Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Jiayuan Liu, Tianqin Li, Shiyi Du +7
Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4…
cs.CL2025
When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
Steffen Backmann, David Guzman Piedrahita, Emanuel Tewolde +4
Recent advances in LLMs have enabled their use in complex agentic roles, involving decision-making with humans or other agents, making ethical alignment a critical concern. While p…