Prune to Probe: Causal Decision-Stability Probes for Efficient Reasoning
Organizations: New York University · Massachusetts Institute of Technology
Abstract
Reasoning models often continue generating after producing an answer, yet stopping prematurely may interrupt useful verification or revision. In this work, we investigate whether targeted interventions in a model's internal computation can provide a reliable signal for when to stop reasoning. We introduce Prune-to-Probe, an inference-time controller that uses causal activation interventions to probe the stability of a model's current answer. Specifically, we identify late-MLP coordinates that contribute to post-answer continuation while excluding those important for answer completion. Once an answer is stated, Prune-to-Probe temporarily suppresses the selected coordinates and measures the resulting stopping response relative to matched random interventions. Crucially, these interventions serve only as probes: the model either returns its existing answer or resumes generation from an untouched cache. On MATH, Prune-to-Probe reduces reasoning-token forwards by 2.60%, preserving all naturally correct trajectories while repairing six errors. On MMLU-Pro, it achieves 1.145% pooled savings with no observed harm. Further analysis shows that the intervention captures decision stability rather than correctness (AUROC 0.502). These results demonstrate the potential of causal activation probes for efficient inference-time control without permanent model modification.
Figures & tables
| Evaluation | Probe exits (correct / wrong) | Harm / repair | Charged savings |
|---|---|---|---|
| 8B MATH held-out | 86 (86 / 0) | 0 / 6 | 99.55 (2.60%) |
| 1.7B MMLU-Pro validation | 99 (64 / 35) | 0 / 4 | 35.58 (1.267%) |
| 1.7B MMLU-Pro confirmation | 91 (55 / 36) | 0 / 1 | 31.12 (1.032%) |
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
| Qwen3-8B held-out | Qwen3-1.7B initial test | |
|---|---|---|
| Evaluation trajectories | 512 | 128 |
| Correct pruning accepts | 86/86 | 60/63 |
| Harms / repairs | 0 / 6 | 1 / 6 |
| Charged saving | 2.60% | 18.04% |
| Specificity | 4.6722 | 7.4081 |
| Strict protocol | pass | fail |
| Metric | Validation | Confirmation | Descriptive union |
|---|---|---|---|
| Trajectories | 1,024 | 1,024 | 2,048 |
| Natural correct | 538 | 481 | 1,019 |
| Accepted: correct / wrong | 64 / 35 | 55 / 36 | 119 / 71 |
| Natural-correct harms / repairs | 0 / 4 | 0 / 1 | 0 / 5 |
| Charged saving per trajectory | 35.58 | 31.12 | 33.35 |
| Relative charged saving | 1.267% | 1.032% | 1.145% |
| State | Seed 54 stop effect | Seed 55 stop effect | Candidate-margin effect, seed 54 / 55 |
|---|---|---|---|
| Repetition | / | ||
| Verification | / | ||
| Revision | / | ||
| Alternative | / |
| Experiment | Model / precision | Accelerator | Purpose |
|---|---|---|---|
| 8B MATH evaluation | Qwen3-8B / BF16 | one A100 80GB PCIe | Validation and held-out evaluation |
| 8B diagnostics | Qwen3-8B / BF16 | one L40S | Seed, latency, and endpoint analyses |
| 1.7B localization | Qwen3-1.7B / BF16 | one L40S | Model-specific causal localization |
| 1.7B MATH evaluation | Qwen3-1.7B / BF16 | one L4 | Controller development and confirmation |
| 1.7B non-math evaluation | Qwen3-1.7B / BF16 | one L4 | Development, validation, and confirmation |
Efficient Language Model Reasoning
Efficient language model reasoning studies how to improve problem-solving accuracy while reducing inference, memory, latency, and training costs.
See all 393 papers