2 citations · 2 across the 4 of their papers we have counts for
5 papers
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
Wang Yang, Chaoda Song, Xinpeng Li +7
Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficul…
Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search
Hao Lu, Haoyuan Huang, Yulin Zhou +2
Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, cur…
MCTSr-Zero: Self-Reflective Psychological Counseling Dialogues Generation via Principles and Adaptive Exploration
Hao Lu, Yanchi Gu, Haoyuan Huang +3
The integration of Monte Carlo Tree Search (MCTS) with Large Language Models (LLMs) has demonstrated significant success in structured, problem-oriented tasks. However, applying th…
Evaluating the Robustness to Instructions of Large Language Models
Yuansheng Ni, Sichao Jiang, Xinyu wu +2
Recently, Instruction fine-tuning has risen to prominence as a potential method for enhancing the zero-shot capabilities of Large Language Models (LLMs) on novel tasks. This techni…
Revisiting Automated Prompting: Are We Actually Doing Better?
Yulin Zhou, Yiren Zhao, Ilia Shumailov +2
Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream task…