long horizon
4 stories and discussions about long horizon, aggregated from every source we track.
1.
Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse. Existing context management methods mainly…
2.
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two…
4.
Ruiyang Wang and colleagues present GAVEL, which verifies and repairs long-horizon LLM robot plans against an explicit graph world model holding object relation