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Language Model\"]","has_code":false}