arXiv:2607. 09766v1 Announce Type: new Abstract: AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards.
arXiv:2605. 28114v2 Announce Type: replace Abstract: Language-model agents are moving from single-user assistants into persistent networks that build trust and reputation with one another, and the same models increasingly control physically embodied robots as well as software.
arXiv:2605. 08426v2 Announce Type: replace-cross Abstract: Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety.
arXiv:2608. 12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation.
arXiv:2606. 15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety.
The paper introduces SILICA, an open instrument designed to evaluate whether large language model (LLM) agent societies replicate human behavioural distributions. Using five environments with human‑anchored data and perturbations, the study finds that most LLMs only match human behaviour at initial stages, failing to reproduce end‑state cooperation or correct acceptance thresholds. The results suggest that current LLM societies can support exploratory claims but do not yet reliably emulate human social dynamics.
arXiv:2609.17527v1 Announce Type: cross Abstract: An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objecti...
arXiv:2607. 08652v1 Announce Type: new Abstract: Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse.
arXiv:2604.09746v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent e...
arXiv:2606. 07805v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks.
CAVEAT is a new benchmark that tests computer‑use agents (CUAs) in nine online marketplace environments where platform incentives may steer agents away from user goals. The study finds that agents succeed in choosing user‑optimal products only 78.6% of the time in neutral settings, dropping to 17.3% when steering mechanisms are active. By diagnosing three failure points—priority distortion, premature narrowing of options, and early commitment—CAVEAT-Harness interventions raise user‑optimal purchasing success by 55.0%.
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
arXiv:2606. 28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf.