# Skill-selection on ToolBench-60 one-hot preference regime (held-out pool)

Source: [Skill-selection on ToolBench-60 one-hot preference regime (held-out pool)](<https://www.sota2.com/research/sota/skill-selection-on-toolbench-60-one-hot-preference-regime-held-out-pool>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-05T09:11:26.662Z

Evaluation of model performance on skill selection using the specific ToolBench-60 configuration under the one-hot preference regime, measured by Regret, Accuracy, and R.R.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Skill-selection |
| Dataset (including any stated split) | ToolBench-60 one-hot preference regime (held-out pool) |
| Metric | Regret |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 27 of 27 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Regret](<https://www.sota2.com/research/sota/skill-selection-on-toolbench-60-one-hot-preference-regime-held-out-pool.md?metric=Regret>): Lower is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/skill-selection-on-toolbench-60-one-hot-preference-regime-held-out-pool.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [RR Score](<https://www.sota2.com/research/sota/skill-selection-on-toolbench-60-one-hot-preference-regime-held-out-pool.md?metric=RR%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Regret | Result date | Report paper |
| --- | --- | --- | --- |
| Freq-as-Override | 103.3 | Not recorded | 6a2258a186173ad9c1468be8 |
| Freq-as-Override | 107.2 | Not recorded | 6a2258a186173ad9c1468be8 |
| Bandit-as-Override | 118.9 | Not recorded | 6a2258a186173ad9c1468be8 |
| Bandit-as-Override | 122.4 | Not recorded | 6a2258a186173ad9c1468be8 |
| Freq-as-Override | 126.3 | Not recorded | 6a2258a186173ad9c1468be8 |
| Bandit-as-Override | 135.7 | Not recorded | 6a2258a186173ad9c1468be8 |
| Pure-Bandit | 137.1 | Not recorded | 6a2258a186173ad9c1468be8 |
| Pure-Bandit | 139.6 | Not recorded | 6a2258a186173ad9c1468be8 |
| Pure-Bandit | 140.2 | Not recorded | 6a2258a186173ad9c1468be8 |
| Freq-Greedy | 162.4 | Not recorded | 6a2258a186173ad9c1468be8 |
| Freq-Greedy | 166 | Not recorded | 6a2258a186173ad9c1468be8 |
| Freq-Greedy | 167.6 | Not recorded | 6a2258a186173ad9c1468be8 |
| Profile-Memory | 208.7 | Not recorded | 6a2258a186173ad9c1468be8 |
| Bandit-as-Context | 216.6 | Not recorded | 6a2258a186173ad9c1468be8 |
| Profile-Memory | 245.1 | Not recorded | 6a2258a186173ad9c1468be8 |
| Bandit-as-Context | 266 | Not recorded | 6a2258a186173ad9c1468be8 |
| Profile-Memory | 269.5 | Not recorded | 6a2258a186173ad9c1468be8 |
| Bandit-as-Context | 344.2 | Not recorded | 6a2258a186173ad9c1468be8 |
| InContext-Memory | 363.9 | Not recorded | 6a2258a186173ad9c1468be8 |
| InCotext-Memory | 365.4 | Not recorded | 6a2258a186173ad9c1468be8 |
| InCotext-Memory | 371.5 | Not recorded | 6a2258a186173ad9c1468be8 |
| ZeroShot-LLM | 376 | Not recorded | 6a2258a186173ad9c1468be8 |
| ZeroShot-LLM | 377.1 | Not recorded | 6a2258a186173ad9c1468be8 |
| ZeroShot-LLM | 377.2 | Not recorded | 6a2258a186173ad9c1468be8 |
| Random | 491.8 | Not recorded | 6a2258a186173ad9c1468be8 |
| Random | 492 | Not recorded | 6a2258a186173ad9c1468be8 |
| Random | 492.1 | Not recorded | 6a2258a186173ad9c1468be8 |

### Freq-as-Override

Regret: 103.3. Result ID: 6a2291ddfbc373592c20dfa6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"LLM with Statistical Prior"}. This record does not assert independent reproduction.

