HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.
Contrastive chain-of-thought prompting
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prior studies surprisingly reveal minimal impact when using invalid demonstrations instead. Furthermore, the conventional chain of thought does not inform language models on what mistakes to avoid, which potentially leads to more errors. Hence, inspired by how humans can learn from both positive and negative examples, we propose contrastive chain of thought to enhance language model reasoning. Compared to the conventional chain of thought, our approach provides both valid and invalid reasoning demonstrations, to guide the model to reason step-by-step while reducing reasoning mistakes. To improve generalization, we introduce an automatic method to construct contrastive demonstrations. Our experiments on reasoning benchmarks demonstrate that contrastive chain of thought can serve as a general enhancement of chain-of-thought prompting.
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
ReasonAlloc introduces a hierarchical decoding-time KV cache budget allocation framework that outperforms uniform and other baselines on math reasoning tasks at small cache budgets.
A cycle of solver, adversarial flawed-chain challenger, and feedback agent optimizes CoT prompts to raise accuracy and cut run-to-run answer variability within two to three cycles.
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
A taxonomy that consolidates prompt patterns from prior surveys into 30 unique canonical forms organized by two dimensions.
CAP-CoT improves LLM reasoning accuracy and stability by iteratively refining solver prompts via contrast with adversarially generated flawed reasoning chains.
ReFineVLA adds teacher-generated reasoning steps to VLA training and reports state-of-the-art success rates on SimplerEnv WidowX and Google Robot benchmarks.
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.
A systematic survey categorizes prompt engineering methods for LLMs and VLMs by application area, summarizing methodologies, applications, models, datasets, strengths, and limitations for each technique along with a taxonomy and summary table.
citing papers explorer
-
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.
-
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
-
ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models
ReasonAlloc introduces a hierarchical decoding-time KV cache budget allocation framework that outperforms uniform and other baselines on math reasoning tasks at small cache budgets.
-
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
A cycle of solver, adversarial flawed-chain challenger, and feedback agent optimizes CoT prompts to raise accuracy and cut run-to-run answer variability within two to three cycles.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
A Taxonomy of Single-Turn Textual Prompt Patterns
A taxonomy that consolidates prompt patterns from prior surveys into 30 unique canonical forms organized by two dimensions.
-
Partial exploiters sustain cooperation: the hump-shaped strategy stably coexists with unconditional cooperators
CAP-CoT improves LLM reasoning accuracy and stability by iteratively refining solver prompts via contrast with adversarially generated flawed reasoning chains.
-
ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning
ReFineVLA adds teacher-generated reasoning steps to VLA training and reports state-of-the-art success rates on SimplerEnv WidowX and Google Robot benchmarks.
-
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.
-
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
A systematic survey categorizes prompt engineering methods for LLMs and VLMs by application area, summarizing methodologies, applications, models, datasets, strengths, and limitations for each technique along with a taxonomy and summary table.