Artificial Intelligence · arXiv:2611.16414 v1 · submitted 12 Nov 2026 · 15 references
Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency
The paper says
“Optional reasoning, retrieval, web search, and tool use can improve large language model responses but incur unnecessary computation when activated indiscriminately.”
more of the abstract
This study investigates whether prompt optimization can compensate for limited router capacity and whether classification gains translate into downstream efficiency. The proposed framework uses prompt-driven small language models to make four independent capability decisions, allowing multiple capabilities to be selected per query. Qwen2.5 routers ranging from 1.5B to 14B parameters are compared across five prompting strategies, followed by an evaluation of capability-specific optimized configurations using a fixed GPT-OSS-120B downstream model on 127 questions. Under minimal prompting, increasing router capacity does not consistently improve classification performance. Prompt optimization narrows the capacity gap for reasoning and calculator routing, whereas RAG and web search retain larger benefits from higher capacity. Similar classification F1 scores do not necessarily imply equivalent downstream behavior: false-positive activations increase unnecessary computation, while missed capabilities can reduce answer quality. The 14B router achieves a mean BERTScore F1 of 0.8408, compared with 0.8418 when all capabilities are enabled, while reducing average downstream token consumption by 68.7% (8,837 to 2,764 tokens) and median downstream latency by 80.5% (9.79 to 1.91 seconds). These savings exclude router overhead, which is measured separately in a different inference environment and increases with router capacity. The findings demonstrate that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent. Consequently, router selection must consider error profiles and routing overhead alongside classification performance.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
Holds up, with conditions. Solid empirical comparison of router capacity and prompting for capability routing, but the headline efficiency numbers in the abstract are not independently validated due to circular prompt selection—the paper acknowledges this, but the abstract overstates. This line is wrong
4 major objections · 7 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 15 references say.
The paper says, at §3.4, Table 2, b166
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.91):
“Because the prompting strategy for each capability was selected using the final RQ2 evaluation results rather than an independent validation set, the RQ3 compar- ison is interpreted as exploratory rather than as an independently validated estimate of generalization per- formance.”
Pith says: Objection 1 of 4 · major
The RQ3 efficiency figures (68.7% token reduction, 80.5% latency reduction) rest on prompt configurations selected using the RQ2 test set, which overlaps substantially with the RQ3 benchmark (Table 2 shows 80+ overlapping question-capability pairs per capability). The authors label this 'exploratory' in §3.4, but the abstract and conclusion present the quantitative savings without this caveat.
more of objection 1
This circularity means the reported gains are not an independent estimate and likely overstate what would be observed on truly held-out data. To support the headline claims, the authors must either: (a) re-run RQ3 with prompt configurations selected on a held-out validation set that is disjoint from the RQ3 benchmark, or (b) explicitly qualify every appearance of the 68.7%/80.5% numbers with a statement that they are exploratory and may not generalize.
The paper says, at §5.4, b258, b273, b274, b288
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.92):
“Because BERTScore measures semantic similar- ity rather than factual, numerical, or task correctness, these values should not be interpreted as demonstrating equivalent or preserved answer quality [13].”
Pith says: Objection 2 of 4 · major
The paper repeatedly acknowledges that BERTScore measures semantic similarity, not factual/numerical correctness, and that small differences do not establish statistical equivalence. However, the narrative in the abstract and conclusion relies on BERTScore to claim that the routed systems 'match' the ALL_ON condition.
more of objection 2
This tension is unresolved. The ALL_OFF condition also achieves a numerically similar BERTScore (§5.4), which suggests the metric may be insensitive to the very capabilities the router is designed to allocate. The authors should either provide task-specific correctness metrics (e.g., accuracy on arithmetic, retrieval precision) or tone down the quality-equivalence language throughout.
The paper says, at §3.2, Table 3, b326
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.84):
“The scope of the downstream benchmark further lim- its generalization.”
