Coadaptive Value Alignment

Theintegrationofautonomousagentsintohumansocietyisagrand challenge for AI. In order to achieve widespread acceptance, agents must conform to the values of people with whom they interact. Current approaches treat the value alignment problem as a unidirectional interaction where the aim is to imbue an agent’s actions with human values. Our Coadaptive Value Alignment paradigm acknowledges that human perceptions, expectations, and values continuously evolve in response to agent actions. We conceptualize human-agent interaction as an adaptive loop where the agent actively models and intentionally influences the human’s perception, rather than just acting according to static human values. For instance, unlike a traditional agent that simply maximizes speed, an adaptive agent could detect a drop in user trust and strategically sacrifice short-term efficiency to repair the relationship. This perspective transforms value alignment into a multi-agent challenge where all actors must identify and adhere to a shared, implicit social contract. The opportunity to create a virtuous cycle of selfimprovement is accompanied by the risk of negative reinforcement, which could result in undesired behaviors. We outline the core framework components, present a research road map for the MAS community, and propose that this dynamic perspective is critical for creating truly collaborative social partners.

Authors

• Nathan Tsoi University of Texas at Austin
• Eric Hsiung University of Texas at Austin
• Masayuki Yamazaki University of Texas at Austin
• Swarat Chaudhuri University of Texas at Austin & Google Deepmind
• Peter Stone University of Texas at Austin & Sony AI
• Joydeep Biswas University of Texas at Austin

Keywords

• Value Alignment
• Multi-Agent Systems
• Human-Agent Interaction