- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes EMO, a training-free framework that alternates per-question system-context optimization with token-level logits steering. An external judge provides feedback for context revisions. The target model then contrasts distributions under successive contexts at a shared prefix, applies a Jacobian-weighted log-ratio correction with a confidence mask, and feeds the steered response into the next update. Experiments cover eight models and six reasoning benchmarks. The paper reports a 9.10-point average gain over zero-shot decoding and a 1.58-point gain over context-only optimization, alongside nominal generation-budget comparisons and a conditional target-KL analysis.
Critical strengths
-
Useful improvements across several backbones. The comparison with context-only optimization controls the judge and candidate count, and steering improves MMLU-Pro accuracy for all eight models. This provides evidence that decoding interventions can add value to feedback-driven context updates.
-
Candidate generation and selection are evaluated separately. Reporting oracle coverage alongside selected accuracy reveals meaningful bottlenecks. For example, on Llama-3.1-8B/GPQA-D, EMO raises coverage to 73.7% versus 60.3% for independent sampling, despite generating fewer candidates.
Critical weaknesses
- Dependence on a stronger external judge. EMO relies on a 122B external judge for both feedback and candidate selection, while the target models are 3B–32B. The paper does not compare against directly using the judge as a solver, and its compute-matched comparisons exclude judge/rewrite overhead. This makes it difficult to assess whether EMO provides a meaningful efficiency or capability advantage over simply allocating computation to the stronger model. Erroneous judge feedback can also be amplified by subsequent context updates and steering.
- Insufficient isolation of the M-step contribution. The paper does not compare the proposed SVDecode-style Jacobian/KL steering against a simpler direct context-contrast baseline using the same . Without this comparison, it is unclear whether the gains come from the proposed steering geometry, from simply amplifying successive-context differences, or from the confidence mask.
- The motivation for steering is not empirically diagnosed. Although EMO improves over context-only TextGrad on average, the paper does not show that these gains arise specifically when the optimized context contains the right guidance but ordinary decoding fails to realize it. Per-instance case studies or analyses of TextGrad-fail/EMO-success examples are needed to establish the claimed learning–execution gap.
- Judge feedback and selection are confounded. Replacing the external judge changes both the feedback used for context optimization and the final candidate selection rule, so the current ablation cannot determine whether gains come from better adaptation or simply stronger reranking.
[1] Jerry Zhi-Yang He, Sashrika Pandey, Mariah L. Schrum, and Anca Dragan. Context Steering: Controllable Personalization at Inference Time. ICLR 2025.
[2] Senkang Hu et al. Distribution-Aligned Decoding for Efficient LLM Task Adaptation. NeurIPS 2025.
Questions for authors
-
How does EMO compare with directly using the external judge as the solver under a comparable end-to-end compute budget? The main experiments use Qwen3.5-122B-A10B as the external judge for both feedback and candidate selection, while the target models are 3B–32B, and the current matched-budget comparisons exclude judge/rewrite costs. If direct inference from the judge achieves comparable or better performance at similar total cost, this would substantially change how I interpret EMO’s practical value.
-
Is the SVDecode-style M-step actually necessary compared with a simpler direct context-contrast intervention? Given the same previous and updated contexts, a closely matched baseline could directly amplify the context-induced logit displacement, i.e., use z_new + beta * (z_new - z_old), similar to Context Steering / contrastive decoding. Can the authors compare this with the proposed Jacobian/KL-based steering under the same confidence mask and tuning budget? This would clarify whether the gain comes from the proposed steering geometry or simply from amplifying successive-context differences.
-
What evidence shows that EMO specifically addresses a failure of execution rather than a failure of context optimization? Among cases where TextGrad fails but EMO succeeds, how often does the optimized context already contain the correct or useful guidance, while ordinary decoding fails to realize it and steering changes the outcome? A case-level or aggregate analysis of these TextGrad-fail/EMO-success examples would materially affect whether the motivation for steering is supported by the experiments.
