When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis
Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge independently released agents precisely because a joint model is unavailable. We build the missing comparison. Training difficulty-1 and difficulty-2 Qwen3-8B specialists on the AppWorld agent benchmark with LOOP, we merge them (TIES, RAM+) and pit the result against a jointly trai
Record details
Published: 17 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy
Retrieved: 20 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization
arXiv · 17 July 2026
Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning
arXiv cs.AI · 17 July 2026
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
arXiv cs.AI · 17 July 2026
CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approach
arXiv cs.LG · 17 July 2026
DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction
arXiv cs.AI · 17 July 2026
When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
arXiv cs.AI · 17 July 2026
How to cite this record
ethics.ai (17 July 2026), “When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis,” evidence record 11848, https://ethics.ai/record/11848 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.