DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making

• URL: http://arxiv.org/abs/2604.23557v1
• Date: Sun, 26 Apr 2026 06:34:21 GMT
• Title: DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making
• Abstract summary: Decision Language Model (DLM) formulates multi-agent decision making as a dialogue-style sequence prediction problem.<n>Experiments show that a unified DLM outperforms strong offline MARL baselines and LLM-based conversational decision-making methods.
• Score: 6.405773239987913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that limit generalization. In contrast, large language models (LLMs) offer a flexible modeling interface that can naturally accommodate heterogeneous observations and actions. Motivated by this, we propose the Decision Language Model (DLM), which formulates multi-agent decision making as a dialogue-style sequence prediction problem under the centralized training with decentralized execution paradigm. DLM is trained in two stages: a supervised fine-tuning phase, which leverages dialogue-style datasets for centralized training with inter-agent context and generates executable actions from offline trajectories, followed by a group relative policy optimization phase to enhance robustness to out-of-distribution actions through lightweight reward functions. Experiments on multiple benchmarks show that a unified DLM outperforms strong offline MARL baselines and LLM-based conversational decision-making methods, while demonstrating strong zero-shot generalization to unseen scenarios across tasks.

Related papers

• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization [14.534152704620261]
  Industrial recommender systems increasingly adopt multi-scenario learning (MSL) and multi-task learning (MTL) to handle diverse user interactions and contexts.<n>Existing approaches suffer from two critical drawbacks: (1) underutilization of large-scale model parameters due to limited interaction with complex feature modules, and (2) difficulty in jointly modeling scenario and task information in a unified framework.<n>We propose a unified textbfMulti-textbfDistribution textbfL MSL framework, inspired by the "prompting" paradigm in large language models (LLMs)
  arXiv  Detail & Related papers  (2026-02-07T12:34:27Z)
• Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition [51.68340973140949]
  Multimodal Named Entity Recognition (GMNER) aims to extract text-based entities, assign them semantic categories, and ground them to corresponding visual regions.<n> MLLMs exhibit $textbfmodality bias$, including visual bias and textual bias, which stems from their tendency to take unimodal shortcuts.<n>We propose Modality-aware Consistency Reasoning ($bfMCR$), which enforces structured cross-modal reasoning.
  arXiv  Detail & Related papers  (2026-02-04T12:12:49Z)
• DecisionLLM: Large Language Models for Long Sequence Decision Exploration [26.033533195580933]
  Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning and planning tasks.<n>This work investigates the application of LLMs to offline decision making tasks.<n>By learning to align trajectory data with natural language task descriptions, our model can autoregressively predict future decisions.
  arXiv  Detail & Related papers  (2026-01-15T07:42:02Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)
• MLLM-CL: Continual Learning for Multimodal Large Language Models [39.19456474036905]
  We introduce MLLM-CL, a novel benchmark encompassing domain and ability continual learning.<n>We propose preventing catastrophic interference through parameter isolation and an MLLM-based routing mechanism.<n>Our approach can integrate domain-specific knowledge and functional abilities with minimal forgetting, significantly outperforming existing methods.
  arXiv  Detail & Related papers  (2025-06-05T17:58:13Z)
• Offline Multi-agent Reinforcement Learning via Score Decomposition [51.23590397383217]
  offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts.<n>This work is the first work to explicitly address the distributional gap between offline and online MARL.
  arXiv  Detail & Related papers  (2025-05-09T11:42:31Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making [85.24399869971236]
  We aim to evaluate Large Language Models (LLMs) for embodied decision making.<n>Existing evaluations tend to rely solely on a final success rate.<n>We propose a generalized interface (Embodied Agent Interface) that supports the formalization of various types of tasks.
  arXiv  Detail & Related papers  (2024-10-09T17:59:00Z)
• Understanding Alignment in Multimodal LLMs: A Comprehensive Study [46.33812471516309]
  We analyze each aspect of preference alignment in Multimodal Large Language Models (MLLMs) We show that combining offline and online methods can improve the performance of the model in certain scenarios. We introduce a novel way of creating multimodal preference data called Bias-Driven Hallucination Sampling (BDHS)
  arXiv  Detail & Related papers  (2024-07-02T17:55:03Z)
• O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models [16.91329676173649]
  Offline Data-driven Discovery and Distillation (O3D) is proposed to improve large language models (LLMs) O3D automatically discovers reusable skills and distills generalizable knowledge across multiple tasks based on offline interaction data. Empirical results under two interactive decision-making benchmarks (ALFWorld and WebShop) verify that O3D can notably enhance the decision-making capabilities of LLMs.
  arXiv  Detail & Related papers  (2023-10-22T20:28:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.