-
Can the effects of judge feedback and candidate selection be disentangled? In the current “w/o Judge” ablation, replacing the external judge changes both the feedback used to update the context and the mechanism used to select the final response, so the reported difference conflates adaptation quality with reranking quality. Can the authors report results that vary feedback source and selection source separately, or otherwise clarify how much of the gain is attributable to each role?
7 comments
Response for W1&Q1 (Part I): Auxiliary-Model Roles and Direct-Solver Reference
1. Why use a stronger auxiliary model?
TextGrad uses a Backward Engine to produce textual gradients and a Textual Gradient Descent optimizer to revise text variables. Its prompt-optimization experiment uses GPT-4o. We follow this division of roles, while optimizing context per question rather than learning one task-level prompt. The stronger model's task understanding motivates using it to diagnose responses and guide context updates. TextGrad §3.3
Our Qwen3.5-122B-A10B-FP8 auxiliary checkpoint has approximately 10B active parameters per token. In the main experiments, its three operations use greedy decoding with thinking disabled:
| Role | Input | Output |
|---|---|---|
| Textual backward / Backward Engine | Question, context, target response | Textual gradient for the context |
| Context rewriting / TGD optimizer | Context and textual gradient | Revised context |
| Candidate evaluation | Question and one target candidate | Score and evaluation rationale |
No auxiliary call receives gold answers. The scoring rationale is separate from the textual gradient and is not used for rewriting. Selection uses scores, with earliest-round tie-breaking. The target generates every candidate with frozen weights. Four refinements produce R0–R4; the historical loop also executes a terminal context update, included in complete-run accounting.
2. Auxiliary-model access as a deployment expense
We view auxiliary-model access as an optimization/evaluation service alongside target serving. For an API deployment, its economic expense depends on input/output tokens and service prices. Equal total FLOPs compares resource efficiency, but does not fully determine monetary cost. This motivates reporting auxiliary usage separately while still charging all model calls in the compute account.
This perspective also charges BoN/SC for their scoring calls. EMO additionally uses backward and rewriting, and its per-question updates remain a recurring expense. Our current evidence records tokens, latency and estimated FLOPs; it does not establish a price-based advantage without a specified tariff and target-serving cost.
3. Direct solving with the same checkpoint
As requested, we give the same 122B checkpoint only the question and ask it to solve directly: greedy decoding, thinking off, and an 8,192-token cap (12,288 for AIME). These are full-set greedy runs. Per-query FLOPs are estimated as
\overline F=N^{-1}\sum_q\widehat F(q),\quad P_{\mathrm{active}}\approx10\mathrm B.$$ Input/output tokens come from saved successful API calls. The table reports confirmed-correct answers and mean estimated TFLOPs per query. This first-order proxy omits attention-length, routing and communication costs; it is not a hardware FLOPs measurement. | Dataset | Questions | Verified correct | Verified accuracy (%) | Estimated FLOPs (TFLOPs/query) | | --- | --- | --- | --- | --- | | MMLU-Pro | 560 | 488 | 87.14 | 31.63 | | GPQA-D | 198 | 154 | 77.78 | 83.35 | | MATH-500 | 500 | 479 | 95.80 | 31.28 | | GSM8K | 1319 | 1281 | 97.12 | 9.58 | | AIME-2025 | 30 | 23 | 76.67 | 124.35 | | AIME-2026 | 30 | 24 | 80.00 | 108.24 | Verified accuracy divides confirmed-correct answers by all questions; answers left unresolved by verification remain in the denominator. GPQA uses the corrected-input solver reference. We acknowledge that direct 122B solving outperforms EMO with either tested 8B target in the separate same-question sampled audit. The direct-solver results demonstrate strong task competence and support our choice of a capable feedback/evaluation model. They support the **capability premise behind this choice**; the effectiveness of its textual guidance remains an empirical question addressed by the ablations and role-separation analysis. EMO focuses on improving a specified frozen target with auxiliary guidance. Part II tests whether such improvement requires access to an external model at all.Response for W1&Q1 (Part II): Adaptation Without an External Model
The paper's “w/o Judge” ablation removes the external judge: the target checkpoint itself performs textual backward, context rewriting, scoring, and selection. “w/o Both” uses the same self-model roles with context-only TextGrad. All roles use the original greedy configuration; no 122B or other larger model is called.
