The paper introduces Self‑Retrospection Distillation (SRD), a method that uses post‑hoc trajectories to supervise foresight predictions made before an agent acts. SRD distills information from completed rollouts into trajectory‑blind predictions, enabling the agent to anticipate useful actions and avoid pitfalls without requiring explicit foresight at inference time. Experiments on ten tool‑integrated reasoning and long‑horizon tasks show that SRD improves performance by up to 24.2 percentage points, especially when reward signals are scarce or uniform across rollouts.
By Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi, Zhuofeng Li, Siming Zhang, Jiaxin Zhang, Jixuan Chen, Fang Wu, Pan Lu, Silvio Savarese, Julian McAuley, Chien-Sheng Wu
arXiv:2610.18614v1 Announce Type: new
Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human....
By Ashutosh Hathidara
The paper introduces Retrospective World Modeling, a new paradigm for vision‑language‑model (VLM) agents that allows them to reason backward by estimating which action most likely caused a state transition. It proposes the Self‑Consistency Reward (SCR), an intrinsic signal that measures how well a policy action aligns with this retrospective explanation, providing dense transition‑level feedback. Experiments demonstrate that incorporating SCR improves policy robustness and generalization compared to purely prospective world‑modeling approaches.
By Yongjiang Liu, Jie Zhang, Haoyue Zhang, Jingcai Guo, Deze Zeng, Song Guo
arXiv:2607. 12397v1 Announce Type: new Abstract: LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed.
By Yaopei Zeng, Congchao Wang, JianHang Chen, Nan Wang, Yurui Chang, Lu Lin
LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed. Reliable deployment therefore requires \emph{step-level confidence estimation}: a calibrated probability that each proposed action is productive, available \emph{before} the action is executed.
arXiv:2606. 27483v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks.
By Xuan Zhang, Zhijian Zhou, Lingfeng Qiao, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi
HINT-SD introduces a targeted self‑distillation framework for long‑horizon language‑model agents that uses full‑trajectory hindsight to identify failure‑relevant actions and applies feedback‑conditioned distillation only to those action spans. This selective approach reduces the need for per‑turn feedback, improving training efficiency and effectiveness. Experiments on BFCL v3 and AppWorld demonstrate that HINT‑SD outperforms dense per‑turn feedback baselines by up to 13.60 percentage points on average while cutting training time per step by 2.26×.
By Woongyeong Yeo, Yumin Choi, Taekyung Ki, Sung Ju Hwang
The paper explores Retrospection-Only Fine-Tuning (ROFT), a method where a language-model agent improves its behavior by generating and training on explanations of its own experiences, without external teachers or reward signals. In software‑engineering tasks with Qwen3.5‑4B, ROFT achieves comparable or better solve rates than GRPO while requiring fewer updates and training time, and can learn from failures alone. Behavioral analysis shows ROFT indirectly assigns credit to actions and can produce shorter, more direct solutions when prompted to focus on direct solutions.
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.
By Jan Malte T\"opperwien, Aditya Mohan, Marius Lindauer
arXiv:2608. 04788v1 Announce Type: cross Abstract: Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated.
By Yi Yang, Cong Qin, Xiaodan Liu, Chishui Chen, Qing Dong, Yan Zhang, Cao Liu, Zhao Yang, Lu Pan, Jiaye Lin, Yi Feng
arXiv:2606. 30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents.
By Ayan Pendharkar
The paper identifies an informational curse of horizon in goal-conditioned policy learning, showing that longer goal relabeling horizons during training can hurt policy generalization and performance. Controlled experiments with oracle planners separate training horizons from test horizons, revealing that behavioral cloning policies degrade with longer horizons while reinforcement learning mitigates this effect. The authors attribute this to reduced conditional mutual information between actions and hindsight-relabeled goals, and demonstrate that distilling short-horizon policy Jacobians into long-horizon policies improves performance, especially in combinatorial manipulation tasks.
By John L. Zhou, Yuxuan Dong, Jonathan C. Kao