# BACAM: Behavior-Aware Continual Agent Merging for Multi-Turn Interaction

arXiv: https://arxiv.org/abs/2610.04966 · HTML: https://mlsanity.com/paper/2610.04966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 34 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 30 of 31)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [AdaMerging: Adaptive Model Merging for Multi-Task Learning](https://mlsanity.com/paper/2310.02575/) (2023)
- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [Task Singular Vectors: Reducing Task Interference in Model Merging](https://mlsanity.com/paper/2412.00081/) (2024)
- [Agent Lightning: Train ANY AI Agents with Reinforcement Learning](https://mlsanity.com/paper/2508.03680/) (2025)
- [No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces](https://mlsanity.com/paper/2502.04959/) (2025)
- [Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors](https://mlsanity.com/paper/2503.08099/) (2025)
- [Scaling Agent Learning via Experience Synthesis](https://mlsanity.com/paper/2511.03773/) (2025)
- [Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging](https://mlsanity.com/paper/2501.09522/) (2025)
- [GEM: A Gym for Agentic LLMs](https://mlsanity.com/paper/2510.01051/) (2025)
- [Behavior Knowledge Merge in Reinforced Agentic Models](https://mlsanity.com/paper/2601.13572/) (2026)
- [Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering](https://mlsanity.com/paper/2502.04469/) (2025)
- [Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity](https://mlsanity.com/paper/2509.21413/) (2025)
- [Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking](https://mlsanity.com/paper/2509.25712/) (2025)
- [ARM: Role-Conditioned Neuron Transplantation for Training-Free Generalist LLM Agent Merging](https://mlsanity.com/paper/2601.07309/) (2026)

## Abstract (arXiv)

Model merging offers a way to integrate the capabilities of specialized experts, but existing agent merging methods typically require all of them to be available at once. We study continual agent merging, which integrates incoming experts sequentially without retaining previously merged experts. Yet merging in parameter space or feature subspaces does not ensure that the merged model acquires an incoming expert's behavior on interaction trajectories. Moreover, updates toward a new expert can disrupt the merged model's previously integrated interactive behavior. Therefore, we propose Behavior-Aware Continual Agent Merging (BACAM), which learns parameter-wise merging gates from candidate-generated trajectories using expert-guided behavioral supervision. Task-level stability-plasticity control and tensor-level conflict-aware update budgets limit interference with existing capabilities while allowing new ones to be acquired. The learned gates are folded into the model weights without additional inference-time parameters. Across four interactive tasks - web shopping, tool use, information retrieval, and embodied interaction - BACAM achieves an average success rate of 62.82%, exceeding the strongest evaluated merging baseline by 21.69 percentage points. Our code is publicly available at https://github.com/shuaitongli/BACAM.