Retrieving structured thinking traces as a corpus improves reasoning performance on AIME, LiveCodeBench, and GPQA over standard RAG or no retrieval.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
Linear probes on frozen LLM hidden states recover an approximate remaining-output-length signal that is decodable at prompt-end, transfers across datasets, and shifts upward at retraction tokens.
COPSD improves mathematical reasoning in low-resource languages by having LLMs self-distill from their own high-resource English behavior via token-level divergence on rollouts with privileged crosslingual context.
Large reasoning models show a negative correlation between token entropy and logit-gradient norms, and the paper uses this 'Entropy-Gradient Inversion' as a reward regularizer (CorR-PO) in RL training.
ProxyCoT transfers CoT reasoning from proxy short contexts to full long contexts through RL/distillation followed by SFT, outperforming baselines with lower overhead and generalizing out-of-domain.
LuckyStar 111B adapts Cohere's Command A model with four scaling techniques to improve tool-use, math reasoning, and NL2SQL in Korean-English while preserving general instruction following.
citing papers explorer
-
RAG over Thinking Traces Can Improve Reasoning Tasks
Retrieving structured thinking traces as a corpus improves reasoning performance on AIME, LiveCodeBench, and GPQA over standard RAG or no retrieval.
-
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Linear probes on frozen LLM hidden states recover an approximate remaining-output-length signal that is decodable at prompt-end, transfers across datasets, and shifts upward at retraction tokens.
-
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
COPSD improves mathematical reasoning in low-resource languages by having LLMs self-distill from their own high-resource English behavior via token-level divergence on rollouts with privileged crosslingual context.
-
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
Large reasoning models show a negative correlation between token entropy and logit-gradient norms, and the paper uses this 'Entropy-Gradient Inversion' as a reward regularizer (CorR-PO) in RL training.
-
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
ProxyCoT transfers CoT reasoning from proxy short contexts to full long contexts through RL/distillation followed by SFT, outperforming baselines with lower overhead and generalizing out-of-domain.
-
Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents
LuckyStar 111B adapts Cohere's Command A model with four scaling techniques to improve tool-use, math reasoning, and NL2SQL in Korean-English while preserving general instruction following.
- Hybrid Policy Distillation for LLMs