7 papers
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
Luan Zhang, Dandan Song, Zhijing Wu +8
Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code interpreters (CI). Most recent s…
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inher…
SCoder: Iterative Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs
Xinyu Zhang, Changzhi Zhou, Linmei Hu +5
Existing code large language models (LLMs) often rely on large-scale instruction data distilled from proprietary LLMs for fine-tuning, which typically incurs high costs. In this pa…
RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
Changzhi Zhou, Xinyu Zhang, Dandan Song +6
Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instru…
Revisit Self-Debugging with Self-Generated Tests for Code Generation
Xiancai Chen, Zhengwei Tao, Kechi Zhang +7
Large language models (LLMs) have shown significant advancements in code generation, but still face challenges on tasks beyond their basic capabilities. Recently, the notion of sel…