- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper is about hybrid reasoning in LLMs. The authors use intermediate reasoning steps as explicit text tokens or latent hidden states and investigate which type of reasoning step works better with each representation and why. Experiments reported show that search and planning steps work better in latent representation and that calculation and verification steps work better as explicit text. They explain this by noting that latent states can keep several candidate paths at once and explicit tokens keep exact values more reliably. Based on these results, the authors propose Function-Adaptive Hybrid Reasoning. The training has three stages. First, they fine-tune the model to support both modes. Second, they train a router supervised by human labels of step types. Finally, they refine the router with RL under a compute budget. At inference time, the router chooses at each step whether to continue, switch mode, or give the final answer. The authors evaluate this method on 8 models and 12 benchmarks.
Critical strengths
- The question the paper is addressing is clear and useful. Instead of just considering the moment of switching between latent and explicit representations, this paper asks which content and steps benefit more from either latent or explicit modes. This is a more meaningful approach for hybrid reasoning.
- A good analysis with well-defined controls is provided. The authors compare the outcomes of different modes on reasoning steps. They support the main idea of the paper by showing that the type of step is more informative than its position. They also show that this preference flips when the number of candidates or exact values in the tasks are changed.
- The evaluation is broad covering different models and benchmarks, and the proposed method improves over CoT-RL on all of the settings.
Critical weaknesses
- Several works with similar ideas have not been cited and compared such as SWITCH (arXiv 2606.13106), LaTER (arXiv 2605.07315), and SwiReasoning (arXiv 2510.05069). The authors should explain the novelty of their work compared to these similar and recent works and add direct comparisons.
- The function-based supervision as one of the main contributions of the work adds little to the final performance. The supervised router beats the no-label router by a small margin. Also, a simple MLP trained on hidden states, and without fucntion labels is performing at the same level.
- Speed and efficiency claims are not measured and backed up with real wall-clock timings. The claims are based on the cost model and should be supported by real timing numbers at realistic settings. The authors’ own serving estimates show that mixing modes in a batch increases latency and lowers throughput.
- The pipeline has many separate steps: latent-capability training, preference measurement, human annotation, control-token grounding, router training and RL. It also relies on up to 8,000 function labels from student annotators and a fixed set of 8 functions, three of which show no clear mode preference. This makes the method expensive to apply to new domains, especially for a small gain.
Questions for authors
- How often does the router switch per problem on average, and what share of steps is latent vs explicit on different tasks? A few example routes showing where switches happen would help readers understand the learned policy and its impact in action.
- Search and planning steps become latent and cannot be read by users. Have the authors considered decoding or inspecting these latent steps, and how do they see this trade-off for settings where reasoning traces need to be checked?
8 comments
Two observations connect this principle to the representation. First, neighboring pre-decision states agree on the sign of the mode advantage 79% of the time, versus 51% after label permutation (§4.2). Second, increasing the number of viable candidates from 1 to 8 moves latent-minus-explicit quality from +0.1 to +3.5 points, while increasing the number of exact fields from 0 to 8 moves it from +2.4 to −3.0 (Fig. 3c–d). On calculation steps, forcing the router’s chosen action at the same state scores 10.6 points above forcing the opposite action (§7.6, Fig. 7b). These results motivate the local model , where is the demand to retain viable candidates and the demand for exact reuse. The useful boundary is the point at which the relative value of these demands changes enough to justify switching.
3. Function-informed initialization gives each proposed boundary a testable rationale
We use the observed preferences to initialize the router. On one frozen capability checkpoint, we force latent and explicit continuations to estimate the relative benefit of each mode for each function. Stage 2 combines those estimates with the segment’s functional labels, downweights uncertain differences and accounts for the cost of switching. At inference the router reads the current state, mode and remaining budget (§5.2, Eq. 2). This gives the initialization a concrete interpretation. A latent span is proposed because keeping an alternative available is expected to improve the continuation.
The published rules give uncertainty different roles in choosing a reasoning mode. SWITCH uses high next-token Shannon entropy to label contiguous spans of written CoT during initial training. At inference the model emits learned boundary markers. SwiReasoning uses a relative signal at inference. Once the current mode has lasted long enough, entropy rising above the block reference can trigger explicit → latent, and entropy falling below it can trigger latent → explicit. ThinkRouter takes a different action when confidence is low. If the maximum next-token probability falls below the threshold, it samples a discrete token to avoid mixing incompatible continuations. At or above the threshold it feeds back a probability-weighted embedding. SwiReasoning uses a soft embedding to keep alternatives open during exploration. ThinkRouter points out that mixing mutually exclusive moves can introduce noise. Both concerns can arise at different points in one problem. These choices give us reason to question whether a single direction of uncertainty can reliably tell us when latent CoT will help. Entropy measures how dispersed the next-token distribution is, its change is relative to a block's history, and maximum probability measures only its peak. Each leaves open a consequential question about the alternatives receiving that probability mass. Some should remain available until later evidence arrives. Others prescribe incompatible actions for a decision that the evidence already settles. Thank you for prompting us to make that distinction concrete.
sample
One broadcast archive lets us vary the reasoning demand while keeping the facts fixed. An archivist must identify the cut of a documentary that aired at 20:00. The playout log names reel R17, which the catalogue assigns to the Harbor cut. An independent recording opens with a bell and ends with rain. Moor shares the bell and Vale shares the rain. Only Harbor has both. The same file contains three signed notices. The web copy WEB-71 was cleared at 19:30 and placed on hold at 19:45. The archive master ARC-17 was cleared at 19:50. For each copy, its own latest signed notice governs.
Table W2.1. Two questions about the same archive, at higher and lower pre-action vocabulary entropy
| Pre-action vocabulary entropy | Keep two valid ways to identify the cut. Predicted L / E success | Carry forward one binding decision. Predicted L / E success |
|---|---|---|
| High, if observed | The log and the recording offer equally plausible starting points. Which cut aired, and can the model still justify it if the editor later accepts only one source? Either the reel lookup or the two sound cues establish Harbor. 74% / 71% | The web clearance, the later web hold and the master clearance are interleaved. Should the model clear or hold the web copy? Both actions have textual support, but only WEB-71 · HOLD · 19:45 satisfies the rule. 70% / 73% |
| Low, if observed | The playout entry sits beside the reel index, making a reel lookup an obvious first move. Can the model still identify Harbor from the bell and the rain if the editor later requests audio evidence alone? 78% / 76% | The two web notices now appear together in time order. HOLD is easy to anticipate. Four catalogue entries later the model must still give WEB-71 · HOLD · 19:45. Substituting the master's ID or time fails. 75% / 78% |
L / E denotes success under a forced latent / explicit reasoning window. The percentages are illustrative targets for held-out groups of source files. Each example describes a candidate test item. Its entropy stratum and the better mode both await measurement. Example questions and answer keys
The low-entropy candidate case is particularly informative. A model can be confident about a substantive first move, looking up R17, while having good reason to keep the acoustic proof available. Conversely, in the high-entropy exact case, hesitation between two well-supported words cannot give two conflicting web decisions equal authority. A scalar uncertainty rule must assign the same action probabilities at identical signal values. If latent mode gains points on a fraction of such states and explicit mode gains on the remainder, its smallest expected loss against a policy that recognizes the demand is .
The submitted comparisons show a routing gain and identify the tasks that benefit
<a id="w2-diagnostic-en"></a>
Table W2.2. Hybrid and routing baselines. Reported in the submission, Qwen3-8B.
| Method | Routing quality (%) | Hybrid-Full minus row (pp) |
|---|---|---|
| Entropy | 64.5 | +4.8 |
| Confidence | 65.2 | +4.1 |
| Router without function labels | 66.3 | +3.0 |
| TARPO* | 67.5 | +1.8 |
| ThinkRouter* | 65.2 | +4.1 |
| SLT* | 65.5 | +3.8 |
| System-1.5* | 66.5 | +2.8 |
| Hybrid-SFT | 67.1 | +2.2 |
| Hybrid-Full | 69.3 | 0.0 |
On this routing diagnostic, Hybrid-Full scores 69.3%, which is 1.8 points above TARPO*, the strongest named adaptation, and 4.8 points above the entropy rule. Estimated compute is 0.70 for Hybrid-Full and 0.76 for TARPO*. We agree that the asterisks in D.6 gave readers too little information to judge implementation fidelity.
Table W2.3. Two pure-mode baselines and Hybrid before and after router RL on every core task. Reported, Qwen3-8B.
| Core task | Explicit CoT-RL | Pure latent | Hybrid-SFT (pre-RL) | Hybrid-Full (post-RL) | Post − pre (pp) |
|---|---|---|---|---|---|
| GSM8K | 93.5 | 87.1 | 93.2 | 93.8 | +0.6 |
| MATH-500 | 85.8 | 77.6 | 88.1 | 90.7 | +2.6 |
| AIME 2025 | 62.2 | 43.3 | 62.2 | 63.3 | +1.1 |
| AIME 2026 | 55.6 | 38.9 | 55.6 | 55.6 | 0.0 |
| HumanEval+ | 76.4 | 68.1 | 77.0 | 77.2 | +0.2 |
| MBPP+ | 79.9 | 72.3 | 81.2 | 82.8 | +1.6 |
| LiveCodeBench v6 | 51.2 | 40.6 | 51.0 | 53.2 | +2.2 |
| GPQA Diamond | 54.5 | 49.0 | 56.6 | 58.6 | +2.0 |
| MMLU-Pro | 66.6 | 61.9 | 66.7 | 67.0 | +0.3 |
| BBEH | 31.5 | 30.0 | 34.2 | 36.1 | +1.9 |
| IFEval | 76.8 | 73.6 | 76.5 | 76.0 | −0.5 |
| MuSiQue | 46.9 | 41.3 | 47.6 | 50.1 | +2.5 |
| Equal-task macro | 65.1 | 57.0 | 65.8 | 67.0 | +1.2 |
App. D.7 (p. 18) reports these scores in the three-seed Qwen3-8B setting. Scores are percentages of each task’s official metric, including exact match on MuSiQue and a within-task balanced macro on BBEH. The bottom row equally weights the 12 displayed task scores and is shown to one decimal. These point differences do not supply paired significance tests.
6m7C · W1 — Relation to SWITCH LaTER and SwiReasoning
与 SWITCH LaTER 和 SwiReasoning 的关系
**Original concern **
Thank you for pointing us to these closely related methods. SWITCH already learns repeated transitions, which makes your question especially valuable: what does Hybrid explain about choosing a boundary? We are pleased to share two findings that motivate our design. With four viable candidates, the effective candidate count was 2.74 in latent states and 1.31 in explicit states. Four steps after an exact value was established, explicit execution recovered it in 81.4% of cases and latent execution in 42.8%. This reversal motivates using the information required by the next operation to initialize routing. The comparison with native SWITCH below tests the practical value of that principle.
1. We identify why latent CoT can outperform explicit CoT during search and planning
A latent step feeds a projection of the current hidden state into the next Transformer update. An explicit step feeds back the embedding of one selected token. Both retain a continuous cache. The distinction matters before a problem has been resolved. Committing to one written approach can make another viable approach harder to recover. With four verifiable solution paths, the effective candidate count at a decision state is 2.74 in latent mode, 1.31 in explicit mode and 1.08 after shuffling latent states (Fig. 3a, p. 4). Candidate information is denser in this diagnostic in a specific sense. More distinct continuations remain accessible from the same decision state.
We then tested whether that information actually helped solve the problem. When later evidence required a particular path, removing its aligned component reduced success by 25.1 points. Adding the same component back restored success to 71.2%, compared with 79.0% under sham (Fig. 7e–f, p. 9). The route-by-erasure interaction is −8.4 points (reported interval [−11.2, −5.7], App. I, p. 26), further connecting the damage to the choice of reasoning mode. Conversely, when the task required exact reuse of a numerical value four steps later, explicit CoT succeeded 81.4% of the time and latent CoT 42.8% (Fig. 3b). Together, these findings explain why alternating the two modes can help within a single solution. The model can defer commitment while several approaches remain useful, then write down the value on which subsequent steps depend.
2. The interventions and ablations locate useful switches where the information demand changes
Retrieval/search, planning/decomposition and hypothesis enumeration favor latent reasoning while the next step still depends on exploring alternatives. Exact calculation, entity binding and constraint checking give the model a reason to switch to explicit reasoning. Fig. 2d reports latent preferences for the first three operations and explicit preferences for calculation and verification. Summarization, comparison and revision vary by instance. This also explains why a calculation near the start can favor explicit CoT and a new search near the end can favor latent CoT. The order in which those operations happen can change within the same problem (§7.4).