Pith says: Objection 3 of 4 · major
The downstream benchmark contains only 127 questions from a single domain (pharmaceutical regulation), with highly imbalanced capability labels (e.g., only 10 web-search-required examples). The authors acknowledge this limitation (§6, b326). Nonetheless, the paper's significance claims are stated broadly. The narrow scope should be clearly stated in the abstract and conclusion, and the reported savings should be interpreted as specific to this benchmark, not as general evidence for the efficiency of the proposed routing approach.
The paper says, at §3.4, §6, b323
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.75):
“Second, the reported downstream savings exclude router overhead, which increased with router capacity.”
Pith says: Objection 4 of 4 · major
The headline efficiency numbers (68.7% token reduction, 80.5% latency reduction) refer only to downstream computation; router overhead is reported separately and increases with capacity (Fig. 8 shows 14B router median latency ~5.56s). Because router and downstream inference were measured in different environments (Colab vs. AWS Bedrock), no controlled end-to-end comparison is possible. The abstract should state explicitly that the reported savings exclude router overhead and that total system latency may be higher for larger routers.
7 minor objections
The paper says, at Abstract
Pith says: minor objection 1 of 7
The abstract refers to 'GPT-OSS-120B' without a citation or explanation. Provide a reference or clarify the model provenance.
The paper says, at §3.2, Table 1
Pith says: minor objection 2 of 7
The train/validation/test splits are highly imbalanced (e.g., reasoning has only 94 training examples vs. 752 test examples). Justify this split or discuss its implications for prompt optimization reliability.
show 5 more
The paper says, at §4
Pith says: minor objection 3 of 7
The reproducibility section mentions saving intermediate predictions to Excel checkpoints but does not state whether the code or prompts will be publicly released. State availability of code and data artifacts.
The paper says, at §5.4, Table 10
Pith says: minor objection 4 of 7
The confusion counts for 1.5B calculator show 65 false positives, but the downstream system may still avoid invoking the calculator. This nuance should be discussed in the main text rather than deferred to the caption.
The paper says, at §5.4, Figure 5
Pith says: minor objection 5 of 7
Figure 5 shows 'mean BERTScore F1' without error bars or confidence intervals. Provide per-question variability (e.g., standard deviation or box plots) to indicate spread.
The paper says, at §A.2
Pith says: minor objection 6 of 7
The appendix provides representative prompts, but the full set of 80+ capability-model-prompt combinations is not included. At minimum, include all GEPA-optimized prompts in an ancillary file.
The paper says, at §3.2
Pith says: minor objection 7 of 7
The RQ1/RQ2 dataset originally had 3,573 records; after audit, 58 were excluded. The text states the audit 'identified 25 duplicated question-capability pairs with conflicting labels, corresponding to 58 records.' Clarify why 25 pairs yield 58 records (some may have more than 2 occurrences).
What would settle it
Identify the set of RQ3 questions that do NOT appear in the RQ2 test set (i.e., no overlap). Since Table 2 gives overlap per capability at the question-capability level, a conservative approach: remove all RQ3 questions that overlap ANY capability in the RQ2 test set. On the remaining held-out subset, recompute the 14B router's average downstream token consumption, median downstream latency, and BERTScore F1 relative to ALL_ON and ORACLE. If the token reduction drops below 50% or the latency reduction below 60% of the reported values (68.7% and 80.5%), the original efficiency claim is an artifact of test-set contamination.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic partly agrees
- Editor wrote the verdict above
- Referee major revision: 4 major objections, 7 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
Here is my take on this paper.
What is actually new: a systematic within-family comparison (Qwen2.5 1.5B–14B) of router capacity and five prompting strategies for four independent capability decisions (reasoning, RAG, web search, calculator), plus a downstream evaluation that links classification error profiles to token and latency costs. The decomposition into independent binary decisions and the emphasis on False Positive/False Negative profiles matter for practical deployment. The paper is honest about its limitations; it flags the test-set contamination for prompt selection in §3.4 and the BERTScore insensitivity in §6. I appreciate that they actually report confusion counts and output reliability (unknown/error rates), not just F1.
