Picture for Hamid Palangi

Hamid Palangi

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents

Add code
Mar 11, 2025
Viaarxiv icon

Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation

Add code
Mar 10, 2025
Viaarxiv icon

Language Models' Factuality Depends on the Language of Inquiry

Add code
Feb 25, 2025
Viaarxiv icon

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

Add code
Feb 22, 2025
Viaarxiv icon

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

Add code
Feb 06, 2025
Figure 1 for Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Figure 2 for Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Figure 3 for Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Figure 4 for Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
Viaarxiv icon

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Add code
Feb 04, 2025
Viaarxiv icon

Reverse Thinking Makes LLMs Stronger Reasoners

Add code
Nov 29, 2024
Figure 1 for Reverse Thinking Makes LLMs Stronger Reasoners
Figure 2 for Reverse Thinking Makes LLMs Stronger Reasoners
Figure 3 for Reverse Thinking Makes LLMs Stronger Reasoners
Figure 4 for Reverse Thinking Makes LLMs Stronger Reasoners
Viaarxiv icon

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Add code
Oct 15, 2024
Figure 1 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Figure 2 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Figure 3 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Figure 4 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Viaarxiv icon

MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark

Add code
Sep 26, 2024
Figure 1 for MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark
Figure 2 for MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark
Figure 3 for MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark
Figure 4 for MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark
Viaarxiv icon

Eureka: Evaluating and Understanding Large Foundation Models

Add code
Sep 13, 2024
Viaarxiv icon