Related papers: CodeDelegator: Mitigating Context Pollution via Ro…
Large language models (LLMs) excel at knowledge-intensive question answering and reasoning, yet their real-world deployment remains constrained by knowledge cutoff, hallucination, and limited interaction modalities. Augmenting LLMs with…
The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…
Constrained decoding approaches aim to control the meaning or style of text generated by the pre-trained large language models (LLMs or also PLMs) for various tasks at inference time. However, these methods often guide plausible…
The exceptional capabilities of large language models (LLMs) have substantially accelerated the rapid rise and widespread adoption of agents. Recent studies have demonstrated that generating Python code to consolidate LLM-based agents'…
Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…
Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…
Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed…
Producing high-quality code across multiple programming languages is increasingly important as today's software systems are built on heterogeneous stacks. Large language models (LLMs) have advanced the state of automated programming, yet…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models…
To exchange complex data structures in distributed systems, documents written in context-free languages are exchanged among communicating parties. Unparsing these documents correctly is as important as parsing them correctly because errors…
Large language models (LLMs) are increasingly strong contenders in machine translation. In this work, we focus on document-level translation, where some words cannot be translated without context from outside the sentence. Specifically, we…
We revisit multi-agent delegation under a stronger and more realistic assumption: an agent's capability is not fixed at the skill level, but depends on task context. A coding agent may excel at short standalone edits yet fail on…
Prompt engineering for LLMs remains complex, with existing frameworks either hiding complexity behind restrictive APIs or providing inflexible canned patterns that resist customization -- making sophisticated agentic programming…
Emergent language research has made significant progress in recent years, but still largely fails to explore how communication emerges in more complex and situated multi-agent systems. Existing setups often employ a reference game, which…
Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long texts and have almost perfect performance in traditional retrieval tasks. However, their performance significantly degrades when it comes to numerical…
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…
It is an amazing fact that remarkably complex behaviors could emerge from a large collection of very rudimentary dynamical agents through very simple local interactions. However, it still remains elusive on how to design these local…
LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action…
Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have…