The load-bearing soft spot is the RQ3 prompt selection: the authors used the RQ2 test set – which overlaps with the RQ3 benchmark questions – to pick the prompt for each capability. They call RQ3 'exploratory' in the text, but the abstract and conclusion present the 68.7% token reduction figure without that qualifier. That's a real discrepancy. The stress-test note is correct: the savings likely shrink on truly held-out questions. The paper's own Table 2 shows 80+ overlapping question-capability pairs per capability. Even with label harmonization, the prompt was optimized on data that includes those same questions. So the central quantitative claim lacks independent validation.
Other issues: the benchmark is small (127 pharmaceutical questions) and domain-specific, with only 10 web-search-positive cases. BERTScore differences are tiny (0.8390 vs 0.8408) and the paper acknowledges BERTScore may not capture factual correctness. The ALL_OFF condition also achieves a numerically similar BERTScore, suggesting the benchmark may not require these capabilities at all—a point the authors raise but do not resolve.
That said, the RQ1/RQ2 results are cleaner and the overall design is sound. The paper is not claiming more than the evidence supports in those parts. The authors think clearly and are transparent about limitations.
Who this is for: researchers building adaptive inference pipelines or studying SLMs for routing. A serious referee would want to see RQ3 repeated with proper train/valid/test splits before accepting the efficiency claims.
Recommendation: send to peer review, but flag that the RQ3 results need independent validation before the efficiency numbers can be taken at face value. The rest of the paper is publishable after minor revision to tone down the abstract claims.
The strongest objection
The central quantitative claim (68.7% token reduction, 80.5% latency reduction with minimal BERTScore drop) rests entirely on RQ3, where prompt configurations were selected based on the RQ2 test set (b166). Critically, the RQ2 test set and RQ3 benchmark overlap in questions: Table 2 shows 80+ overlapping question-capability pairs per capability. The paper harmonized labels but used original router outputs for RQ3. This means the prompt configurations were optimized (via F1 on RQ2 test) on data that includes the same questions later evaluated for downstream efficiency. Even if the labels were corrected post-hoc, the original router outputs were generated before correction, and the prompt selection process was influenced by those same questions' classifier performance. Hence the RQ3 efficiency numbers are not an independent estimate: they likely overstate gains because the router was effectively tuned to perform well on the evaluation set. The paper labels this 'exploratory' but the abstract and conclusion present the 68.7% number without qualification. This is the most load-bearing weakness: if the prompt configurations degrade on truly held-out questions, the headline resource savings may shrink or disappear.
The reader correctly identified the lack of independent prompt validation as the weakest assumption. I agree this is the most load-bearing concern for the headline efficiency claim. My analysis adds the specific overlapping-data dimension, which makes the contamination more severe than a simple train/test split issue. The reader's CONDITIONAL verdict appropriately flags this; my concern does not change the verdict but sharpens the condition for acceptance: the paper must either rerun RQ3 with proper held-out prompt selection or, minimally, recompute savings on the non-overlapping subset. If the savings survive that test, the conditional can be lifted. If not, the central quantitative claim is unsupported. The paper's own acknowledgment that RQ3 is 'exploratory' aligns with this view.
The referee's report
If the findings are validated, the paper demonstrates a promising approach to capability-aware routing that can substantially reduce downstream computational cost with minimal degradation in semantic similarity. The decomposition into four independent binary classifiers and the systematic comparison of router capacity and prompt strategies are methodologically sensible. The within-family comparison reduces architectural confounds, and the authors are transparent about several limitations.
