arXiv:2606. 15306v1 Announce Type: cross Abstract: We envision continually learning agentic systems that become more useful over time: as they encounter sequences of related tasks, they should infer the hidden structure shared across those tasks and use it to improve future decisions.
The paper introduces a steering agent that supervises large language model (LLM)-based agents and multi‑agent systems during execution to prevent goal drift. By observing the execution context, the steering agent decides when to intervene using either a low‑cost fast path or a high‑cost slow path, and both paths are jointly trained with reinforcement learning. Experiments on information‑seeking search tasks demonstrate that the steering agent improves performance and efficiency for both single‑agent and multi‑agent systems, generalizes to out‑of‑domain tasks, and allows controllable intervention frequency without retraining.
arXiv:2610.19614v1 Announce Type: new Abstract: In this work, we reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations. We show that success...
arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.
arXiv:2606. 04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback.
arXiv:2603.02935v2 Announce Type: replace Abstract: Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task repres...
Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
arXiv:2601. 19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks.
arXiv:2607. 07178v1 Announce Type: cross Abstract: Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks.
Policy Learning with a Language Bottleneck (PLLB) is a framework that lets AI agents generate linguistic rules to describe high‑level strategies. PLLB alternates between rule generation, guided by language models, and policy updates that use these rules, even when a single rule cannot fully capture a complex policy. Experiments on five tasks—including a signaling game, maze navigation, image reconstruction, and robot grasp planning—show that PLLB agents learn more interpretable, generalizable behaviors and can share rules with humans for better coordination.
arXiv:2608. 20169v1 Announce Type: cross Abstract: We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection.
Collab‑Solver introduces a multi‑agent policy learning framework for mixed‑integer linear programming (MILP) that enables collaborative optimization of multiple solver modules. By modeling the interaction between cut selection and branching as a Stackelberg game, the approach employs a two‑phase learning paradigm—data‑communicated policy pretraining followed by coordinated policy refinement. Experiments on synthetic and large‑scale real‑world MILP datasets show that the jointly learned policies markedly improve solving performance and generalize well across diverse instance sets.