Copertina

SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mishra, Kshitij, Lukas, Nils, Lahlou, Salem
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CORE: Collaborative Reasoning via Cross Teaching
di: Mishra, Kshitij, et al.
Pubblicazione: (2026)

LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs
di: Choukrani, Omar, et al.
Pubblicazione: (2025)

Mitigating Societal Cognitive Overload in the Age of AI: Challenges and Directions
di: Lahlou, Salem
Pubblicazione: (2025)

Token-Budget-Aware LLM Reasoning
di: Han, Tingxu, et al.
Pubblicazione: (2024)

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
di: Li, Zheng, et al.
Pubblicazione: (2025)

A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets
di: Lagasse, Ryan, et al.
Pubblicazione: (2025)

Reinforced Efficient Reasoning via Semantically Diverse Exploration
di: Zhao, Ziqi, et al.
Pubblicazione: (2026)

From Next-Token to Mathematics: The Learning Dynamics of Mathematical Reasoning in Language Models
di: Mishra, Shubhra, et al.
Pubblicazione: (2024)

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
di: Petullo, James, et al.
Pubblicazione: (2026)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
di: Yang, Wang, et al.
Pubblicazione: (2026)

WHODUNIT: Evaluation benchmark for culprit detection in mystery stories
di: Gupta, Kshitij
Pubblicazione: (2025)

ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform
di: Lahlou, Salem
Pubblicazione: (2026)

Hierarchical Budget Policy Optimization for Adaptive Reasoning
di: Lyu, Shangke, et al.
Pubblicazione: (2025)

DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
di: Thareja, Rushil, et al.
Pubblicazione: (2025)

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
di: Ma, Yufei, et al.
Pubblicazione: (2026)

State over Tokens: Characterizing the Role of Reasoning Tokens
di: Levy, Mosh, et al.
Pubblicazione: (2025)

Semantic Tokens in Retrieval Augmented Generation
di: Suro, Joel
Pubblicazione: (2024)

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
di: Liu, Dong, et al.
Pubblicazione: (2025)

Extending Token Computation for LLM Reasoning
di: Liao, Bingli, et al.
Pubblicazione: (2024)

Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks
di: Muhammad, Sajan, et al.
Pubblicazione: (2025)

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
di: Huang, Shijue, et al.
Pubblicazione: (2025)

DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning
di: Pandey, Atharva, et al.
Pubblicazione: (2025)

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
di: Li, Ziniu, et al.
Pubblicazione: (2025)

SD$^2$: Self-Distilled Sparse Drafters
di: Lasby, Mike, et al.
Pubblicazione: (2025)

Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
di: Nogueira, João Paulo, et al.
Pubblicazione: (2025)

Say Anything but This: When Tokenizer Betrays Reasoning in LLMs
di: Ayoobi, Navid, et al.
Pubblicazione: (2026)

Entropy-based Exploration Conduction for Multi-step Reasoning
di: Zhang, Jinghan, et al.
Pubblicazione: (2025)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
di: Qian, Chen, et al.
Pubblicazione: (2025)

BaRDa: A Belief and Reasoning Dataset that Separates Factual Accuracy and Reasoning Ability
di: Clark, Peter, et al.
Pubblicazione: (2023)

SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning
di: Elbadry, Rania, et al.
Pubblicazione: (2026)

Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization
di: Chen, Yile, et al.
Pubblicazione: (2025)

Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
di: Miyamoto, Sora, et al.
Pubblicazione: (2026)

PORT: Preference Optimization on Reasoning Traces
di: Lahlou, Salem, et al.
Pubblicazione: (2024)

Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning
di: Bhatia, Gagan, et al.
Pubblicazione: (2025)

Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models
di: Lee, Sungjae, et al.
Pubblicazione: (2025)

Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs
di: Wu, Zongqian, et al.
Pubblicazione: (2025)

Learning to Reason with Mixture of Tokens
di: Jain, Adit, et al.
Pubblicazione: (2025)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
di: Qi, Penghui, et al.
Pubblicazione: (2025)

RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation
di: Xu, Xinnuo, et al.
Pubblicazione: (2025)

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
di: Li, Huihan, et al.
Pubblicazione: (2025)