The paper introduces RADT, a decision transformer for offline, reward‑free, goal‑conditioned reinforcement learning that can handle arbitrary avoid‑regions specified at evaluation time. By encoding goals and avoid‑regions as prompt tokens and using an avoid‑region hindsight relabeling strategy, RADT learns reach‑avoid behavior from suboptimal random trajectories without reward or cost supervision. Across 17 tasks and environments, RADT outperforms existing offline goal‑conditioned RL models, achieving significant zero‑shot generalization to novel avoid‑region sizes and counts, and is also applied to a biological cell reprogramming task.
By Kevin Li, Marinka Zitnik
The paper introduces Online Rubric Self-Distillation (ORSD), a method that extracts natural‑language process rubrics from agent trajectories and uses them as dense token‑level supervision signals. ORSD generates multiple rubric bundles per step, verifies them against trajectories, and selects the bundle that best aligns rubric satisfaction with task success. The selected rubric is then used to compute token‑specific process credit, which is added to the trajectory‑level advantage to enable fine‑grained credit assignment. Experiments on ALFWorld and WebShop demonstrate that ORSD speeds up policy learning and improves final performance for Qwen3 models within the same interaction budget.
By Shumao Wu, Kongcheng Zhang, Jianqiang Huang, Baisheng Lai
arXiv:2611.05730v1 Announce Type: cross
Abstract: Two foundational aspects of human cognition, abstractness and gender, are typically examined as separable. Here, we find they are systematically link...
By Douglas Guilbeault, Bhargav Srinivasa Desikan
Recent work in machine learning has demonstrated that transformer-based language model agents can communicate state not only through text, but also directly in latent space via key-value (KV) caches....
LLM agents are increasingly used for repository-level software engineering tasks. However, most agents still access repositories through raw files, lexical search, and shell commands, treating code pr...
Researchers use large language models as agents in social simulations, where agents are prompted with observations and background information intended to shape their actions. Yet LLM agents have been...
We introduce LifeVal, a benchmark evaluating AI model performance on personalized agentic consumer tasks. LifeVal covers the most valuable life tasks that a personalized digital superassistant could a...
The article announces the release of datasette-llm version 0.1a10. It reports a bug fix that corrects the demo site at agent.datasette.io, ensuring that only LLM models specified in the configuration are available. The update addresses a configuration issue affecting model availability.
Unmanned aerial vehicle (UAV)-based collaborative perception enables multiple agents to share complementary perceptual information, overcoming limitations such as occlusion and limited sensing range....
Resource management for distributed edge networks hosting different services has been handled efficiently using Reinforcement learning (RL). Reward generalization in complex workflows is still an open...
Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression,...
AI's inflection point is a fountain of alarming risks. Digital platforms in particular are vulnerable to three major AI risks, as those in control of global platforms cede control to AI, of the algori...
Large language model (LLM) coding assistants and agents construct a repository context before generating code. For security-sensitive code, this context decides whether the model sees the project's sa...
OpenAI developed an autonomous pipeline that identified, validated, and produced patches for 948 local privilege‑escalation vulnerabilities in the Linux kernel. The system automatically discovered the issues, confirmed their validity, and generated the necessary code fixes. This demonstrates a large-scale, automated approach to kernel security remediation.
IndicDBBench is a new multilingual Text-to-SQL benchmark that evaluates cross‑lingual semantic parsing across 20 databases and 237 tables in seven languages, including English and six Indic languages. The benchmark uses real‑world open‑data schemas from NDAP and IDP, and a three‑agent pipeline to create complex relational structures with high relational density and join depths up to six. Evaluation of state‑of‑the‑art models shows a 9‑point drop in execution accuracy from English to Indic languages, revealing an "Indic Gap" that persists even when gold tables and literal values are supplied.
By Aviral Dawar, Roshan Karanth, Vikram Goyal, Rakhee Kulshrestha, Sumanta Pasari, Dhruv Kumar
ElectroChemLLM is a multimodal large language model pipeline that extracts structured electrochemical records—such as electrolyte compositions, electrode materials, cell configurations, and measured physicochemical properties—from unstructured scientific PDFs. By combining hybrid document parsing with vision-capable LLM orchestration, it captures data across text, tables, and figures, achieving an F‑1 score of 0.97 on a benchmark of 232 battery‑electrolyte papers. The extracted data populate ElectroChemDB, a database of 15,000 research articles, which is then used to train machine learning models for electrolyte property prediction, demonstrating a full workflow from literature to materials discovery.
By Dikshya Mohanty, Manoj Praveen Nandigama, Kuldeepsinh Raj, Sourav Kanti Maiti, Jiannan Yang, Ruiqi Luo, Srinivasa Phani Madhav Marupudi, Mounika Geriki, Prayag Raghunandan, Puneet Lingutla, Tengfei Ma, Niranjan Balasubramanian, Nav Nidhi Rajput
MemRole is a framework that explicitly models the memory-to-decision process for large language model (LLM) role‑playing agents, enabling them to make role‑consistent decisions over long narrative horizons. It introduces Long‑Horizon Memory Thinking (LHMT), a reasoning schema that decomposes hidden reasoning into context understanding, memory activation, and response strategy planning, and is trained on a novel dataset that limits each character’s memory pool to what it could plausibly know at the current narrative point. The framework also includes Self‑Refining On‑Policy Self‑Distillation (SR‑OPSD), where the model critiques its own rollouts and distills token‑level guidance back into the policy, resulting in a 15.2‑point improvement over its backbone and competitive performance with frontier LLMs such as GPT‑5.4.
By Mengting Li, Xilong Cheng, Zhihao Xiao, Zhenhua Xu, Jingyuan Zhou, Linfeng Li, Long Zhang, Borui Cai, Yunxiao Qin
The paper introduces TRIO, a retrieval‑augmented generation framework that uses three agents—query extension, judge, and answer—to iteratively refine queries and improve retrieval and answer quality. It aligns each agent’s objective with rewards derived from answer quality, employs unanimity voting to label expanded queries, and applies dynamic matching‑based rewards with curriculum learning for the answer agent. Experiments on multiple benchmarks show TRIO outperforms state‑of‑the‑art methods.
By Yingtao Ren, Xiao Luo, Yiwei Fu, Jinzhao Zhou, Yu-Cheng Chang, Chin-Teng Lin
The paper surveys the evolving field of agent skill evaluation and evolution, emphasizing the shift from isolated skill creation to automated, evaluation-driven development. It categorizes skill evolution into four paradigms—execution feedback, trajectory distillation, compression, and reinforcement learning—and analyzes six skill-centric benchmark categories to highlight gaps and trade-offs. The authors outline open research directions for building generalizable, efficient, and verifiably safe skill ecosystems.
By Kexin Ding, Yang Zhou, Can Jin, Feng Tong, Mu Zhou, Dimitris N. Metaxas
TMax is an open reinforcement‑learning recipe that trains terminal‑using agents from small language models, achieving 33% on Terminal‑Bench 2.0 with only 9B parameters and outperforming larger prior models. The approach generates training data via a novel taxonomy that blends difficulty control, personas, and verifier diversification, enabling cheap creation of many terminal environments for both RL and supervised fine‑tuning. The recipe is applicable to models ranging from 2B to 27B across different families, dominating the Pareto curve for open terminal‑agent performance at smaller sizes.
By Hamish Ivison, Junjie Oscar Yin, Rulin Shao, Teng Xiao, Nathan Lambert, Hannaneh Hajishirzi