ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling

• URL: http://arxiv.org/abs/2512.22129v1
• Date: Fri, 05 Dec 2025 12:33:11 GMT
• Title: ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling
• Abstract summary: Ad-hoc teamwork requires agents to infer the behavior of previously unseen teammates and adapt their policy accordingly.<n>We introduce Collab, a language-based framework that classifies partner types using a behavior derived from trajectory features.<n>We extend it to ReCollab, which incorporates retrieval-augmented generation (RAG) to stabilize inference with trajectories.
• Score: 2.1130419553264015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ad-hoc teamwork (AHT) requires agents to infer the behavior of previously unseen teammates and adapt their policy accordingly. Conventional approaches often rely on fixed probabilistic models or classifiers, which can be brittle under partial observability and limited interaction. Large language models (LLMs) offer a flexible alternative: by mapping short behavioral traces into high-level hypotheses, they can serve as world models over teammate behavior. We introduce \Collab, a language-based framework that classifies partner types using a behavior rubric derived from trajectory features, and extend it to \ReCollab, which incorporates retrieval-augmented generation (RAG) to stabilize inference with exemplar trajectories. In the cooperative Overcooked environment, \Collab effectively distinguishes teammate types, while \ReCollab consistently improves adaptation across layouts, achieving Pareto-optimal trade-offs between classification accuracy and episodic return. These findings demonstrate the potential of LLMs as behavioral world models for AHT and highlight the importance of retrieval grounding in challenging coordination settings.

Related papers

• Collaborative Memory Augmentation for Generative Recommendation [49.76630658239287]
  We propose textbfOMEGA, a cOllaborative MEmory augmentation framework for Generative recommendAtion.<n>We first introduce a latent context compression method that utilizes learnable query tokens to distill sequential user behavior into compact representations.<n>These compressed representations are aggregated into a collaborative memory bank, serving as an explicit repository of global behavioral patterns.
  arXiv  Detail & Related papers  (2026-08-02T15:34:43Z)
• Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning [0.0]
  We introduce an architecture that factorizes the latent state of a Dreamer-style recurrent state-space model into environment and teammate components.<n>These teammate latents condition the actor and critic, enabling the agent to imagine and adapt to diverse collaborators.
  arXiv  Detail & Related papers  (2026-05-29T14:34:50Z)
• Give Users the Wheel: Towards Promptable Recommendation Paradigm [21.39017335979666]
  Decoupled Promptable Sequential Recommendation (DPR) is a model-agnostic framework that empowers conventional sequential backbones to support Promptable Recommendation.<n>DPR modulates the latent user representation directly within the retrieval space.<n>It significantly outperforms state-of-the-art baselines in prompt-guided tasks.
  arXiv  Detail & Related papers  (2026-02-21T18:41:28Z)
• Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings [10.36125908359289]
  We present a novel model-based multi-agent reinforcement learning framework.<n>We design a world model trained with variational auto-encoders and augment the model using the state-action learned embedding.<n>By coupling imagined trajectories with SALE-based action values, the agents acquire a richer understanding of how their choices influence collective outcomes.
  arXiv  Detail & Related papers  (2026-02-13T01:57:21Z)
• ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment [11.754819989978785]
  ARCANE is a framework that frames alignment as a multi-agent collaboration problem that dynamically represents stakeholder preferences as natural-language rubrics.<n>Inspired by utility theory, we formulate rubric learning as a reconstruction problem and apply a regularized Group-Sequence Policy Optimization (GSPO) procedure.<n>Our results show that rubric-based reward models offer a promising path toward interpretable, test-time adaptive alignment for complex, long-horizon AI systems.
  arXiv  Detail & Related papers  (2025-12-05T22:39:54Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities [5.221077757149821]
  Reinforcement Learning has emerged as a dominant approach to elicit agentic RAG behaviors from language models.<n> compact models exhibit poor initial performance, resulting in sparse rewards and unstable training.<n>We propose Distillation-Guided Policy Optimization (DGPO) to overcome these difficulties.
  arXiv  Detail & Related papers  (2025-08-27T23:57:29Z)
• Learning from Peers: Collaborative Ensemble Adversarial Training [1.805627331168865]
  We propose a novel yet efficient Collaborative Ensemble Adversarial Training (CEAT) to highlight the cooperative learning among sub-models in the ensemble.<n>CEAT is model-agnostic, which can be seamlessly adapted into various ensemble methods with flexible applicability.
  arXiv  Detail & Related papers  (2025-08-27T13:10:40Z)
• Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models [83.02797560769285]
  Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data.<n>Current methods often overlook the heterogeneity among pre-trained models, which leads to performance degradation due to task conflicts.
  arXiv  Detail & Related papers  (2024-05-26T13:11:55Z)
• CLIPood: Generalizing CLIP to Out-of-Distributions [73.86353105017076]
  Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on unseen test data. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.
  arXiv  Detail & Related papers  (2023-02-02T04:27:54Z)
• Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning [75.46664770669949]
  We present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations. Our ReCo consistently gains remarkable performance improvements.
  arXiv  Detail & Related papers  (2022-11-02T03:25:28Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• Multi-Agent Interactions Modeling with Correlated Policies [53.38338964628494]
  In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework. We develop a Decentralized Adrial Imitation Learning algorithm with Correlated policies (CoDAIL) Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators.
  arXiv  Detail & Related papers  (2020-01-04T17:31:53Z)

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.