Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks

Agentic retrieval combining LLM reasoning with dense retrieval improves nDCG@10 by 8.7 points over standard retrieval but requires 107 seconds and 764K input tokens per query.

Reza Esfandiarpoor, Radek Osmulski, Yauhen Babakhin, Gabriel de Souza P. Moreira and 7 more

Published Oct 5, 2026 · ▲ 7 on Hugging Face

EVISKILL: Grounding Skill Evolution in Replayable Evidence

EVISKILL grounds LLM skill evolution in replayable evidence cards linking edits to supporting contexts, using targeted replay for verification and global validation for incorporation.

Yan Zhou, Yili Wang, Yiwei Dai, Qinggang Zhang and 1 more

Published Oct 4, 2026 · ▲ 11 on Hugging Face · Code ★ 8

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

ASCENT online test-time trains agents by self-distilling verified deployment trajectories into LoRA weights via a frozen hindsight model, improving long-horizon success and efficiency without external teachers or memory retrieval.

Haodong Lu, Dong Gong

Published Oct 4, 2026 · ▲ 17 on Hugging Face

Code2Games: Enabling Coding Agents for Gaming World Generation

Code2Games coordinates scene analysis and gameplay planning via shared representations to generate consistent gaming worlds and adapt them to Unreal Engine 5. The framework improves visual quality, interactive fidelity, and playable-game quality over direct coding-agent generation on the GameCode4D

Wei Wu, Ziyang Xu, Zeyu Zhang, Yang Zhao and 1 more

Published Oct 4, 2026 · ▲ 6 on Hugging Face · Code ★ 4

SearchJev: A Fast and Calibrated System-1 Model for Search Agents

SearchJev is a fast calibrated System-1 model that scores search decisions directly without autoregressive generation, improving decision quality, speed, and calibration over same-size language models.

Congfeng Cao, Lipeng Zuo, Konstantinos Papakostas, Qiwei Xu and 5 more

Published Oct 4, 2026 · ▲ 20 on Hugging Face · Code ★ 8

Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It

LLM agents show strong source preferences across search domains that can override item quality, though supplying missing information or countering preconceptions reduces this bias.

Jonghyun Song, Haewon Park, Jeonghoon Shim, Woojung Song and 1 more

Published Oct 2, 2026 · 0 citations · ▲ 43 on Hugging Face

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Recursive Self-Rewrite uses diverse harnesses and recursive revision to rewrite successful terminal trajectories for supervised fine-tuning, boosting pass@3 by up to 7.6x on hard benchmarks.

Zongxia Li, Yucheng Shi, Zhongzhi Li, Junyao Yang and 6 more

Published Oct 2, 2026 · 0 citations · ▲ 100 on Hugging Face

Harness-Aware Distillation for Small Language Model Agents

Harness-Aware Distillation focuses agent distillation on capabilities beyond the fixed harness via action preferences and validity checks, improving long-horizon agent performance without task rewards.

Moonseok Choi, Taehong Moon, Giung Nam, Juho Lee

Published Oct 2, 2026 · 0 citations · ▲ 4 on Hugging Face · Code

Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery

ADSD links numerical diagnosis to reusable solver self-improvement, reducing mean solver error by nearly 71x across four challenging numerical domains.

Peter Chen, Wotao Yin

Published Oct 2, 2026 · ▲ 8 on Hugging Face

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

VeriHarness turns fixed base LLMs into agentic verifiers with workspaces and evidence tools, achieving top selection scores and 6.2, 6.4 point gains over single rollouts on long-horizon tasks.

Caiqi Zhang, Rujun Han, Zifeng Wang, Zoey CuiZhu and 3 more

Published Oct 1, 2026 · 0 citations · ▲ 55 on Hugging Face · Code ★ 54

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Selection-based Structured Reasoning replaces open-ended reasoning with selection among reusable candidates, cutting per-turn latency over 90% while matching leading small-model search agents' success rates.

Feiyu Gavin Zhu, Xiaoyu Zhu, Jiqi Yang, Rui Yang and 8 more

Published Oct 1, 2026 · 0 citations · ▲ 3 on Hugging Face · Code

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

ActiveSaddler automates curriculum learning for agent harness optimization via non-stationary bandits that adapt training scenarios to evolving failure patterns, boosting Pass@1 by 4.4, 7.5 points.

Sungho Park, Wonjoong Kim, Jue Zhang, Wook-Shin Han and 7 more

Published Oct 1, 2026 · ▲ 82 on Hugging Face

From Knowledge Access to Source Learning: Developing Source-Specific Competence

SourceLearn develops reusable source-specific competence via persistent source models and dual learning mechanisms, outperforming retrieval and memory baselines by up to 22.6 points.

Lucheng Fu, Kejing Xia, Yiyang Wang, Yiqiao Jin and 9 more

Published Oct 1, 2026 · 0 citations · ▲ 9 on Hugging Face · Code

Code Owns the Simulation, Jev Owns the Evaluation

Judgment models excel at evaluation but fail at simulation, yet pairing them with code simulation yields expert control.

Yaodong Yang, Hongyao Tang, Yi Ma, Xingyu Fan and 3 more

Published Oct 1, 2026 · 0 citations

Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

Frontier models follow unreliable external guidance; training improves selective reliance, identifying it as a key agent reliability dimension.

