Copertina

Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pandey, Rohan, Ye, Eric, Li, Michael
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks
di: Saini, Dhruv, et al.
Pubblicazione: (2026)

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
di: Tian, Yijun, et al.
Pubblicazione: (2024)

Incentivizing LLMs to Self-Verify Their Answers
di: Zhang, Fuxiang, et al.
Pubblicazione: (2025)

Plantain: Plan-Answer Interleaved Reasoning
di: Liang, Anthony, et al.
Pubblicazione: (2025)

To See or To Read: User Behavior Reasoning in Multimodal LLMs
di: Dong, Tianning, et al.
Pubblicazione: (2025)

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
di: Phan, Phuc, et al.
Pubblicazione: (2024)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
di: Cao, Chentao, et al.
Pubblicazione: (2025)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
di: Fan, Jiajun, et al.
Pubblicazione: (2025)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
di: Wang, Changsheng, et al.
Pubblicazione: (2025)

Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and Beyond
di: Fan, Joshua, et al.
Pubblicazione: (2025)

Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
di: Wang, Shengjie, et al.
Pubblicazione: (2026)

ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding
di: Zhoubian, Sining, et al.
Pubblicazione: (2025)

Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
di: Deb, Rohan, et al.
Pubblicazione: (2025)

Conservative Contextual Bandits: Beyond Linear Representations
di: Deb, Rohan, et al.
Pubblicazione: (2024)

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
di: Kirchhof, Michael, et al.
Pubblicazione: (2025)

Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs
di: Chen, Xinzhu, et al.
Pubblicazione: (2025)

Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression
di: Tian, Ye, et al.
Pubblicazione: (2026)

From Stochastic Answers to Verifiable Reasoning: Interpretable Decision-Making with LLM-Generated Code
di: Mahesh, Anirudh Jaidev, et al.
Pubblicazione: (2026)

DMax: Aggressive Parallel Decoding for dLLMs
di: Chen, Zigeng, et al.
Pubblicazione: (2026)

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
di: Zhang, Yuxiang, et al.
Pubblicazione: (2025)

Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
di: Dong, Zihan, et al.
Pubblicazione: (2026)

Shared Lexical Task Representations Explain Behavioral Variability In LLMs
di: Yang, Zhuonan, et al.
Pubblicazione: (2026)

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
di: Zhao, Yilong, et al.
Pubblicazione: (2025)

Trained Persistent Memory for Frozen Decoder-Only LLMs
di: Jeong, Hong
Pubblicazione: (2026)

SciTS: Scientific Time Series Understanding and Generation with LLMs
di: Wu, Wen, et al.
Pubblicazione: (2025)

Temporal Sampling for Forgotten Reasoning in LLMs
di: Li, Yuetai, et al.
Pubblicazione: (2025)

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
di: Alomrani, Mohammad Ali, et al.
Pubblicazione: (2025)

Learning to Answer from Correct Demonstrations
di: Joshi, Nirmit, et al.
Pubblicazione: (2025)

WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
di: Yang, Haojin, et al.
Pubblicazione: (2025)

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
di: Li, Zhen, et al.
Pubblicazione: (2025)

From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning
di: Zhan, Chen, et al.
Pubblicazione: (2026)

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
di: Liu, Huanyu, et al.
Pubblicazione: (2025)

Sci-Reasoning: A Dataset Decoding AI Innovation Patterns
di: Liu, Jiachen, et al.
Pubblicazione: (2026)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
di: Dai, Xinnan, et al.
Pubblicazione: (2025)

OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning
di: Wu, Hao, et al.
Pubblicazione: (2026)

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
di: Zhang, Yifei, et al.
Pubblicazione: (2026)

Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
di: Chen, Ming, et al.
Pubblicazione: (2025)

ReasonCACHE: Teaching LLMs To Reason Without Weight Updates
di: Gupta, Sharut, et al.
Pubblicazione: (2026)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
di: Fernandez, Nigel, et al.
Pubblicazione: (2025)