The paper introduces self‑referenced social preferences, allowing agents to learn cooperative behavior without observing others’ private rewards. Each agent models its own reward, applies this model to observed transitions of other agents, and uses the resulting assessments to inform either the learning reward or policy updates. Experiments on three social‑dilemma environments show that agents can achieve cooperation and more equitable outcomes even when independent learners fail, with the best integration point depending on the type of social preference used.
arXiv:2607. 04710v1 Announce Type: new Abstract: Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations.
Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations. There, individual interests are misaligned with the common good and individual rationality leads to suboptimal group outcomes.
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:2608. 20016v1 Announce Type: cross Abstract: Reputation is widely recognized as a key mechanism for sustaining cooperation.
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
arXiv:2606. 11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare.
arXiv:2608. 03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.
arXiv:2511. 10687v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning.
arXiv:2609.38516v1 Announce Type: cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to wor...
arXiv:2610.07491v1 Announce Type: cross Abstract: When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty sh...
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:2607. 04470v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood.