cs.LGNov 12, 2026

JudgeMix: Judge-Guided Mixed-Rollout Data Synthesis for LLM Agents

Authors: Cheng-Yu Hsieh, Ting-Yao Hu, Sanjoy Chowdhury, Fatih Ilhan, Oncel Tuzel, Raviteja Vemulapalli

Organizations: Apple

Abstract

Supervised fine-tuning (SFT) on expert trajectories is a standard paradigm for training LLM agents. However, it suffers from a well-known training-inference distribution mismatch, calling for target-aware data synthesis strategies that ground the training data in the target model's native state distribution. To bridge this gap, emerging approaches incorporate the expert either to guide mixed rollouts alongside the target model, or to provide dense step-wise supervision. Nonetheless, existing methods apply expert assistance blind to the target model's inherent behavior: they either disrupt the rollout using sub-optimal random intervention heuristics, or they enforce indiscriminate uniform supervision that unnecessarily overwrites the model's already-correct actions. We introduce JudgeMix, a judge-guided data synthesis framework that dynamically interleaves the target model and expert based on step-wise semantic evaluations. JudgeMix queries expert guidance precisely when the target model struggles, ensuring high trajectory success rates while keeping the state distribution aligned with the target model. It additionally uses the judge evaluation to reweight expert supervision on different steps, preserving model's inherent valid behavior while correcting its errors. On two agentic tool-use benchmarks, AppWorld and AutomationBench, JudgeMix demonstrates consistent superior performance to existing methods, with improvements up to 10 pass@1 points.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 14, 2026

Beyond Corrected Actions: Training LLM Agents on Textual Critiques

Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions. A common approach to improving LLM agents is to use more capable expert models to provide training supervision, either by behavior cloning the expert's trajectories or by using the expert to correct the actions in trajectories generated by the weaker student model. However, expert LLMs can provide richer supervision than actions alone: they can directly generate textual critique that explain why specific actions are incorrect. We study whether training on such feedback benefits LLM agents and propose Critique-Augmented Agentic Fine-Tuning (CAFT), a framework that elicits textual expert feedback on student-generated trajectories. For each incorrect action, the expert yields both a corrected action and a textual critique explaining the student's mistake--which we then use as the training target for fine-tuning. Across four student models from the Nemotron 3 and Gemma 4 families on the agentic domains τ2τ^2-Bench Airline+Retail and WebShop, adding critiques to action-level supervision improves performance by 8% on average over action-only distillation. Additionally, CAFT checkpoints can also provide a better warm start for reinforcement learning than expert-trajectory distillation. Our results demonstrate that textual critiques can strengthen supervision for multi-turn LLM agents.
Jun 19, 2026

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

As agentic systems tackle increasingly complex multi-step tasks, evaluating their trajectories presents a major bottleneck - human annotation of a single trajectory on popular agentic benchmarks can take hours, making it difficult to scale evaluations for measuring performance or curating training data. This has driven widespread reliance on automated approaches such as LLM-as-a-judge (LLMJ) to critique agents at the process and outcome-levels at scale, however, the soundness of LLMJ critiques often goes unmeasured. Here, we introduce Counsel, the first public dataset of meta-evaluations for agentic tasks. Counsel consists of process-level critiques from open-weight LLMJs on two agent benchmarks: tau-bench (customer support agents) and DA-Code (coding agents), and human meta-evaluations of these critiques. Human annotators label critiques on each flagged error as "spot on", "correct location but poor reasoning", or "should not have flagged", achieving reliable inter-annotator agreement (Krippendorff's alpha of 0.78). The resulting dataset stratifies LLMJ critiques by human alignment across both error location within a trajectory and reasoning quality, serving as valuable data to calibrate, improve, or train LLMJs for agents. Comparing open-weight judges, we find that more capable judge models and more reasoning effort both enabled improved human agreement, with the strongest judge reaching ~88% agreement on location and ~65% on reasoning. Counsel is generated using open-weight models and is permissively licensed for broad community use, which we hope will enable rigorous study and improved alignment of LLM-based evaluators for agentic systems.
Oct 7, 2026

Training Advisors for LLM Agents from Task Outcomes

Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has shown that natural-language feedback can help these agents revise their decisions during task execution. We introduce Caddie, a method for training critics to provide natural-language analysis and advice as agents work through a task. Unlike approaches that rely on step-level labels or reference critiques, Caddie learns from whether the agent ultimately succeeds after receiving the critic's feedback. We optimize the critic through reinforcement learning while keeping the base model frozen. Trained on multi-hop question answering with a single base model, our Qwen3-4B critic improves success rates across four base models of different scales and architectures, including three not used during critic training. On the MuSiQue benchmark, the trained critic improves Qwen3-4B's success rate by more than 25 percentage points, surpassing the performance of Kimi K3 without a critic. The same critic also yields gains on out-of-domain interactive benchmarks, including τ3τ^3 and DeepDive, with no additional training. Our results show that agents can decide when to seek help from a critic at inference time and that outcome-based critic training can produce guidance that transfers across base models and task domains.