arXiv:2606. 15064v1 Announce Type: new Abstract: Manipulation demonstrations have temporal phase structure, and a natural hypothesis is that demonstration-curation metrics should be applied within phases rather than globally.
arXiv:2606. 05588v1 Announce Type: cross Abstract: Imitation-learning policies inherit the quality of the demonstrations they are trained on, and a growing set of curation metrics promise to score and filter low-quality demonstrations automatically.
arXiv:2606. 10229v1 Announce Type: cross Abstract: We study whether demonstration-curation metrics that detect defective training episodes also improve the downstream behavior-cloning policy that trains on the curated data.
PROOF-Gen is a method that improves distillation of tool‑calling models by recovering successful trajectories from teacher failures. It uses per‑scenario prompt optimization to generate corrective guidance that steers the teacher to a passing trajectory, then removes this guidance before training so the student learns from clean demonstrations. On τ2‑bench, PROOF-Gen recovers 93% of failed scenarios, boosting Qwen3‑4B‑Instruct‑2507’s Pass^1 from 0.132 to 0.529 and improving Gemma 4 E4B‑it by 7.2pp on BFCL v4 multi‑turn, while also raising deployed on‑device model performance by up to 5.0pp across response‑quality metrics.
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv:2604.07799v3 Announce Type: replace-cross Abstract: Robots deployed for long periods keep improving their skills, and each update changes a released system. We treat this as a software-lifecycl...
The paper introduces DART‑SD, a framework for improving multi‑turn tool‑calling agents by respecting the diamond‑shaped topology of task sub‑goals. It models the execution as an Interaction‑State Transition Graph, identifies critical topological breakpoints during rollouts, and uses these to retrieve recovery references. A progressive self‑distillation process then applies localized supervision only on recovery steps, preserving valid reasoning prefixes and enhancing policy diversity.
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. 02302v1 Announce Type: cross Abstract: Long-horizon coding-agent trajectories are poorly matched to the credit units available to train on: a single action has no stable value, an episode label merges productive exploration with abandoned directions, and a fixed window cuts where the logging mechanics fall.
arXiv:2602. 05459v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method.
The paper introduces HALTER, a graph-based system that automates the reset and evaluation of long-horizon robot manipulation tasks. HALTER constructs a spatial scene graph from point clouds and vision models, uses an LLM to score rollouts, plan resets, and verify success, all without labeled success images. In experiments on a Franka arm, HALTER restores scenes in 76% of episodes, improves skill completion estimation, and reduces operator time by 72% compared to manual reset.
DART‑SD introduces a diamond‑topology aware framework for training large language models to perform multi‑turn tool‑calling. It models the execution process as an Interaction‑State Transition Graph, identifies critical topological breakpoints, and retrieves recovery references to guide localized self‑distillation. Experiments show that this approach outperforms traditional full‑trajectory baselines on complex multi‑turn tool‑calling benchmarks.
The paper investigates the reliability of tool‑using agents, focusing on two failure modes: selecting the wrong tool and constructing incorrect arguments. It introduces a correct‑invocation rate metric to distinguish these errors and evaluates five open‑weight models on multi‑step tasks up to depth 8, finding that by depth 6 about 70% of a model’s clean‑context capability is lost due to earlier mistakes. The study reveals that exact‑match scoring against a fixed gold trajectory forces severity and recovery parameters to extreme values, and proposes a conditional‑on‑state scoring remedy that yields more realistic severity estimates.