6 papers · 1 filter
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Changle Qu, Sunhao Dai, Hengyi Cai +4
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-l…
MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
Changle Qu, Sunhao Dai, Hengyi Cai +3
Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing rei…
Length-Induced Embedding Collapse in PLM-based Models
Yuqi Zhou, Sunhao Dai, Zhanshuo Cao +2
Text embeddings from PLM-based models enable a wide range of applications, yet their performance often degrades on longer texts. In this paper, we introduce a phenomenon we call Le…
GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
Yuqi Zhou, Sunhao Dai, Shuai Wang +3
Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object gr…
From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
Changle Qu, Sunhao Dai, Xiaochi Wei +5
Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent i…
Tool Learning with Large Language Models: A Survey
Changle Qu, Sunhao Dai, Xiaochi Wei +5
Recently, tool learning with large language models (LLMs) has emerged as a promising paradigm for augmenting the capabilities of LLMs to tackle highly complex problems. Despite gro…