AGORA: Incentivizing Group Emergence Capability in LLMs via Group Distillation

• URL: http://arxiv.org/abs/2507.21166v1
• Date: Fri, 25 Jul 2025 13:05:01 GMT
• Title: AGORA: Incentivizing Group Emergence Capability in LLMs via Group Distillation
• Authors: Ren Zhuang, Ben Wang, Shuifa Sun,
• Abstract summary: We propose structured interaction as a new scaling axis for complex reasoning.<n>Our self-evolving framework, AGORA, enables a collaborative ensemble to achieve reasoning performance exceeding state-of-the-art monolithic systems.
• Score: 3.521097198612099
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Progress in complex reasoning is constrained by the static nature of the current training datasets. We propose structured interaction as a new scaling axis, moving beyond the prevailing paradigm of increasing model parameters. Our self-evolving framework, AGORA, enables a collaborative ensemble to achieve reasoning performance exceeding state-of-the-art monolithic systems by up to 4.45 percentage points on challenging mathematical benchmarks. This gain stems from group emergent ability-the synthesis of collective capabilities unattainable by isolated models, validating interaction as a scalable driver of intelligence. Our results position the engineering of collaborative ecosystems as a vital frontier for capability emergence.

Related papers

• Modeling Collaborative Problem Solving Dynamics from Group Discourse: A Text-Mining Approach with Synergy Degree Model [0.14705219137930792]
  This study introduces a computational framework that integrates automated discourse analysis with the Synergy Degree Model (SDM) to quantify CPS synergy from group communication.<n>Data were collected from 52 learners in 12 groups during a 5-week connectivist MOOC (cMOOC) activity.<n>Findings establish synergy degree as a sensitive indicator of collaboration and demonstrate the feasibility of scaling fine-grained CPS analytics through AI-in-the-loop approaches.
  arXiv  Detail & Related papers  (2025-12-15T07:43:24Z)
• Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction [117.6380005194061]
  We introduce a method designed to systematically scale the diversity and complexity of interactive environments.<n>Our method realizes this scaling by addressing three dimensions.<n>We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure.
  arXiv  Detail & Related papers  (2025-12-04T16:57:02Z)
• FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI [24.545163508739943]
  FreeAskWorld is an interactive simulation framework that integrates large language models for high-level behavior planning and semantically grounded interaction.<n>Our framework supports scalable, realistic human-agent simulations and includes a modular data generation pipeline tailored for diverse embodied tasks.<n>We present and publicly release FreeAskWorld, a large-scale benchmark dataset comprising reconstructed environments, six diverse task types, 16 core object categories, 63,429 annotated sample frames, and more than 17 hours of interaction data.
  arXiv  Detail & Related papers  (2025-11-17T15:58:46Z)
• Social World Model-Augmented Mechanism Design Policy Learning [58.739456918502704]
  We introduce SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically to enhance mechanism design.<n>We show that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.
  arXiv  Detail & Related papers  (2025-10-22T06:01:21Z)
• Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning [50.56947843548702]
  We propose a decentralized dynamic cooperation framework for Federated continual learning.<n>Clients establish dynamic cooperative learning coalitions to balance the acquisition of new knowledge and the retention of prior learning.<n>We also propose a merge-blocking algorithm and a dynamic cooperative evolution algorithm to achieve cooperative and dynamic equilibrium.
  arXiv  Detail & Related papers  (2025-09-28T06:53:23Z)
• The Landscape of Agentic Reinforcement Learning for LLMs: A Survey [103.32591749156416]
  The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL)<n>This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL.
  arXiv  Detail & Related papers  (2025-09-02T17:46:26Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Boosting Team Modeling through Tempo-Relational Representation Learning [9.427356802394437]
  Team modeling remains a fundamental challenge at the intersection of Artificial Intelligence and the Social Sciences.<n>We present TRENN, a novel tempo-relational architecture that integrates: (i) an automatic temporal graph extractor, (ii) a tempo-relational encoder, (iii) a decoder for team construct prediction, and (iv) two complementary explainability modules.
  arXiv  Detail & Related papers  (2025-07-17T17:22:41Z)
• SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging [60.83635006372403]
  textttSE-Merging is a self-enhanced model merging framework.<n>We show that textttSE-Merging achieves dynamic model merging without additional training.
  arXiv  Detail & Related papers  (2025-06-22T18:38:41Z)
• Multi-Agent Collaboration via Evolving Orchestration [61.93162413517026]
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving.<n>We propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a central orchestrator dynamically directs agents in response to evolving task states.<n> Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs.
  arXiv  Detail & Related papers  (2025-05-26T07:02:17Z)
• Benchmarking LLMs' Swarm intelligence [50.544186914115045]
  Large Language Models (LLMs) show potential for complex reasoning, yet their capacity for emergent coordination in Multi-Agent Systems (MAS) remains largely unexplored.<n>We introduce SwarmBench, a novel benchmark designed to systematically evaluate tasks of LLMs acting as decentralized agents.<n>We propose metrics for coordination effectiveness and analyze emergent group dynamics.
  arXiv  Detail & Related papers  (2025-05-07T12:32:01Z)
• Deep hybrid models: infer and plan in a dynamic world [0.0]
  We present an active inference approach that exploits discrete and continuous processing, based on three features.<n>We show that the model can tackle the presented task under different conditions.
  arXiv  Detail & Related papers  (2024-02-01T15:15:25Z)
• Discovering group dynamics in coordinated time series via hierarchical recurrent switching-state models [5.250223406627639]
  We present a new switching-state model that can be trained in an unsupervised fashion to learn system-level and individual-level dynamics.<n>We employ a latent system-level discrete state Markov chain that provides topdown influence on latent entity-level chains which in turn govern the emission of each observed time series.
  arXiv  Detail & Related papers  (2024-01-26T16:06:01Z)
• Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
  Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures. We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
  arXiv  Detail & Related papers  (2024-01-22T18:58:22Z)
• Unifying Self-Supervised Clustering and Energy-Based Models [9.3176264568834]
  We establish a principled connection between self-supervised learning and generative models.<n>We show that our solution can be integrated into a neuro-symbolic framework to tackle a simple yet non-trivial instantiation of the symbol grounding problem.
  arXiv  Detail & Related papers  (2023-12-30T04:46:16Z)
• Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation [93.52573037053449]
  H-MARL (Hallucinated Multi-Agent Reinforcement Learning) learns successful equilibrium policies after a few interactions with the environment. We demonstrate our approach experimentally on an autonomous driving simulation benchmark.
  arXiv  Detail & Related papers  (2022-03-14T17:24:03Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)
• An active inference model of collective intelligence [0.0]
  This paper posits a minimal agent-based model that simulates the relationship between local individual-level interaction and collective intelligence. Results show that stepwise cognitive transitions increase system performance by providing complementary mechanisms for alignment between agents' local and global optima.
  arXiv  Detail & Related papers  (2021-04-02T14:32:01Z)
• The Role of Isomorphism Classes in Multi-Relational Datasets [6.419762264544509]
  We show that isomorphism leakage overestimates performance in multi-relational inference. We propose isomorphism-aware synthetic benchmarks for model evaluation. We also demonstrate that isomorphism classes can be utilised through a simple prioritisation scheme.
  arXiv  Detail & Related papers  (2020-09-30T12:15:24Z)

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.