- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a new reflexive reasoning paradigm that leverages models’ internal representations through learned sensor and control tokens that propagate through the model’s forward pass. Experiments on reasoning and non-reasoning tasks using open-source models support the paper’s insights and demonstrate the effectiveness of the proposed paradigm.
Critical strengths
-
The results showing that sensor tokens can predict reasoning failures are interesting.
-
The evaluation covers both reasoning and non-reasoning tasks.
Critical weaknesses
-
The paper lacks ablation studies to isolate the contributions of the sensor and controller, and to compare performance with and without controller fine-tuning.
-
The novelty needs further justification. It is unclear how the proposed “introspective, closed-loop system” differs substantially from existing probing and continuous-token steering approaches. Such as: [1] Activation Steering with a Feedback Controller,ICLR 2026 [2] Programming Refusal with Conditional Activation Steering(CAST),ICLR 2025
-
The claim of “no added inference-time compute” is insufficiently supported. Sensor evaluation and control-token generation introduce additional computation.
Questions for authors
NA
4 comments
Author Rebuttal 2/2
W3. We agree that how we phrased our claim of “no added inference-time compute” was too drastic. We meant to illustrate that our method substantially enhances reasoning performance without expensive inference-time rollouts, re-generations, tree/beam search, or multi-turn self-correction. Indeed, our core contribution is to show that we can repurpose the LLM’s forward pass to manage its own targeted monitoring and intervention. To enable this closed-loop introspection, we add very lightweight linear classifiers and gates, corresponding to only 0.0125% additional parameters on top of Gemma-3 4B. This is a negligible increase of 0.038% extra FLOPs compared to standard discrete token generation. Still, we understand that detailed efficiency profiles of our method would be quite useful. Therefore we will include a complete efficiency panel on resource usage and latency for our method compared to soft prompting and the standard chain-of-thought baseline:
| Model | Method | Extra Params (%) | FLOPs/Token Overhead | Peak VRAM (GB) | Mean Output Tokens | Total Processed Tokens | Latency p50 (s) | Latency p95 (s) |
|---|---|---|---|---|---|---|---|---|
| Qwen3-0.6B | Greedy CoT | 0.000% | +0.00% | 1.85 | 377.8 | 498.2 | 2.45 | 3.82 |
| Soft Prompt (20 tokens) | +0.003% | +1.92% | 1.86 | 328.4 | 468.8 | 2.22 | 3.51 | |
| Reflexive Reasoning (Ours) | +0.019% | +0.04% | 1.86 | 233.2 | 361.6 | 1.68 | 2.74 | |
| Qwen3-1.7B | Greedy CoT | 0.000% | +0.00% | 4.12 | 383.6 | 504.1 | 3.88 | 5.92 |
| Soft Prompt (20 tokens) | +0.002% | +1.92% | 4.14 | 351.2 | 491.7 | 3.61 | 5.48 | |
| Reflexive Reasoning (Ours) | +0.015% | +0.04% | 4.15 | 183.9 | 312.4 | 2.15 | 3.42 | |
| Gemma-3-4B-IT | Greedy CoT | 0.000% | +0.00% | 9.42 | 203.2 | 323.5 | 3.12 | 4.85 |
| Soft Prompt (20 tokens) | +0.001% | +1.58% | 9.45 | 198.9 | 339.2 | 3.10 | 4.81 | |
| Reflexive Reasoning (Ours) | +0.0125% | +0.038% | 9.48 | 248.7 | 376.9 | 3.45 | 5.21 |
Finally, we will re-phrase the sentence stating “no added inference-time compute” to “Across multiple standard benchmarks, reflexive reasoning improves task performance across model architectures and sizes while keeping backbone weights frozen and operating within a single generation trajectory, without separate judge-model evaluations.”
Thanks for the response. I'd like to keep my score.
Could you explain why you would like to keep your score, considering that we directly addressed each weakness in your original review?
We added full "ablation studies to isolate the contributions of the sensor and controller, and to compare performance with and without controller fine-tuning" (table of comparisons with different sensor trigger mechanisms, a direct comparison of SFT only versus SFT+GRPO). We compared the novelty of our approach, in detail, with Activation Steering with a Feedback Controller, ICLR 2026 and Programming Refusal with Conditional Activation Steering (CAST), ICLR 2025. Finally, we add a full efficiency profiling table to more fully support our claim of “no added inference-time compute”, and we soften the language to avoid over-claiming on the efficiency front.
We are happy to further clarify any additional points. Thank you for your time.
Author Rebuttal 1/2
We thank the reviewer for their thoughtful comments, and appreciate that they found our method interesting across a breadth of reasoning and non-reasoning tasks.
W1. We acknowledge that it may be beneficial to include additional controls and ablations. As such, we present new control experiments on random, periodic, fixed-rate, and unconditional control-token insertion. We find that our adaptive, sensor-driven insertion approach outperforms these methods comfortably, avoiding damaging insertions and only inserting control tokens at points that are helpful for reasoning recovery.
Qwen3-0.6B control token insertion variants on GSM8K test set
We also report new results comparing SFT-only and SFT+GRPO sensor/control token training. We find that the additional GRPO step is essential for learning a robust and generalizable control token insertion policy. SFT serves as a useful warmup but is not sufficient by itself. We will add these results to the Appendix.
Qwen3-0.6B GSM8K test set pass@1 accuracy, SFT vs GRPO
W2. We thank the reviewer for pointing out these related recent works. While the general idea of closed-loop control of LLM generation is not by itself novel, we believe that our novel contribution lies in how to implement this idea efficiently: using the frozen transformer itself to perform both learned state sensing and recurrent, on-the-fly construction of context-dependent interventions. In particular, prior activation steering techniques (such as CAST and feedback controller steering) operate by patching intermediate hidden states with additive offsets at specific layers. In direct contrast, our approach operates strictly within sequence space, taking advantage of the recurrent, autoregressive nature of the transformer and the full capacity of its representation space to monitor its own reasoning trajectory and design control adjustments on-the-fly. This last piece is important: each successive control token is formed by the LLM, conditioned on the intermediate hidden state of the preceding control token and the entire sequence prefix, allowing the intervention to adapt to the evolving generation context rather than applying a static vector offset. CAST by contrast relies on clamping activations along fixed, pre-extracted semantic directions, making it naive to the model’s own preceding generations. This is a fundamental difference in philosophy. Traditional activation steering approaches could be thought of as operating in static activation space, whereas our approach effectively leverages the essential temporal aspect of the transformer. We are convinced that respecting the temporal nature of the LLM is necessary to enable robust control, and indeed this approach has allowed us to explore more difficult reasoning tasks such as math, formal logic, and code which were not explored in CAST or the feedback controller paper (tested on simple refusal tasks, not complex reasoning).
Further, we show that our learned continuous sensor token captures trajectory-level derailment far more effectively than traditional linear probes; as reported in Section 4.1 and Figure 2A, the sensor achieves an AUC of 0.807 on GSM8K failure prediction, significantly outperforming both a trained linear probe on preceding hidden states (AUC 0.695). Taken together, we believe that our approach opens the door to harness the LLM’s representation space and recurrent nature to build more complex and programmable reasoning machines for monitoring, control, and capability enhancement. We will add these comparisons to the updated Related Work section to better highlight the novelty of our approach.