conftrace_
← Learning Types
Deep Learning › Learning Types ›

Chain-of-Thought Reasoning

68 papers

Papers per year

1
2
4
61

Papers

Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning ACL 2026
Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection ACL 2026
SeLaR: Selective Latent Reasoning in Large Language Models ACL 2026
MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning ACL 2026
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks ACL 2026
Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations ACL 2026
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do ACL 2026
Shanks: Simultaneous Hearing and Thinking for Spoken Language Models ACL 2026
Self-Reflective Generation at Test Time ACL 2026
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning ACL 2026
To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples ACL 2026
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning ACL 2026
Do LLMs Really Need 10+ Thoughts for “Find the Time 1000 Days Later”? Towards Structural Understanding of LLM Overthinking ACL 2026
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning ACL 2026
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring ACL 2026
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking ACL 2026
Merlin’s Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting ACL 2026
ReEfBench: Quantifying the Reasoning Efficiency of LLMs ACL 2026
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning ACL 2026
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation ACL 2026
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning ACL 2026
Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy ACL 2026
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models ACL 2026
Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models ACL 2026
Learning to Think on Hypergraph: HyperCoT for Structure-Guided N-ary Knowledge Graph Completion ACL 2026