RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
Evaluation of openai o1: Opportunities and challenges of agi
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
JAM discovers theory-invariant pseudo-facets via attention-pooled graph prototypical networks, Cross-Theory Harmonization, and LLM-as-a-Judge, improving cross-framework balanced accuracy on Essays and Kaggle datasets.
RePro defines a surrogate objective with intensity and stability scores to generate process-level rewards that enhance LLM reasoning efficiency and accuracy within RLVR pipelines.
Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding, and QA tasks.
HuatuoGPT-o1 achieves superior medical complex reasoning by using a verifier to curate reasoning trajectories for fine-tuning and then applying RL with verifier-based rewards.
ARGUS uses a Prosecutor-Defender-Umpire multi-agent setup plus RAG and chain-of-thought rewards to adapt ad policy enforcement to new regulations using minimal fresh labels.
STPR uses LLMs to generate Python constraint functions from natural language instructions, then applies them via traditional search algorithms to point clouds in simulated Gazebo robot environments with reported full compliance.
ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.
Semi-CoT selects low-entropy pseudo-CoT chains from unlabeled questions via answer-level semantic entropy and shows high pseudo-answer precision but only small or negative gains on math reasoning benchmarks.
The paper delivers a multi-axis taxonomy for world models that maps architectures, training families, reasoning strategies, and domains from early cognitive foundations through systems such as Dreamer, MuZero, and Sora while noting evaluation gaps.
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
STILL-2 uses imitation of distilled long-form thoughts, multi-rollout exploration on difficult problems, and iterative self-improvement of the dataset to train reasoning models that reach competitive performance on three challenging benchmarks.
citing papers explorer
-
RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
-
Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition
JAM discovers theory-invariant pseudo-facets via attention-pooled graph prototypical networks, Cross-Theory Harmonization, and LLM-as-a-Judge, improving cross-framework balanced accuracy on Essays and Kaggle datasets.
-
Rectifying LLM Thought from Lens of Optimization
RePro defines a surrogate objective with intensity and stability scores to generate process-level rewards that enhance LLM reasoning efficiency and accuracy within RLVR pipelines.
-
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding, and QA tasks.
-
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
HuatuoGPT-o1 achieves superior medical complex reasoning by using a verifier to curate reasoning trajectories for fine-tuning and then applying RL with verifier-based rewards.
-
ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring
ARGUS uses a Prosecutor-Defender-Umpire multi-agent setup plus RAG and chain-of-thought rewards to adapt ad policy enforcement to new regulations using minimal fresh labels.
-
"Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation
STPR uses LLMs to generate Python constraint functions from natural language instructions, then applies them via traditional search algorithms to point clouds in simulated Gazebo robot environments with reported full compliance.
-
ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.
-
Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning
Semi-CoT selects low-entropy pseudo-CoT chains from unlabeled questions via answer-level semantic entropy and shows high pseudo-answer precision but only small or negative gains on math reasoning benchmarks.
-
World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications
The paper delivers a multi-axis taxonomy for world models that maps architectures, training families, reasoning strategies, and domains from early cognitive foundations through systems such as Dreamer, MuZero, and Sora while noting evaluation gaps.
-
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
-
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
STILL-2 uses imitation of distilled long-form thoughts, multi-rollout exploration on difficult problems, and iterative self-improvement of the dataset to train reasoning models that reach competitive performance on three challenging benchmarks.