微软用 ThinkingBox 把数据库评分变成 RL 奖励，微调 Qwen3.8-27B

Contents

What the benchmark found, in sixty seconds

Results: the dependability column moved

Offline policy-relative difficulty

In a hurry? The headline result is above. The implementation is in Run the training stack .

What the benchmark found, in sixty seconds

ThinkingBox-Bench grades agents on the database records they leave behind. Each of its 507 tasks starts a real backend, hands the agent a set of MCP tools and a simulated LLM user with private context, and at the end runs executable checks against the terminal database state. Checks are against the backend record that needs to be correct, not the specific tool calls. This incentivizes the model to discover possibly new solution paths rather than “rediscover” the human-backed solution, that might be suboptimal albeit correct.

In our first post we ran eighteen models through that benchmark twenty times each and reported a gap that headline accuracy hides. Kimi-K3 solved 93.89% of tasks at least once but completed only 68 of 507 tasks (13.41%) on all twenty recorded attempts . Claude Opus 5 inverted it: narrower coverage, far more consistency.

And bigger or better model did not close it. Claude Opus 5.5 scored 0.66 percentage points higher than Claude Opus 5 on pass@1, yet passed exactly the same number of tasks, 241 , on all twenty attempts. That gain in headline accuracy bought zero additional dependability.

If you are choosing a model for work that touches production database records, pass@1 should not be read alone. Observed 20/20 shows which tasks succeed on every attempt, which is closer to what production reliability requires.

The executable terminal-state verdict was also the training reward. Before unpacking the training loop, here is what changed on the sealed benchmark.

Results: the dependability column moved

After training Qwen3.8-27B, we evaluated the selected step-50 checkpoint on the 507-task benchmark it had never trained on. The 507 tasks represent an out-of-distribution test set: their domains, databases, and most MCP tools were not encountered during RL training.

Table 2. ThinkingBox-Bench pass@1 (%) by domain, for selected models from our first blog's Table 2 and our fine-tuned model for different domains and overall. Observed 20/20 numbers are over the entire benchmark with 507 tasks. Each model is evaluated on all 507 tasks for 20 repeated trials. Bold marks the column leader; underline marks the runner-up.

The headline result is the observed-20/20 row in Table 1. A 27B model that initially completed 38 (7.5%) of ThinkingBox-Bench on every attempt now completes 107 (21.1%) on every attempt, almost thrice. For comparison, observed 20/20 for Kimi-K3 is 68, GPT-5.4 with 128, GPT-6 Astra has 231, and Claude Opus 5.5 leads with 241.

Average success and repeatability produce different orderings. In Table 2, we notice that GPT-5.6 Sol scored slightly higher on pass@1 than the RL fine-tuned Qwen3.8-27B (61.91% versus 60.78%) but passed fewer tasks on all 20 recorded attempts: 82 versus 107. Claude Sonnet 4.6 scored lower on pass@1, at 59.19%, yet passed nearly the same number of tasks every time, at 102. Neither metric alone captures the full picture.

The observed pattern is consistent with sharpening: repeatable success rose while at-least-once coverage fell slightly. This is in-line with prior work . One explanation is that probability distribution moved toward trajectories that work repeatedly while some low-probability paths disappeared.

Overall, the model did not become broader. It became more repeatable. The next question is where those gains landed.

Where the gains landed

Figure 3. Domain-level base scores, RLFT scores, and percentage-point changes. Green change cells show gains and red cells show declines; blue shading indicates the score level within each metric.

Pass@1 and observed 20/20 rose in all five domains. Pass@20 was mixed: it increased in neobank and consulting, but declined in retail, travel, and auto insurance. Auto insurance had the largest breadth loss (−7.0 points), while retail had the largest observed-20/20 gain (+24.5 points).

What dependability costs

The first post priced consistency using simple math: divide the estimated cost of the full 20-run campaign by the number of tasks the model passed every single time.

Cost per dependable task = estimated cost of the 507 × 20 campaign ÷ tasks passing 20/20

Applying the same cost math to the fine-tuned checkpoint's measured token usage:

Table 3. Estimated evaluation cost and dependability for base and RL fine-tuned Qwen3.8-27B. Cost per successful attempt divides total estimated campaign cost (507 x 20) by the number of passing attempts.

