ALFWorld
Harbor: pendingALFWorld — AI evaluation benchmark listed by awesome.
Auto57%Agentic / Tool Use
- Samples
- N/A
- Released
- 2020
- Scores
- 0
AgentDecisionBench
AgentDecisionBench AgentDecisionBench is the benchmark of the paper JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs.
How to run
ltb · agentdecisionbench
$ npm i -g lettokenburn-cli$ ltb bench info agentdecisionbench
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
2 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| AgentDecision-4B v1 | 24.0 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
| DeepSeek V4 Pro | 7.2 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
AgentDecisionBench
AgentDecisionBench is the benchmark of the paper JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs. Code: github.com/JevAgentHarness/JevAgentHarness (the research code is in its research/ folder). A decision model is a small model that answers a multiple-choice question about an agent's next step, such as "which tool should the agent call next?", with a probability for each option. A harness can hand that choice…