Related papers: On-Policy Self-Evolution via Failure Trajectories …

Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core…

LLM-agent training pipelines routinely discard failed trajectories even though GPT-4o achieves only 14-20% on WebArena and below 55% pass@1 on ToolBench; even specialised systems at 50-65% leave the majority of trajectories unused. We…

Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization…

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model…

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Due to the increasing sophistication of web attacks, Web Application Firewalls (WAFs) have to be tested and updated regularly to resist the relentless flow of web attacks. In practice, using a brute-force attack to discover vulnerabilities…

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

We propose Frictive Policy Optimization (FPO), a framework for learning language model policies that regulate not only what to say, but when and how to intervene in order to manage epistemic and normative risk. Unlike standard alignment…

End-to-end autonomous driving has substantially progressed by directly predicting future trajectories from raw perception inputs, which bypasses traditional modular pipelines. However, mainstream methods trained via imitation learning…

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental…

Recent analyses highlight challenges in autonomous vehicle technologies, particularly failures in decision-making under dynamic or emergency conditions. Traditional automated driving systems recalculate the entire trajectory in a changing…

LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this cost comes from synchronized stage execution and imbalance…

Autonomous agents excel in self-improvement through reflection and iterative refinement, which reuse successful task trajectories as in-context examples to assist subsequent reasoning. However, shifting across tasks often introduces a…

We have recently presented SAFE -- Solution And Fitness Evolution -- a commensalistic coevolutionary algorithm that maintains two coevolving populations: a population of candidate solutions and a population of candidate objective functions.…

Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches…

Large language models (LLMs) are effective for automated program repair, but plausible patches that pass the full test suite often rewrite more code than necessary, increasing review and maintenance costs. This over-editing is common…