Related papers: Awakening the Sleeping Agent: Lean-Specific Agenti…

Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability patterns undermines the effectiveness of a single unified model, and manual prompt…

Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often…

The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined…

Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as…

Tool-augmented language agents frequently fail in real-world deployment due to tool malfunctions--timeouts, API exceptions, or inconsistent outputs--triggering cascading reasoning errors and task abandonment. Existing agent training…

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Reproducing computational research is often assumed to be as simple as rerunning the original code with provided data. In practice, missing packages, fragile file paths, version conflicts, or incomplete logic frequently cause analyses to…

Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, existing methods relying on static embedding retrieval or…

LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance…

Why do language agents fail on tasks they are capable of solving? We argue that many such failures are reliability failures caused by stochastic drift from a task's latent solution structure, not capability failures. Every well-defined…

Agentic systems that chain reasoning, tool use, and synthesis into multi-step workflows are entering production, yet prevailing evaluation practices like end-to-end outcome checks and ad-hoc trace inspection systematically mask the…

Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…

We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving. Built on the standard expert iteration and reinforcement learning pipeline, our approach incorporates three…

Large Language Model (LLM)-based multi-agent systems show promise for automating real-world tasks but struggle to transfer across domains due to their domain-specific nature. Current approaches face two critical shortcomings: they require…

The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tuning LLMs for domain-specific applications is the potential…

Tool using agents often fail for operational reasons even when language understanding is strong. Common causes include invalid arguments, interface drift, weak recovery, and inefficient retry behavior. We introduce ToolMisuseBench, an…

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple…

Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of…