At $8.00 per dependable task, the fine-tuned model came close to GPT-5.4 ($6.80), GPT-6 Astra ($7.45), and Claude Opus 5.5 ($7.80) in the companion comparison.

The single-attempt view

Figure 4 prices cost per successful attempt against pass@1.

Figure 4. The golden arrow traces Qwen3.8-27B base pareto cost position to the RLFT (diamond): pass@1 rises from 51.70% to 60.78% while estimated cost per successful attempt falls from $0.177 to $0.139. Ringed circles mark the Pareto cost frontier.

The move places the fine-tuned checkpoint close to GPT-5.6 Sol, although GPT-5.6 Sol remains cheaper and slightly higher on pass@1. Four models priced in our paper fall outside the plotted range.

The dollar values are a comparative serving index, not invoice or cloud bills. Serving the fine-tuned checkpoint would be the same as the base model. The calculation includes model inference cost, and excludes training run and policy-probe cost for curating the training dataset.

These results tell us what moved. The next sections explain the training loop and why selecting the right tasks matters the most.

The training loop

Figure 5. The six stages, now in context: candidate tasks feed in, the first three run once offline, the last three repeat for every group in the training run. The trained checkpoint is evaluated against ThinkingBox-Bench.

Selection runs once, offline, against the base policy model, i.e in this case Qwen3.8 27B; training then uses that fixed pool that has been curated. The dashed amber arrow in Figure 5 marks the path we did not take: re-probing difficulty during the training run.

Every rollout is a complete episode, not a text completion. It gets a fresh backend, an isolated MCP session, and GPT-5 Chat as the simulated user. Most rewards come from deterministic terminal-state checks; a minority of narrow rubric requirements can invoke the configured judge (GPT-5 Chat).

Training and evaluation must interpret Qwen output identically. That includes reasoning extraction, tool calls, argument typing, rendering, and isolated task state. Otherwise the reward measures a different agent from the one evaluated. The shared interpretation code is in trainer/core/tb_interpret.py .

For the reference run, we ran full-parameter RL fine-tuned Qwen3.8-27B on 187 tasks using token-mean GRPO. Each update generated 18 groups of 8 rollouts, or 144 episodes, across 24 H100s. Training ran synchronously with parameter and optimizer offload; AdamW used a 1e-6 learning rate and zero weight decay. We ran the training for 50 steps.

Zero-variance groups were replaced DAPO-style during training. System errors were handled separately: a backend timeout is not an incorrect agent outcome, so affected groups were refilled rather than scored as failures.

That explains how retained tasks were trained. The remaining question is which tasks entered the training pool.

Offline policy-relative difficulty

Before diving deep into the selection of training tasks, a disclaimer:

No ThinkingBox-Bench task was included in the RL training pool. The benchmark was reserved for evaluation.

ThinkingBox-Bench is out-of-distribution relative to the RL training pool: its domains, databases, policies, and most tools were not encountered during RL training. The two sets still share the ThinkingBox framework, simulated-user machinery, executable terminal-state grading, a few common tools, and a similar task style. These shared elements limit the scope of the transfer claim.

Why selection matters comes down to one arithmetic fact about GRPO. If all eight rollouts fail, the reward vector is [0, 0, 0, 0, 0, 0, 0, 0] . If all eight succeed, it is [1, 1, 1, 1, 1, 1, 1, 1] . In either case, centering within the group produces no task-reward advantage because no trajectory did better than another. ++

A mixed group such as [0, 0, 0, 1, 1, 1, 1, 1] supplies the contrast GRPO can learn from. That distinction is expensive for a stateful agent: every rollout provisions an isolated backend, runs a real tool session, and calls a separate model to play the user.

The question that shaped this work was therefore not only which model or optimizer? It was: which candidate tasks should enter the fixed training pool?

We used an offline pass-rate filter on the posterior to select the training pool. It estimates which tasks are likely to produce contrasting terminal rewards under the base policy.

So we probe. Each candidate task is run repeatedly against the base policy model. The plain-language rule is simple: tasks the model always fails are unlikely to teach it yet; tasks it always passes are already learned; tasks it solves sometimes are where outcomes can provide contrast.