### Freq-as-Override

Regret: 107.2. Result ID: 6a2291ddfbc373592c20dfca.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Bandit-as-Override

Regret: 118.9. Result ID: 6a2291ddfbc373592c20dfa7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"LLM with Statistical Prior"}. This record does not assert independent reproduction.

### Bandit-as-Override

Regret: 122.4. Result ID: 6a2291ddfbc373592c20dfcb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Freq-as-Override

Regret: 126.3. Result ID: 6a2291ddfbc373592c20dfb8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"LLM with Statistical Prior","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### Bandit-as-Override

Regret: 135.7. Result ID: 6a2291ddfbc373592c20dfb9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"LLM with Statistical Prior","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### Pure-Bandit

Regret: 137.1. Result ID: 6a2291ddfbc373592c20dfc6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60891e209131ce9efe66.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Pure-Bandit

Regret: 139.6. Result ID: 6a2291ddfbc373592c20dfa2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60891e209131ce9efe66.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"Statistical"}. This record does not assert independent reproduction.

### Pure-Bandit

Regret: 140.2. Result ID: 6a2291ddfbc373592c20dfb4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60891e209131ce9efe66.md>)

Recorded evaluation configuration: {"Method Category":"Statistical","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### Freq-Greedy

Regret: 162.4. Result ID: 6a2291ddfbc373592c20dfc5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Freq-Greedy

Regret: 166. Result ID: 6a2291ddfbc373592c20dfa1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"Statistical"}. This record does not assert independent reproduction.

### Freq-Greedy

Regret: 167.6. Result ID: 6a2291ddfbc373592c20dfb3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"Statistical","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### Profile-Memory

Regret: 208.7. Result ID: 6a2291ddfbc373592c20dfc8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Bandit-as-Context

Regret: 216.6. Result ID: 6a2291ddfbc373592c20dfa5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60891e209131ce9efe66.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"LLM with Statistical Prior"}. This record does not assert independent reproduction.

### Profile-Memory

Regret: 245.1. Result ID: 6a2291ddfbc373592c20dfa4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"LLM with Memory"}. This record does not assert independent reproduction.

### Bandit-as-Context

Regret: 266. Result ID: 6a2291ddfbc373592c20dfc9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60891e209131ce9efe66.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Profile-Memory

Regret: 269.5. Result ID: 6a2291ddfbc373592c20dfb6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"LLM with Memory","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### Bandit-as-Context

Regret: 344.2. Result ID: 6a2291ddfbc373592c20dfb7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60891e209131ce9efe66.md>)

Recorded evaluation configuration: {"Method Category":"LLM with Memory","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### InContext-Memory

Regret: 363.9. Result ID: 6a2291ddfbc373592c20dfb5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"LLM with Memory","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### InCotext-Memory

Regret: 365.4. Result ID: 6a2291ddfbc373592c20dfa3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"LLM with Memory"}. This record does not assert independent reproduction.

### InCotext-Memory

Regret: 371.5. Result ID: 6a2291ddfbc373592c20dfc7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### ZeroShot-LLM

Regret: 376. Result ID: 6a2291ddfbc373592c20dfc4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### ZeroShot-LLM

Regret: 377.1. Result ID: 6a2291ddfbc373592c20dfa0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"No Learning"}. This record does not assert independent reproduction.

### ZeroShot-LLM

Regret: 377.2. Result ID: 6a2291ddfbc373592c20dfb2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"No Learning","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

### Random

Regret: 491.8. Result ID: 6a2291ddfbc373592c20dfc3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"GPT-5.2"}. This record does not assert independent reproduction.

### Random

Regret: 492. Result ID: 6a2291ddfbc373592c20df9f.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V4-Flash","Agent Category":"No Learning"}. This record does not assert independent reproduction.

### Random

Regret: 492.1. Result ID: 6a2291ddfbc373592c20dfb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a186173ad9c1468be8.md>)

Recorded evaluation configuration: {"Method Category":"No Learning","Backbone":"Qwen3-30B-Instruct"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
