arXiv:2604. 10760v2 Announce Type: replace-cross Abstract: Artificial agents can be made to ``help'' through explicit social rewards, hard-coded prosocial bonuses, or direct access to another agent's state.
arXiv:2608. 01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by their behavior, not only their reward.
arXiv:2601. 17454v2 Announce Type: replace-cross Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evaluated in settings that confound coordination structure with function approximation and partial observability.
arXiv:2608. 04663v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning often adds social terms to individual rewards, yet the scale of those terms is usually chosen by hand.
arXiv:2608. 04232v1 Announce Type: new Abstract: Biological systems must regulate competing needs under limited perceptual bandwidth, where sharpening one estimate costs the capacity to sharpen the others.
arXiv:2609.24876v1 Announce Type: new Abstract: In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confid...
arXiv:2608.28046v1 Announce Type: cross Abstract: Collective behaviour in living systems is usually modelled as the outcome of a \emph{direct} social drive: agents are rewarded, or hard-wired, to ali...
In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confidently those inferences should guide policy select...
arXiv:2608. 13787v1 Announce Type: new Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices.
arXiv:2604.27167v3 Announce Type: replace-cross Abstract: On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, loc...
arXiv:2605. 08747v4 Announce Type: replace Abstract: Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment.
arXiv:2604. 15267v2 Announce Type: replace-cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings.
arXiv:2604. 15010v2 Announce Type: replace-cross Abstract: When do transformers commit to a decision, and what prevents them from correcting it?