Multi-Agent Protocol Distillation (MAPD), a joint distillation and RL framework uses a structured, style-normalized protocol as an intermediate representation that generalizes robustly across diverse proprietary teachers while effectively mitigating the student policy from style drift and verbosity degeneration.
Abstract
Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision. Knowledge distillation can supply denser guidance, and advanced proprietary models with their strong reasoning capabilities are promising teachers. While distilling from proprietary models can densify this supervisory signal, conventional logit-matching is precluded by hidden logits and mismatched tokenizers, whereas raw natural language trajectory imitation transfers superficial stylistic artifacts rather than core reasoning competence. To address the heterogeneous distillation problem and bridge the distribution gap, we propose Multi-Agent Protocol Distillation (MAPD), a joint distillation and RL framework uses a structured, style-normalized protocol as an intermediate representation. An offline multi-agent system (MAS) decomposes each query, retrieves supporting evidence, repairs failed searches, and converts the resulting exploration trace into a JSON protocol containing the task type, reasoning plan, and extractive grounding facts. During training, the protocol is provided only to a privileged branch of the student policy, whose token distributions furnish a dense distillation signal alongside the sparse RL objective. Extensive evaluations across seven QA benchmarks demonstrate that MAPD consistently outperforms competitive distillation and RL, achieving average success rates of 39.4\% on Qwen3-1.7B and 44.4\% on Qwen3-4B. Crucially, the framework generalizes robustly across diverse proprietary teachers while effectively mitigating the student policy from style drift and verbosity degeneration.
Evidence Anchors are constructed, which are concise, step-level evidence snippets extracted from the web, as privileged information that captures key reasoning steps without revealing the entire answer path, and SSPO, which converts teacher-student disagreement into step-level advantage weights within GRPO, applied exclusively to incorrect trajectories.
Haoze Wu, Chuqiao Kuang, Tianyi Zhuang et al.· 0 citations
Autonomous multi-modal agents are increasingly important in real-world applications due to their ability to reason about complex environments and orchestrate tool use. However, deploying multi-modal large language models (MLLMs) for tool use is often constrained by computational cost and inference latency, creating a pressing need for compact models that retain strong agentic capabilities. Training small multi-modal agents remains difficult: limited backbone capacity weakens multi-step reasoning, reward signals for tool use are often sparse and brittle, and naive distillation can fail to transfer the procedural knowledge required for reliable tool invocation and grounding. In this paper, we propose a two-stage self-evolutionary knowledge distillation framework that equips small MLLMs with robust and adaptive tool-use behaviors. Our method combines (i) mutual information-guided trajectory distillation, which selectively transfers high-utility segments of agentic trajectories from a larger teacher, and (ii) reinforcement-driven policy evolution with iterative teacher feedback. To stabilize learning and prevent semantic collapse, we introduce weighted semantic objectives and iteratively expand competence through error-driven optimization, hybrid experience replay, and group-relative policy refinement with multi-dimensional rewards over answer correctness, invocation validity, and tool effectiveness. Integrated with interactive tool modules, our approach enables small models to achieve strong performance across diverse tool-use benchmarks. Comprehensive experiments show consistent improvements over single-pass distillation and RL baselines. Overall, our framework provides a practical path to deploy efficient multi-modal agents without sacrificing tool-use reliability.
Lei Shen, Chengyu Wang, Yuanjie Lyu et al.· Proceedings of the 32nd ACM...· 0 citations
This literature review synthesizes 57 peer-reviewed and openly archived contributions published since 2019 into a thematic taxonomy spanning value-decomposition algorithms, trust-region and sequence-model policy methods, and LLM-based agentic frameworks, and discusses implications for applied decision analytics.
B. Rai, Milena Popović· Applied Decision Analytics· 0 citations
Multi-agent reasoning (MAR) improves reasoning reliability through iterative solution exchange and refinement. Existing adaptive MAR methods typically learn routing decisions from query-level labels or trajectory-level returns, but such coarse supervision cannot accurately estimate the state-conditioned utility of individual operators in multi-step collaboration. We propose TreeCredit, a shared-prefix credit assignment framework for efficient adaptive MAR. Its core insight is to estimate operator utility through state-matched downstream comparisons, rather than directly attributing trajectory-level outcomes to preceding decisions. TreeCredit constructs shared-prefix collaboration trees by expanding candidate operators from the same intermediate state and assigns each state--operator pair a correctness-prioritized suffix credit based on the terminal correctness and cumulative additional cost of its complete continuation. These structured credits are converted into state-local operator preferences to train a lightweight pairwise state router, which dynamically selects the next admissible operator during inference. Experiments on six reasoning benchmarks show that TreeCredit modestly improves accuracy while substantially reducing inference cost, achieving a better accuracy--cost trade-off than representative MAR methods.
Yi-Qing Liu, Zi-Hao Wang, Han-Tao Yao et al.· 2 citations
The role of a frozen off-the-shelf instruct model as the teacher in on-policy distillation is investigated, and a key insight is revealed: the teacher reshapes the student's policy distribution so that subsequent RL converges to a superior solution that RL alone cannot reach.
Qi Ye, Zhi-Yuan Gu, Jingjie Xia et al.· 0 citations
This work introduces multi-agent from-scratch evaluation benchmark, MSEval, evaluating multi-agent coding on real-world tasks, and establishes a rigorous, reproducible standard for measuring how multi-agent teams actually build software.
Yanyu Ren, Yu Bai, Xizheng Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
