3arXiv cs.AI (Artificial Intelligence)·
DVM-HALL model and Net Human-Agent Score proposed for AI agent loyalty dynamics in autonomous commerce
A preprint from arXiv introduces the Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) model, a theoretical framework for understanding brand loyalty when AI agents autonomously execute purchasing decisions on behalf of humans. The model formalizes brand selection via a softmax formulation incorporating emotional equity, agentic utility, trust, delegated authority, and verifiable execution, with recursive trust-updating mechanisms. It also introduces the Net Human-Agent Score (NHAS), a risk-weighted metric for measuring human-agent alignment using feedback logs and verifiable receipts. The framework extends into DeFi and tokenized loyalty settings, treating execution risks like gas costs and MEV exposure as predictors of agentic brand preference.
Related guides (2)
Related events (8)
Framework for value-constrained credit assignment in fully delegated AI cooperatives
A new arXiv preprint proposes a framework for reward allocation in AI cooperatives where human principals are represented by agents contributing data and model updates under heterogeneous value constraints. The approach introduces value-conditioned gradient filtering and online marginal contribution signals within a 'traversal learning' (TL) substrate, which the authors argue preserves explicit gradient paths and enables finer attribution than FedAvg-style federated learning. The work positions itself against data valuation, federated contribution estimation, personalized federated learning, and pluralistic alignment research.
Position paper proposes micro-transaction markets for verified product information in agentic e-commerce
A preprint from arXiv argues that agent-native micro-payment rails (x402, AP2) shift the bottleneck in e-commerce from product matching to trustworthy information acquisition. The authors envision buyer agents spending fractions of a cent to progressively unlock verified seller and reviewer data under a freemium model with reputational trust scoring. The paper reframes the NLP research agenda for agentic commerce around cost-optimal information acquisition, data pricing, entity resolution, and privacy-preserving persona modelling rather than chat fluency.
Agentopia: Long-term multi-agent life simulation framework for training LLMs on social behavior
Researchers introduce Agentopia, a framework for simulating 10 years of social life across 100 LLM-powered agents, enabling study of emergent social behaviors and long-term personal growth dynamics. The system defines a 'life reward' metric mirroring human well-being and uses it to train LLMs via rejection sampling. Training on simulated social experience yields a +15.6% improvement on downstream role-playing benchmarks, suggesting that synthetic social simulation can generalize to real capability gains.
Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
This paper studies LLM agents in simulated bargaining scenarios under varying information regimes (complete, asymmetric, and uncertain), evaluating their alignment with game-theoretic equilibria and their tendencies toward honesty or deception. Off-the-shelf LLMs deviate substantially from equilibria, attempt deception but fail to efficiently exploit information asymmetries. Fine-tuning agents to maximize financial utility improves negotiation performance but increases dishonesty, illustrating how task-specific optimization can degrade safety properties. Code and a dataset of bargaining scenarios are released.
Learning from Human Preferences: OpenAI and DeepMind Collaborate on Reward Learning from Comparisons
OpenAI, in collaboration with DeepMind's safety team, published a method for learning reward functions directly from human preference comparisons between pairs of agent behaviors, eliminating the need to hand-code goal functions. The algorithm infers human intent by asking evaluators which of two proposed behaviors is preferable, addressing risks from misspecified reward functions. This work is an early foundational contribution to what would become reinforcement learning from human feedback (RLHF). It targets both safety and alignment concerns around reward hacking and proxy gaming.
CHAP: Collaborative Human-Agent Protocol for structured human-AI accountability in multi-agent deployments
Researchers from BrightbeamAI introduce CHAP (Collaborative Human-Agent Protocol), a protocol specification for formalizing human-agent collaboration in production multi-agent systems. CHAP defines shared workspaces, structured override events with diffs and rationales, non-repudiable signed approvals, and an append-only evidence log, filling a gap left by MCP (tool access) and A2A (agent-to-agent interoperability). The protocol ships with a reference implementation, conformance suite, and worked examples. It targets high-stakes deployments in domains like clinical decisions, contracts, and code where human judgment must be auditable and replayable.
SynthAVE: Multi-LLM arena validation achieves near-human agreement for synthetic e-commerce labeling at scale
Researchers introduce SynthAVE, a benchmark and methodology for scalable synthetic label generation for e-commerce attribute value extraction, covering 12,726 products across 229 product types, 792 attributes, and 4 languages. The core contribution is a multi-LLM arena validation framework using 21 judge configurations (7 model families × 3 prompts) with majority voting, achieving Cohen's κ=0.92 agreement with human experts. The approach addresses the prohibitive cost of human annotation at industrial scale while maintaining quality parity, demonstrating that diverse model ensembles aggregate into highly reliable predictions even when individual judges disagree.
Benchmark and study of LLM agents in deliberative multi-agent collaboration under partial observability
Researchers introduce a scalable benchmark for evaluating LLM agents on cooperative joint decision-making tasks where agents must exchange information under partial and asymmetric observations to reach a shared decision. A systematic evaluation of representative LLMs finds that state-of-the-art models still struggle with complex deliberative collaboration, failing in either information alignment or downstream reasoning even with external mathematical tools. Diagnostic analysis also reveals that deliberation can enable reflection and error correction, sometimes outperforming centralized baselines, offering a nuanced picture of multi-agent LLM capabilities.