Estimating difficulty from limited probes

Each candidate task is run n times, producing k successes. We model its latent success probability with Jeffreys posterior probability:

success probability | k successes in n probes ~ Beta(k + ½, n − k + ½)

Figure 6. Offline policy-relative difficulty is estimated from repeated base-policy probes and used to retain tasks likely to produce contrasting rewards.

We partition the unit interval into five buckets with boundaries at 0.08, 0.40, 0.60, and 0.90, chosen as hyperparameters for these runs. Each task is assigned to the bucket containing the greatest posterior mass:

Rarely solved [0, 0.08): drop

Difficult [0.08, 0.40): keep

Intermediate [0.40, 0.60): keep

Frequently solved [0.60, 0.90): keep for full-parameter RLFT

Nearly always solved [0.90, 1]: drop

Further details are in Appendix C.4 of our ThinkingBox paper .

One task, end to end

Figure 7. Zooming in, one task through all six stages: GPT-5.4 screening, base-model probes, difficulty classification, a rollout group, terminal-state grading, and a GRPO update.

Figure 7 follows one candidate task that can potentially enter the training pool. For the Qwen3.8 27B full-parameter pool, GPT-5.4 first served as a solvability screen. The base policy then succeeded on few of the probes e.g 3 of 8, producing a Beta(3.5, 5.5) posterior. Its largest mass, 54.0%, fell in the Difficult band.

When sampled for training, the task produced the mixed reward group [0, 0, 0, 0, 1, 1, 1, 1] . Successful trajectories therefore received above-mean task advantage and failed trajectories below-mean advantage, giving GRPO contrast to learn from. A different policy model could place the same task in a different difficulty band.

The final Qwen3.8-27B curated training pool contained 187 tasks.

What earns a reward

Nothing about the trajectory. The reward is the task's own executable verdict.

When an episode ends, the sandbox extracts what actually changed in the backend and runs the task's deterministic checks against the terminal state. Any trajectory that produces the correct end state passes. Wrong, missing, or extra side effects fail. The reward is 1 or 0.

In the benchmark, the database grader can be thought of as the “examiner”: it caught agents that reported success and left the wrong record. In training, the same kind of check can be seen as the “teacher” on a different, disjoint set of tasks.

Two reward paths, one binary verdict

Executable check (the large majority). When the required outcome is represented in terminal state or side effects, a deterministic test accepts or rejects it; no LLM judge call is needed. Judge-assisted check (a minority). When a narrow requirement cannot be determined cleanly from database state, the configured LLM judge answers a binary rubric question used by the executable test.

Run the training stack

We release the data-selection, rollout, reward, and Verl integration used to train Qwen3.8-27B in microsoft/thinkingbox-training . The repository README is the entry point. The detailed guides are:

docs/data-preparation.md for task hydration, policy probes, benchmark exclusion, and train/validation splitting;

docs/reference-q38-run.md for the validated 24-H100 Qwen3.8 configuration;

docs/evaluation.md for merging a checkpoint and running ThinkingBox-Bench 507 x 20.

Before you start

Tested on Linux and WSL with Python 3.12 and uv . You need NVIDIA GPUs with a compatible CUDA/NCCL stack, a local Qwen3.8-27B checkpoint, and OpenAI-compatible endpoints for the simulated user and judge. The validated reference configuration uses 3 nodes x 8 H100 GPUs; smaller custom configurations depend on model size, context length, and rollout concurrency.

The public sample task list exercises the interface. It is not the private 187-task training pool used for the reported run. Supply an authorized training source that remains disjoint from the public benchmark.

Install

Keep the three repositories side by side:

Create the validated environment

The released stack targets Linux, Python 3.12, Verl 0.9.0, and the pinned package lock:

The final two commands should report a verified patched Verl checkout and no broken requirements. Do not run another automatic package sync afterward: it can replace the patched source installation with the vanilla Verl wheel.

Prepare the training data

Start with the publicly provided samples, or add your own authorized dataset in ThinkingBox format. Then run the repository's preparation script:

The script aggregates policy probes, applies offline policy-relative difficulty filters and benchmark exclusions, and writes the selected train.yaml and test.yaml files. docs/data-preparation.md documents the input fields, loader contract, and complete command.