Pith's reading of the paper (a machine's summary, not the authors')
This paper investigates whether small language models, guided by carefully designed prompts, can decide which inference capabilities (reasoning, retrival, web search, calculator) to activate for each query before a large downstream model generates an answer. The authors find that prompt optimization can compensate for limited router capacity on reasoning and calculator decisions but not on retrival-augmented generation or web search, where larger models retain a clear advantage. In a downstream evaluation on 127 pharmaceutical questions, a 14B parameter router prompt-optimized per capability achieved a mean BERTScore F1 of 0.8408, essentially matching the 0.8418 of always-on capabilities, while reducing average downstream token consumption by 68.7% and median latency by 80.5%. However, the authors acknowledge that the prompt configurations were selected using the same test set on which they were evaluated, making the efficiency estimates exploratory rather than independently validated.
What carries the argument. The central machinery is a set of four independent binary classifiers, each a Qwen2.5 small language model (1.5B, 3B, 7B, or 14B parametersution) that decides whether to enable a specific capability: reasoning effort, retrieval-augmented generation, web search, or calculator access. The classifiers are driven entirely by prompts — five strategies are compared (Minimal Baseline, Descriptive SME, DSPy Baseline, DSPy Few-Shot, and GEPA) — with no weight updates. The downstream model is a fixed GPT-OSS-120B, and the evaluation uses BERTScore for semantic similarity, token count, and latency to link routing decisions to downstream consequences.
Core claim. The paper establishes that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent. Under minimal prompting, larger router models do not consistently outperform smaller ones. Prompt optimization narrows the capacity gap for reasoning and calculator routing, but RAG and web search retain larger benefits from higher capacity. Crucially, similar classification F1 scores do not necessarily imply equivalent downstream behavior: false-positive activations increase unnecessary computation, while missed capabilities can reduce answer quality. The 14B router achieves a mean BERTScore F1 of 0.8408 compared with 0.8418 when all capabilities are enabled, while reducing average downstream token consumption by 68.7% (from 8,837 to 2,764 tokens) and median downstream latency by 80.5% (from 9.79 to 1.91 seconds). These savings exclude router overhead, which increases with router capacity and was measured in a separate inference environment.
The premise it rests on. The prompt configurations used in the downstream evaluation were selected based on the same test set on which they were evaluated, rather than an independent validation set, so the reported token and latency savings may be overestimates that would shrink under proper held-out selection.
If the paper is right (Pith's inferences, not the authors')
Smaller prompt-optimized routers can substitute for larger ones on reasoning and calculator routing, potentially reducing the computational cost of the routing stage itself.
RAG and web search routing appear to require larger router capacity even after prompt optimization, suggesting that these tasks demand more nuanced understanding or broader context that smaller models cannot fully capture.
Router selection for production systems must consider not only classification F1 but also error profiles (false-positive and false-negative rates) because these directly determine downstream token consumption and latency.
Prompt optimization can substantially reduce inference cost in multi-capability LLM pipelines without fine-tuning, offering a lightweight deployment strategy.
The method suggests a path toward modular, capability-aware routing where each capability decision is made independently, allowing any subset of capabilities to be enabled per query.
The reported efficiency gains (68.7% token reduction, 80.5% latency reduction) may be overestimates because the prompt configurations for the downstream evaluation were selected using the same test set; an independent validation set would likely produce smaller savings.
Because BERTScore measures semantic similarity rather than factual correctness, a router that performs well on this metric might still degrade factual accuracy or numerical precision compared to always-on capabilities.
The cost-benefit comparison between router overhead and downstream savings is incomplete because the two were measured in different environments (local Google Colab vs. AWS Bedrock); a controlled end-to-end measurement could shift the optimal router size.
