CAFE (Coupled Agent–Feedback Evolution) is a framework that lets a shared‑parameter model alternate between acting as a search agent and as a critic that provides corrective feedback. By learning when to request feedback and how to use it, CAFE trains the agent to recover from its own failures and shapes rewards both online and offline. Experiments on seven search benchmarks show that CAFE outperforms other RL‑based agents, maintains gains on out‑of‑domain tests, and reduces hallucinations, indicating that co‑evolving feedback is essential for self‑improving search agents.
Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those errors compound. Tre...
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.
arXiv:2608. 07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence.
As Large Language Model (LLM) agents are applied in continuously interactive environments, driving the evolution of their own capabilities becomes a core problem for achieving long-term autonomy. Curr...
arXiv:2607. 03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute critical experience signals.
arXiv:2608. 06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods.
arXiv:2609.24289v1 Announce Type: new Abstract: As Large Language Model (LLM) agents are applied in continuously interactive environments, driving the evolution of their own capabilities becomes a co...
arXiv:2605. 29796v3 Announce Type: replace Abstract: Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search.
arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.
arXiv:2608. 02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model.
Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods. We ask a fundamentally different question: how much of this search policy can be internalized by a single tool-using agent?
arXiv:2608.21946v1 Announce Type: cross Abstract: Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exp...