arXiv:2610.02700v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal...
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:2610.07898v1 Announce Type: new Abstract: Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended interactions, use tools, and adapt...
arXiv:2609.09133v1 Announce Type: new Abstract: Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agen...
The paper introduces On-Policy Reminder Distillation (OPRD), a method that enhances long-horizon coding agents by combining multi-scope reminder supervision with outcome-based routing. OPRD uses successful rollouts as autoregressive self-imitation targets and failed rollouts for reminder-conditioned reverse-KL supervision from a teacher that re-evaluates student prefixes. The approach improves task resolution rates by 11.3 points and cuts error events by 50.2% on several SWE-bench benchmarks.
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.
arXiv:2609. 40285v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories.
Steering vectors (SVs) are residual-stream directions that can shift LLM behavior when added to hidden states during inference. This study investigates whether the same SVs can guide parameter updates during post‑training, exploring supervised learning (SFT and distillation) and reinforcement learning with verifiable rewards (RLVR). The authors find that SV injection improves performance over plain SFT and distillation, achieving up to a 12% gain in certain distillation settings, and that applying a correctness‑contrast direction as advantage repair in RL recovers learning signals for held‑out math benchmarks. They also identify failure boundaries related to code generation, cross‑family layer transfer, and inference‑time application on SV‑trained checkpoints.
arXiv:2608. 16333v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories.
arXiv:2608. 03674v1 Announce Type: new Abstract: Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments.
arXiv:2606. 20512v1 Announce Type: cross Abstract: LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself.
The paper introduces TISD, a trajectory-intervention self-distillation method that forces a teacher-selected branch action and then lets the student generate the suffix, distilling the full trajectory under a privileged-context-conditioned teacher. This approach addresses a data-collection bottleneck in on‑policy self‑distillation by exposing successor contexts that the student would otherwise miss. Experiments on coding and science domains show modest but consistent improvements in average performance metrics compared to baseline methods.