The approach could be extended to a wider range of capabilities, dynamic thresholds per capability, or router ensembles, but the capability-dependent results suggest that no single router size or prompting strategy will be optimal across all tasks.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Optional reasoning, retrieval, web search, and tool use can improve large language model responses but incur unnecessary computation when activated indiscriminately. This study investigates whether prompt optimization can compensate for limited router capacity and whether classification gains translate into downstream efficiency. The proposed framework uses prompt-driven small language models to make four independent capability decisions, allowing multiple capabilities to be selected per query. Qwen2.5 routers ranging from 1.5B to 14B parameters are compared across five prompting strategies, followed by an evaluation of capability-specific optimized configurations using a fixed GPT-OSS-120B downstream model on 127 questions. Under minimal prompting, increasing router capacity does not consistently improve classification performance. Prompt optimization narrows the capacity gap for reasoning and calculator routing, whereas RAG and web search retain larger benefits from higher capacity. Similar classification F1 scores do not necessarily imply equivalent downstream behavior: false-positive activations increase unnecessary computation, while missed capabilities can reduce answer quality. The 14B router achieves a mean BERTScore F1 of 0.8408, compared with 0.8418 when all capabilities are enabled, while reducing average downstream token consumption by 68.7% (8,837 to 2,764 tokens) and median downstream latency by 80.5% (9.79 to 1.91 seconds). These savings exclude router overhead, which is measured separately in a different inference environment and increases with router capacity. The findings demonstrate that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent. Consequently, router selection must consider error profiles and routing overhead alongside classification performance.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 0.72
“The findings demonstrate that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.03 · states limitation 0.94 · human participants 0.04 · controlled comparison 0.91 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.89 · mentions code or data availability 0.02
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Optional reasoning, retrieval, web search, and tool use can improve large language model responses but incur unnecessary computation when activated indiscriminately. | background 1.00 | 0.06 | 0.03 | hedged possibility 0.59 |
| This study investigates whether prompt optimization can compensate for limited router capacity and whether classification gains translate into downstream efficiency. | contribution 0.87 | 0.39 | 0.05 | unclear 0.61 |
| The proposed framework uses prompt-driven small language models to make four independent capability decisions, allowing multiple capabilities to be selected per query. | method 0.90 | 0.79 | 0.04 | asserted 1.00 |
| Qwen2.5 routers ranging from 1.5B to 14B parameters are compared across five prompting strategies, followed by an evaluation of capability-specific optimized configurations using a fixed GPT-OSS-120B downstream model on 127 questions. | method 0.99 | 0.95 | 0.04 | asserted 0.86 |
| Under minimal prompting, increasing router capacity does not consistently improve classification performance. | result 1.00 | 0.92 | 0.08 | asserted 0.95 |
| Prompt optimization narrows the capacity gap for reasoning and calculator routing, whereas RAG and web search retain larger benefits from higher capacity. | result 0.96 | 0.93 | 0.15 | asserted 0.99 |
| Similar classification F1 scores do not necessarily imply equivalent downstream behavior: false-positive activations increase unnecessary computation, while missed capabilities can reduce answer quality. | interpretation 0.93 | 0.67 | 0.16 | asserted 0.77 |
| The 14B router achieves a mean BERTScore F1 of 0.8408, compared with 0.8418 when all capabilities are enabled, while reducing average downstream token consumption by 68.7\% (8,837 to 2,764 tokens) and median downstream latency by 80.5\% (9.79 to 1.91 seconds). | result 1.00 | 0.96 | 0.20 | asserted 1.00 |
| These savings exclude router overhead, which is measured separately in a different inference environment and increases with router capacity. | limitation 0.94 | 0.92 | 0.04 | asserted 1.00 |
| The findings demonstrate that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent. | interpretation 0.84 | 0.91 | 0.53 | asserted 1.00 |
| Consequently, router selection must consider error profiles and routing overhead alongside classification performance. | interpretation 0.95 | 0.48 | 0.48 | asserted 0.96 |
What kind of paper the classifier reports this is: empirical study 0.99 · evidence from observation or experiment 0.98
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 8,316 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (8)
Figures are the authors', reproduced from the paper.
