Search Results for author:
Found 9 papers, 6 papers with code
MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration
We investigate how iterative collaboration among multiple instances and types of large language models (LLMs) enhances subtasks in the refinement process, such as error detection, critiquing unfaithful sentences, and making corrections based on critiques.
Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning
We propose a skill-based recruiting strategy that dynamically selects the most relevant set of expert LLMs for diverse reasoning tasks based on their strengths.
Learning to Generate Unit Tests for Automated Debugging
However, we uncover a trade-off between generating unit test inputs that reveal errors when given a faulty code and correctly predicting the unit test output without access to the gold solution.
Reverse Thinking Makes LLMs Stronger Reasoners
Reverse thinking plays a crucial role in human reasoning.
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
Moreover, to ensure effective refinement, we employ a multi-agent loop with three agents: Solver, Reviewer (which generates targeted feedback based on step-wise RM scores), and the Refiner (which incorporates feedback).
System-1.x: Learning to Balance Fast and Slow Planning with Language Models
To this end, we propose the System-1. x Planner, a controllable planning framework with LLMs that is capable of generating hybrid plans and balancing between the two planning modes based on the difficulty of the problem at hand.
MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
Experiments on seven widely used commonsense and math reasoning benchmarks show that MAGDi improves the reasoning capabilities of smaller models, outperforming several methods that distill from a single teacher and multiple teachers.
Location-Aware Visual Question Generation with Lightweight Models
This work introduces a novel task, location-aware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location.
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
In each round, ReConcile initiates discussion between agents via a 'discussion prompt' that consists of (a) grouped answers and explanations generated by each agent in the previous round, (b) their confidence scores, and (c) demonstrations of answer-rectifying human explanations, used for convincing other agents.