We report the complete original-paper comparison below. Self-EMO and Self-TG each generate R0–R4 and retain their historical score-based selections. Acc measures the selected answer; Pass@5 measures whether the five-candidate pool contains a correct answer. Base is the initial unoptimized response. These are historical greedy runs, not three-seed means. Bold compares Base/Self-TG/Self-EMO accuracy and Self-TG/Self-EMO Pass separately within each dataset–target row.
| Dataset | Target / self model | Questions | Base accuracy (%) | Self-TG accuracy (%) | Self-TG Pass@5 (%) | Self-EMO accuracy (%) | Self-EMO Pass@5 (%) |
|---|---|---|---|---|---|---|---|
| MMLU-Pro | Qwen3-8B | 560 | 63.57 | 63.75 | 69.82 | 65.18 | 76.79 |
| MMLU-Pro | Qwen3-32B | 560 | 71.43 | 74.82 | 82.32 | 75.36 | 84.46 |
| GPQA-D | Qwen3-8B | 198 | 48.99 | 54.55 | 64.14 | 51.01 | 63.64 |
| GPQA-D | Qwen3-32B | 198 | 59.60 | 64.14 | 74.24 | 61.62 | 73.74 |
| MATH-500 | Qwen3-8B | 500 | 75.00 | 78.00 | 86.60 | 78.60 | 86.40 |
| MATH-500 | Qwen3-32B | 500 | 78.60 | 82.60 | 87.40 | 83.20 | 87.80 |
| GSM8K | Qwen3-8B | 1319 | 91.43 | 92.42 | 95.53 | 91.81 | 95.75 |
| GSM8K | Qwen3-32B | 1319 | 91.36 | 91.74 | 95.91 | 91.66 | 95.83 |
| AIME-2025 | Qwen3-8B | 30 | 16.67 | 20.00 | 43.33 | 26.67 | 50.00 |
| AIME-2025 | Qwen3-32B | 30 | 10.00 | 26.67 | 50.00 | 30.00 | 53.33 |
| AIME-2026 | Qwen3-8B | 30 | 23.33 | 30.00 | 66.67 | 36.67 | 70.00 |
| AIME-2026 | Qwen3-32B | 30 | 26.67 | 43.33 | 63.33 | 46.67 | 70.00 |
Self-EMO improves selected accuracy over Base in all 12 configurations. Giving each of the six datasets equal weight, Qwen3-8B increases from 53.17% to 58.32% (+5.16 pp), and Qwen3-32B from 56.27% to 64.75% (+8.48 pp). AIME-2025/2026 gains are +10.00/+13.33 pp for 8B and +20.00/+20.00 pp for 32B.
Relative to Self-TG, mean selected accuracy improves by 1.87/0.87 pp and Pass@5 by 2.75/1.99 pp for 8B/32B. Each model wins on four of six datasets in selected accuracy; GSM8K and GPQA do not show an advantage. These are descriptive macro averages, with each AIME edition counted separately, rather than significance tests.
The table retains the paper's original question sets, correctness, and candidate selections, including the full historical GPQA set. The results establish that external-model access is not necessary for obtaining improvements over the unoptimized target. They do not isolate feedback from selection, since both roles change together in the original ablation; the crossed-selector experiment in our W4/Q4 response addresses that distinction.
Overview of Our Responses to Weaknesses and Questions
Thank you for recognizing the improvements across backbones and the distinction between candidate coverage and final selection. We organize our responses around your four weaknesses and four corresponding questions, followed by the bibliography concern.
Historical tables retain the original grading and selections. New controlled experiments and cost measurements are identified separately. Each response below addresses the corresponding concern directly.