References (15)
- [1] Lakshya A. Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency Herumb Shandilya, Michael J... on PithPith's reviewarXivdoi:10.48550/arxiv.2507.19457
- [2] Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, and Hervé Jégou. 2024. The Faiss Library. (2024). arXiv:2401.08281 https://arxiv.org/abs/ 2401.08281 on PithPith's reviewarXiv
- [3] Huizhong Guo, Tianjun Wei, Dongxia Wang, Yingpeng Du, Ziyan Wang, Jie Zhang, and Zhu Sun. 2026. Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking. arXiv:2601.18146 doi:10.48550/arXiv.2601.18146 on PithPith's reviewarXivdoi:10.48550/arxiv.2601.18146
- [4] Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, and Wei Cheng. 2026. DeepSieve: Information Sieving via LLM-as- a-Knowledge-Router. InFindings of the Association for Computational Linguistics: EACL 2026. Association for Computationa... on Pithdoi:10.18653/v1/20
- [5] Zhixuan He and Yue Feng. 2026. When to Think Deeply: In- hibitory Deliberation for LLM Reasoning. arXiv:2606.06745 doi:10.48550/arXiv.2606.06745 on PithPith's reviewarXivdoi:10.48550/arxiv.2606.06745
- [6] Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong Park. 2024. Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Ques- tion Complexity. InProceedings of the 2024 Conference of the North American Chapter of the Association for Compu... on Pithdoi:10.18653/v1/2024.naacl-long.389
- [7] Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts. 2024. DSPy: Compiling Declarative Language Model Calls into Self... on Pith
- [8] Yansong Ning, Mianpeng Liu, Jingwen Ye, Weidong Zhang, and Hao Liu. 2026. HRBench: Benchmarking and Un- derstanding Thinking-Mode Switch Strategies in Hybrid- Reasoning LLMs. arXiv:2605.28398 doi:10.48550/arXiv.260 5.28398 on PithPith's reviewarXivdoi:10.48550/arxiv.2605.28398
- [9] Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Meth- ods in Natural Language Processing and the 9th Inter- national Joint Conference on Natural Language Process- ing. Ass... on Pithdoi:10.18653/v1/d19-1410
- [10] Richard Šléher, William Brach, Kristián Košťál, and Lukas Galke Poech. 2026. Influence of Prompt Engineering on Small Language Models for Guarded Query Routing. arXiv:2607.24801 doi:10.48550/arXiv.2607.24801 on PithPith's reviewarXivdoi:10.48550/arxiv.2607.24801
- [11] Vinay Tiparadi, Narayan Krishnan, Chetanya Rathi, Hiren Manani, et al. 2026. An Iterative Self-Correcting Agen- tic RAG System.The International FLAIRS Conference Proceedings39, 1 (2026). doi:10.32473/flairs.39.1.141838 on Pithdoi:10.32473/flairs.39.1.141838
- [12] An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, et al. 2024. Qwen2.5 Technical Report. arXiv:2412.15115 doi:10.48550/arXiv.2412.15115 on PithPith's reviewarXivdoi:10.48550/arxiv.2412.15115
- [13] Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Wein- berger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. InInternational Conference on Learning Representations. https://openreview.net/forum ?id=SkeHuCVFDr on Pith
- [14] Heng Zhou, Zelin Tan, Zhemeng Zhang, Yutao Fan, Yib- ing Lin, Li Kang, Xiufeng Song, Rui Li, Songtao Huang, Ao Yu, Yuchen Fan, Yanxu Chen, Kaixin Xu, Xiaohong Liu, Yiran Qin, Philip Torr, Chen Zhang, and Zhenfei Yin on Pith
- [2026] Select-then-Solve: Paradigm Routing as Inference- Time Optimization for LLM Agents. arXiv:2604.06753 doi:10.48550/arXiv.2604.06753 A Detailed Experimental Configuration This appendix documents the principal software, model, prompting, retrieval, tool-use, and evaluation settin... on PithPith's reviewarXivdoi:10.48550/arxiv.2604.06753
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment