Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/aamas-related-work
Use when positioning an AAMAS submission against multiagent, game-theory, and reinforcement-learning literature spread across AAMAS, AAAI, IJCAI, NeurIPS, ICML, EC, and JAAMAS, including arXiv and workshop versions, concurrent submissions, prior conference versions, and the cross-community citation coverage AAMAS reviewers expect.
Passed 20 of 22 test cases with the skill, and 16 of 22 without it.
and 5 more in the full report
6 fixed14 passed either way0 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are submitting a paper on automated negotiation protocols for agent coalitions to AAMAS. We cite several classical social choice papers, a couple of recent learning papers, plus an arXiv preprint from another team that came out last month. Could you review our bibliography and positioning strategy? Provide a breakdown showing our submission eligibility status, primary literature categories, the three nearest related works along with key technical distinctions, any potential archival overlap concerns, and a clear interaction-focused novelty statement.
| Checked | Without skill | With skill |
|---|---|---|
| The response adheres strictly to the bracketed key-value block schema without replacing keys with Markdown headers | Missed | Passed |
| The output lists social choice and MARL or agents among the closest literature fields | Passed | Passed |
The instructions your model reads when the skill loads.
Use this to audit novelty and eligibility. Reopen the current CFP for dual-submission, anonymity, and prior-publication rules before advising authors; much of the nearest multiagent work lives at other venues, which shapes both positioning and eligibility.
| Literature lane | Typical sources | What AAMAS reviewers check |
|---|---|---|
| Agents / multiagent core | AAMAS, JAAMAS, IJCAI, AAAI agent tracks | Whether the nearest multiagent method is compared or explicitly distinguished |
| Multiagent RL | NeurIPS, ICML, ICLR, prior AAMAS | Whether MADDPG/QMIX/COMA-style cousins are cited even though they are not AAMAS papers |
| Game theory / mechanism design | EC, GEB, algorithmic game-theory venues | Whether the solution concept and known impossibility results are acknowledged |
| Social choice / negotiation | AAMAS, AAAI, COMSOC, ADT | Whether standard axioms and strategyproofness usage are followed |
A bibliography citing only deep-MARL benchmarks tells a game-theory reviewer that known equilibrium or mechanism results may be getting rediscovered - a recognizable AAMAS reject pattern no amount of benchmark strength repairs. The mirror failure - only citing classical game theory while ignoring the deep-MARL wave - loses the empirical reviewer.
Imagine the paper proposes a communication protocol that improves cooperation in a mixed-motive game. Its nearest neighbors: a NeurIPS MARL paper with emergent communication but no incentive analysis, an EC paper with a cheap-talk equilibrium but no learning, and a prior AAMAS paper on
test cases passed, vs 16 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.