LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
hub
Big-bench extra hard.arXiv preprint arXiv:2502.19187, 2025
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
An empirical evaluation of 22 agentic frameworks on BBH, GSM8K, and ARC benchmarks shows stable performance in 12 frameworks but highlights orchestration failures and weaker mathematical reasoning.
InternBootcamp supplies 1000+ verifiable, auto-generated task environments across domains that enable task scaling to improve LLM reasoning, producing a 32B model with state-of-the-art results on the new Bootcamp-EVAL benchmark.
Longer prompts and solutions in a new expert-authored math dataset correlate with higher failure rates across LLMs, with length linked to empirical difficulty after difficulty adjustment.
A reasoning-driven problem generator plans synthesis directions with CoT and uses solver performance feedback to adapt difficulty, producing complementary problems that yield a 3.4% average improvement across 10 reasoning benchmarks.
A label-free self-supervised RL method derives rewards from instructions via constraint decomposition and binary classification, yielding improvements on in-domain and out-of-domain instruction-following tasks.
The serial scaling hypothesis formalizes inherently serial problems in complexity theory and demonstrates that diffusion models cannot solve them.
Human tests should not be applied to AI to measure traits like intelligence due to calibration, validity, contamination, and prompt sensitivity issues; develop AI-specific evaluation frameworks instead.
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
A position and survey paper that identifies convergence between neuroscience, AGI, and neuromorphic computing and outlines four key integration challenges.
citing papers explorer
-
Hypothesis generation and updating in large language models
LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
-
Agentic Frameworks for Reasoning Tasks: An Empirical Study
An empirical evaluation of 22 agentic frameworks on BBH, GSM8K, and ARC benchmarks shows stable performance in 12 frameworks but highlights orchestration failures and weaker mathematical reasoning.
-
InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling
InternBootcamp supplies 1000+ verifiable, auto-generated task environments across domains that enable task scaling to improve LLM reasoning, producing a 32B model with state-of-the-art results on the new Bootcamp-EVAL benchmark.
-
Too long; didn't solve
Longer prompts and solutions in a new expert-authored math dataset correlate with higher failure rates across LLMs, with length linked to empirical difficulty after difficulty adjustment.
-
Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis
A reasoning-driven problem generator plans synthesis directions with CoT and uses solver performance feedback to adapt difficulty, producing complementary problems that yield a 3.4% average improvement across 10 reasoning benchmarks.
-
Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
A label-free self-supervised RL method derives rewards from instructions via constraint decomposition and binary classification, yielding improvements on in-domain and out-of-domain instruction-following tasks.
-
The Serial Scaling Hypothesis
The serial scaling hypothesis formalizes inherently serial problems in complexity theory and demonstrates that diffusion models cannot solve them.
-
Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead
Human tests should not be applied to AI to measure traits like intelligence due to calibration, validity, contamination, and prompt sensitivity issues; develop AI-specific evaluation frameworks instead.
-
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
-
Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems
A position and survey paper that identifies convergence between neuroscience, AGI, and neuromorphic computing and outlines four key integration challenges.