ThinkProbe builds non-generative Thought Graphs from 4200 LLM traces across 7 models and 200 questions to extract 5D cognitive profiles, finding model-level stability in reasoning structure that exceeds domain effects in four dimensions.
Think-bench: Evaluat- ing thinking efficiency and chain-of-thought quality of large reasoning models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
Evaluations of 53 LLMs on 14 basic math tasks show reasoning models use ~18x more tokens with sometimes lower accuracy, non-monotonic gains from extended budgets, and sharp performance drops under token constraints.
RecurGuard monitors recurrence rate, volume growth, and query progress in exposed reasoning traces to terminate generation on token-consumption attacks, reporting 99% detection on OverThink and 92% on ExtendAttack with near-zero false positives.
CRANE applies magnitude thresholding, a Conservative Taylor Gate, and Graduated Sigmoidal Projection to the Thinking-Instruct delta to improve code agent pass rates on Roo-Eval, SWE-bench-Verified, and Terminal-Bench while preserving efficiency.
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
AgroCoT is a new Chain-of-Thought VQA benchmark with 4759 samples to evaluate reasoning capabilities of vision-language models in agriculture.
citing papers explorer
-
ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs
ThinkProbe builds non-generative Thought Graphs from 4200 LLM traces across 7 models and 200 questions to extract 5D cognitive profiles, finding model-level stability in reasoning structure that exceeds domain effects in four dimensions.
-
Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
-
Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
Evaluations of 53 LLMs on 14 basic math tasks show reasoning models use ~18x more tokens with sometimes lower accuracy, non-monotonic gains from extended budgets, and sharp performance drops under token constraints.
-
RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks
RecurGuard monitors recurrence rate, volume growth, and query progress in exposed reasoning traces to terminate generation on token-consumption attacks, reporting 99% detection on OverThink and 92% on ExtendAttack with near-zero false positives.
-
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
CRANE applies magnitude thresholding, a Conservative Taylor Gate, and Graduated Sigmoidal Projection to the Thinking-Instruct delta to improve code agent pass rates on Roo-Eval, SWE-bench-Verified, and Terminal-Bench while preserving efficiency.
-
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
-
AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture
AgroCoT is a new Chain-of-Thought VQA benchmark with 4759 samples to evaluate reasoning capabilities of vision-language models in agriculture.