Configure and inspect the launch

Follow docs/reference-q38-run.md to start Typesense and the MCP servers, configure the simulated user and judge, set the model, task-list, checkpoint, and topology variables, and prepare the Ray cluster. Keep credentials in runtime secret injection rather than committed files or shell history.

Before allocating a training job, use the guide's dry-run command:

It must exit zero without starting Ray or allocating GPUs. Read the emitted python -m verl.trainer.main_ppo command and every resolved override before launching the run.

Train

The launcher configures training; it does not provision hosts. On the reference three-node topology, export the same environment on every node, mount CHECKPOINT_DIR at the same absolute path, then start Ray:

After ray status reports all 24 GPUs, launch once from the head node:

Evaluate the checkpoint through OpenEnv

The first ThinkingBox post covers Typesense, the MCP Session Proxy, and OpenEnv setup. Merge the trained checkpoint following docs/evaluation.md , then serve it with vLLM.

From the OpenEnv repository root, set MERGED_MODEL to the merged model directory and THINKINGBOX_DATA to the pinned benchmark checkout. The historical checkpoint evaluation used this eight-A100 serving configuration:

In a separate terminal, start the OpenEnv compatibility proxy for the Qwen chat template from the ThinkingBox Training checkout. It listens on port 8014 and forwards to vLLM on 8001:

Keep it running during evaluation. From another terminal, check readiness:

Update the agent entry in the existing thinkingbox.yaml ; retain its MCP, simulated-user, and judge configuration:

Start OpenEnv as in the first post, with OPENENV_TB_CONFIG pointing to this thinkingbox.yaml and OPENENV_TB_DATASET to $THINKINGBOX_DATA . Once /ready succeeds, run the full protocol of 507 tasks × 20 attempts:

The full profile validates all 10,140 expected task/repetition keys before aggregation.

Where this goes next

The useful part of this work is not one Qwen3.8-27B checkpoint. It is the training loop and training data curation that turns executable outcomes into rewards.

If you are training or evaluating an agent that touches real database records:

Probe before you train. Take your own agent task set, run the base policy against it n times, and look at the band histogram. In our experience teams often have not inspected this distribution, and it is usually more lopsided than expected.

Check your parity. Replay the same recorded model output through the training and evaluation parsers, and verify that both extract identical tool names and arguments. Otherwise, training may reward behavior that evaluation interprets differently.

Report both coverage and repeatability. State how many tasks pass at least once in k attempts and how many pass all k . A model that occasionally finds a solution is not necessarily one that repeats it consistently.

Further details can be found in the following links:

Environment: envs/thinkingbox_env

OpenEnv: ThinkingBox environment documentation

Framework: microsoft/thinkingbox · tutorial

Benchmark: microsoft/thinkingbox-data · v1.0 release

Dataset viewer: microsoft/ThinkingBox-Bench

Paper: arXiv:2608.19741 or HF

RL training: microsoft/thinkingbox-training

Blog: The Agent Said It Was Done. The Database Disagreed.

Cite the paper

ThinkingBox code is MIT-licensed; the benchmark data is CDLA-Permissive-2.0 .

Disclaimer: every task in the public benchmark is a synthetic reconstruction. The workflows and policies are modeled on real enterprise agent patterns; the customers are not real.

ThinkingBox, ThinkingBox-Bench and ThinkingBox-Training is built by the Microsoft Copilot Studio team in partnership with Toloka with collaborators from the University of Pittsburgh, Northwestern University, Columbia University and UC Irvine who interned at Microsoft. Questions are welcome in the comments section below or on github or by email at firstnamelastname@microsoft.com .

+ A minority of tasks also include narrow binary rubric requirements for outcomes that the database cannot capture cleanly; those checks can invoke the configured LLM judge.

++ That zero-gradient problem has a standard batch-time fix: oversample, discard the degenerate groups, refill. The full-parameter run did exactly that, similar to DAPO with replacement of zero-variance groups. But refilling still pays full price for every wasted rollout before throwing it away.

Datasets mentioned in this article 1

microsoft/ThinkingBox-Bench

Papers mentioned in this article 1

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

More from this author

The Agent Said It Was Done. The Database Disagreed.

Datasets mentioned in this article 1

microsoft/ThinkingBox-Bench

Papers mentioned in this article 1

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows