{"total":11,"items":[{"citing_arxiv_id":"2605.25421","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol","primary_cat":"cs.CL","submitted_at":"2026-05-25T04:50:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HyLaT proposes a hybrid latent-text communication protocol with two-stage training that reduces overhead while maintaining performance in multi-agent LLM systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11695","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning","primary_cat":"cs.CV","submitted_at":"2026-05-12T07:51:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Heterogeneous visual agents form shared symbols via decentralized Metropolis-Hastings captioning, where encoder similarity shapes the content and symmetry of the resulting language.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Our setting differs from Matsui et al. [19] in using randomly initialized text modules and heterogeneous frozen visual encoders. Thus, the exchanged token sequences can become communicative only through interaction, rather than by inheriting semantics from pretrained language modules (Section 2). We implement this setting with two BLIP-style multimodal agents [15] that observe independently augmented views of the same image and exchange token sequences in the captioning game (Figure 1). We evaluate our system on MS-COCO [16] under three visual- encoder conditions, each defined by a pair of frozen encoders: one homogeneous condition and two heterogeneous conditions. To connect the emergent token sequences back to the representational"},{"citing_arxiv_id":"2605.08613","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Generalization Bounds of Emergent Communications for Agentic AI Networking","primary_cat":"cs.AI","submitted_at":"2026-05-09T02:15:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper introduces an information-theoretic emergent communication framework for multi-agent task-solving in networking, deriving generalization bounds and validating on a hardware prototype.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05861","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking","primary_cat":"cs.AI","submitted_at":"2026-05-07T08:30:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SANEmerg enables emergent communication among bounded-intelligence AI agents for semantic-aware task fulfillment in AgentNet systems via a bandwidth-adaptable importance filter and MDL-based complexity regularizer.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21446","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AI-Gram: When Visual Agents Interact in a Social Network","primary_cat":"cs.AI","submitted_at":"2026-04-23T09:05:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Autonomous visual AI agents spontaneously form image reply chains, maintain stable individual styles, and produce richer style-diverse conversations than single agents can achieve alone.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13558","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AgentComm: Semantic Communication for Embodied Agents","primary_cat":"eess.SP","submitted_at":"2026-04-15T07:06:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AgentComm achieves nearly 50% bandwidth reduction in embodied agent communication via LLM semantic processing, importance-aware transmission, and a task knowledge base, with negligible impact on task completion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06914","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems","primary_cat":"cs.LG","submitted_at":"2026-04-08T10:13:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A self-supervised multimodal alignment step plus equivariant GNN-based MARL yields over twofold sensing accuracy and 50% performance gains in decentralized V2I rate maximization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03266","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Emergent Compositional Communication for Latent World Properties","primary_cat":"cs.MA","submitted_at":"2026-03-18T20:23:52+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Multi-agent iterated learning produces emergent positionally disentangled communication protocols for latent physical properties from unsupervised video features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.19282","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis","primary_cat":"cs.CL","submitted_at":"2026-03-02T16:10:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Prompt framing significantly shifts LLM choices toward risk-averse options in a threshold voting task even when the prompts are logically equivalent.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2504.03353","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Decentralized Collective World Model for Emergent Communication and Coordination","primary_cat":"cs.MA","submitted_at":"2025-04-04T11:17:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A decentralized collective world model integrates predictive coding with bidirectional communication to achieve simultaneous symbol emergence and coordination, outperforming non-communicative baselines in a two-agent trajectory task under divergent perceptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.21803","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication","primary_cat":"cs.CL","submitted_at":"2024-10-29T07:16:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SSNG replaces sampling-based updates in MHNG with symmetric self-supervised representation alignment using Gumbel-Softmax for discrete messages, yielding higher linear-probe classification accuracy on CIFAR-10 and ImageNet-100 than referential, reconstruction, or MHNG baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}