decision model
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
3 papers in the last two months, against 0 in the two before.
Start here
Two papers to read first, in the order they came out- 1Small decision models can safely handle routine agent decisions with little loss of success
Replacing most LLM calls with a decision model cuts agent cost and latency with minimal success loss.
Oct 2026 - 2Neither decision models nor new LLMs beat statistical baselines as synthetic survey respondents
Decision models produce plausible survey marginals but lack psychometric validity, while newer generative models do not improve on older models or statistical baselines.
Oct 2026
How fast it is moving
Often studied with
agentic evaluationMeasuring AI agents' performance in complex tasks, highlighting failures in planning, monitoring, and real2 togetherconfidence calibrationConfidence calibration aligns a model's predicted confidence with its actual accuracy across predictions.2 togetherbenchmarkA standard set of tasks or data used to evaluate and compare the performance of AI systems.1 togetherThe papers
Most central to this idea first, not most recent.
- Big Techcs.AI
Small decision models can safely handle routine agent decisions with little loss of success
Replacing most LLM calls with a decision model cuts agent cost and latency with minimal success loss.
University of Illinois Urbana-Champaign, Princeton University · Oct 2026
- Academiccs.AI
Neither decision models nor new LLMs beat statistical baselines as synthetic survey respondents
Decision models produce plausible survey marginals but lack psychometric validity, while newer generative models do not improve on older models or statistical baselines.
Hostinger, Kaunas University of Technology · Oct 2026
- Big Techcs.CL
AI agents struggle to finish workflows with a thousand tools
Even the best tested LLM agent completes only 5.0% of tasks in a benchmark requiring selection from 1,000 APIs over long chains of steps.
Amazon, Georgia Institute of Technology · Nov 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.