NeurIPS 2024PastMath & reasoningML systems
The First Workshop on System-2 Reasoning at Scale, NeurIPS'24
Sys2-Reasoning
- Submission deadline
- Sep 27, 2024, 10:41 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (50)
Fetched from OpenReview (v2) on 2026-06-10.
A Llama Sunk My Battleship! Asking Rational Questions with LLMs via Bayesian Inference
Algorithmic Language Models with Neurally Compiled Libraries
ALTA: Compiler-Based Analysis of Transformers
Automated Design of Agentic Systems
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
Can Language Models Perform Implicit Bayesian Inference Over User Preference States?
Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
Can Stories Help LLMs Reason? Curating Information Space Through Narrative
CausalBench: A Comprehensive Benchmark for Evaluating Causal Reasoning Capabilities of Large Language Models
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
CryptoFormalEval: Integrating Large Language Models and Formal Verification for Automated Cryptographic Protocol Vulnerability Detection
Diffusion On Syntax Trees For Program Synthesis
Distilling System 2 into System 1
Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rules
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
Equitable Access to Justice: Logical LLMs Show Promise
From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
Generative Verifiers: Reward Modeling as Next-Token Prediction
Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning
Implicit Reasoning in Deep Time Series Forecasting
Improving LLM Generation with Inverse and Forward Alignment: Reward Modeling, Prompting, Fine-Tuning, and Inference-Time Optimization
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
LLMs on interactive feature collections with implicit look-ahead strategies
Logically Consistent Language Models via Neuro-Symbolic Integration
MemReasoner: A Memory-augmented LLM Architecture for Multi-hop Reasoning
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning
MovieCORE: COgnitive REasoning in Movies
Not All LLM Reasoners Are Created Equal
Planning in Natural Language Improves LLM Search for Code Generation
Proof Flow: Preliminary Study on Generative Flow Network Language Model Tuning for Formal Reasoning
PROOF OF THOUGHT : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning
Rational Metareasoning for Large Language Models
Reasoning Abilities of Large Language Models through the Lens of Abstraction and Reasoning
Recurrent Transformers Trade-off Parallelism for Length Generalization on Regular Languages
Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning
Sampling Language from Latent System 2 Reasoning
softmax is not enough (for sharp out-of-distribution)
STaR: Benchmarking Spatio-Temporal Reasoning for Systematic Generalization
System 1.5: Designing Metacognition in Artificial Intelligence
System 2 Reasoning Capabilities Are Nigh
System-2 Reasoning via Generality and Adaptation
The Turing Game
Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events
Thought of Search: Planning with Language Models Through The Lens of Efficiency
VCR: Visual Caption Restoration
World Models for Web Agents
Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers