Cooperation Between Autonomous LLM Agents in the Prisoner's Dilemma
The only report directly on this event is a single arXiv paper (item 1) on cooperation between autonomous LLM agents in the Prisoner's Dilemma; the remaining six items are unrelated arXiv announcements on other agent topics and contain no material about this event. No details on methods, models, numbers, or findings are available in the supplied material. The event therefore rests on one paper with no independent coverage yet.
How this story unfolded
Key points2 items Model summary · ordered by when the evidence was published
- Point 01 11/14, 04:46
One arXiv paper addresses cooperation between autonomous LLM agents in the Prisoner's Dilemma.
Based on 1 - Point 02 11/16, 13:00
The other six supplied items concern unrelated agent topics and do not cover this event.
ReportsBy publish time · newer further down
- November 14, 2026 · Sat
- November 16, 2026 · Mon
- +2d 8h
What LLM Agents See and What Users Say
Original summary arXiv:2611.17639v1 Announce Type: new Abstract: Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its
arXiv cs.AI Original ↗ - +2d 8h
Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
Original summary arXiv:2611.17880v1 Announce Type: new Abstract: LLM agents that execute multi-step tool calls must satisfy two objectives simultaneously: completing the user's task (utility) and c
arXiv cs.AI Original ↗ - +2d 8h
OutfitterBench: Evaluating LLM Agents on Long-Horizon Resource Allocation and Commitment Coordination
Original summary arXiv:2611.17933v1 Announce Type: new Abstract: In many long-horizon settings, an agent's own choices create future constraints: committing finite capacity establishes future oblig
arXiv cs.AI Original ↗ - +2d 8h
CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents
Original summary arXiv:2611.17808v1 Announce Type: new Abstract: Long-horizon LLM agents can coordinate tools and applications to complete complex, multi-step tasks. As their interaction histories
arXiv cs.CL Original ↗ - +2d 8h
When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors
Original summary arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when
arXiv cs.AI Original ↗ - +2d 8h
MineralExp: Benchmarking LLM Agents for Experimental Design in Real-World Mineral Exploration
Original summary arXiv:2611.17931v1 Announce Type: new Abstract: In mineral exploration, verifying geological hypotheses relies on designing a variety of geochemical experiments. While large langua
arXiv cs.CL Original ↗ - Still developing · later reports will keep extending this axis