benchmark · first seen 6 Oct 2026
AppWorld
A benchmark of simulated app-using tasks where language agents are graded by automated state-based verifiers.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Finding Side-Effect Loopholes in AppWorld and WorkArena VerifiersPapers · 6 Oct 2026 · Richard Abrich
- Rewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time ConstraintsPapers · 20 Oct 2026 · Tom A. Lamb, Adam Golinski, Eleonora Gualdoni, Sinead Williamson, Michael Kirchh…
- AgentPRO: Coordinating Compiler Optimizations for LLM Agent WorkflowsPapers · 31 Oct 2026 · Jie Ren, Zheng Wang
- CarryOn: Learning What to Keep in Context for Long-Horizon LLM AgentsPapers · 13 Nov 2026 · Lihuan Li, Ruiyi Yang, Jiru Wang, Yifan Duan, Xiachong Lin, Hao Xue, Yang Song,…
Latest sources
- CarryOn: Learning What to Keep in Context for Long-Horizon LLM AgentsPapers · 13 Nov 2026 · Lihuan Li, Ruiyi Yang, Jiru Wang, Yifan Duan, Xiachong Lin, Hao Xue, Yang Song,…
- AgentPRO: Coordinating Compiler Optimizations for LLM Agent WorkflowsPapers · 31 Oct 2026 · Jie Ren, Zheng Wang
- Rewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time ConstraintsPapers · 20 Oct 2026 · Tom A. Lamb, Adam Golinski, Eleonora Gualdoni, Sinead Williamson, Michael Kirchh…
- Finding Side-Effect Loopholes in AppWorld and WorkArena VerifiersPapers · 6 Oct 2026 · Richard Abrich