Minghan Wang, Boyuan Wang, Jinhang Zuo, Yuxin Tao and 1 more

Published Sep 30, 2026 · 0 citations · ▲ 67 on Hugging Face

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Mid-Harness verifies candidate terminal actions at the model-harness boundary, raising TerminalBench-Lite Pass@1 from 50.00% to 68.03% and improving success at lower token cost than trajectory scaling alone.

Minki Kang, Ryo Hachiuma, Shaokun Zhang, Subhashree Radhakrishnan and 7 more

Published Sep 30, 2026 · 0 citations · ▲ 116 on Hugging Face

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Self-evolving search agents suffer co-cheating where proposers and solvers mutually reinforce errors; CrossFit partitions sources to cross-fit agreement and cuts false agreement by over half, boosting downstream search by 8+ points.

Meijia Chen, Hao Li, Zheng Lu, Hongshan Lin and 11 more

Published Sep 30, 2026 · 0 citations · ▲ 672 on Hugging Face

GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

GraphForge synthesizes workspace tasks and verifiers over real file evidence graphs to train working agents, and fine-tuning Qwen3.6-27B improves GDPVal, Workspace-Bench-Lite, and SpreadsheetBench II results.

Qisheng Su, Hanchen Wang, 朱冠儒, Huicheng Jiang and 8 more

Published Sep 30, 2026 · 0 citations · ▲ 146 on Hugging Face

EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making

EVOKE improves LLM agent transfer by ranking actions under diverse goals at fixed states to elicit pretrained world knowledge for robust decision-making.

Yuhan Guo, Jinming Liu, Liang Xu, Ziqiang Li and 7 more

Published Sep 29, 2026 · 0 citations · ▲ 78 on Hugging Face · Code ★ 7

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

A Builder learns reusable meta-skills from target feedback to construct execution harnesses that boost target performance on unseen tasks. Meta-skills improve macro-average scores by 8.95 points over no-skill construction and 12.02 over direct delivery.

Cheng Qian, Kunlun Zhu, Beibin Li, Zhenhailong Wang and 1 more

Published Sep 29, 2026 · 0 citations · ▲ 83 on Hugging Face · Code ★ 9

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

AREX-2 synthesizes long-horizon reflective trajectories to train a Qwen3.8-27B agent that self-improves at test time, achieving strong results on MLE-bench, Frontier-CS, and deep research benchmarks while scaling with iteration budget.

Hongjin Qian, Chaofan Li, Kun Luo, Wenqing Wei and 10 more

Published Sep 29, 2026 · 0 citations · ▲ 139 on Hugging Face · Code ★ 31

Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym

Proactive LLM agents need joint optimization of task capability, temporal compute allocation, and user trust, with Proactivity-Gym exposing evaluation gaps and human preference for unobtrusive assistance.

Jio Oh, Seunghyun Do, Youngjun Lee, Steven Euijong Whang and 1 more

Published Sep 29, 2026 · 0 citations · ▲ 28 on Hugging Face

Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation

RASO retrieves and adapts external skills via cross-harness adaptation to initialize and iteratively update agent skills, outperforming non-retrieval baselines across benchmarks.

Jaewon Chu, Ji Soo Lee, Jihwan Park, Dohwan Ko and 7 more

Published Sep 29, 2026 · ▲ 63 on Hugging Face

AIM: Agentic Idea Management for Automated Research

AIM autonomously manages research ideas via Bayesian-inspired selection and auditing to outperform baselines by up to 4.9 points and speed up search up to 3.1x.

Hyeong Kyu Choi, Bhavana Dalvi Mishra, Jiefeng Chen, Mihir Parmar and 6 more

Published Sep 29, 2026 · 0 citations · ▲ 51 on Hugging Face

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization

X-Tree learns reusable hierarchical skills from agent trajectories and improves success rates up to 5.8% across web and science benchmarks.

Sitao Cheng, Xunjian Yin, Zhiyuan Sun, Yuxuan Li and 3 more

Published Sep 26, 2026 · 0 citations · ▲ 76 on Hugging Face · Code ★ 2

PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins

PluginRSI evolves agent harnesses via reusable plugins, improving over existing methods and accelerating optimization on unseen tasks.

Yaorui Shi, Yuchun Miao, Yuxin Chen, Jiayuan Zhang and 4 more

Published Sep 26, 2026 · 0 citations · ▲ 7 on Hugging Face

From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis

CEG-Agent introduces causal error graphs and a taxonomy separating anomalies, errors, and failures to diagnose agentic traces, achieving state-of-the-art results on the CEG-Bench benchmark.

Shu-Xun Yang, Yidong Wang, Zhuoer Feng, Bosi Wen and 6 more

Published Sep 26, 2026 · 0 citations

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

RRSI regularizes recursive agent harness self-improvement via annealed edit budgets, trajectory exploration, and critical selection to boost out-of-distribution performance and reduce token use. It improves up to 14.1 points in-distribution and 4.7 points out-of-distribution while cutting policy tok

Peng Xia, Rujun Han, Zifeng Wang, Yanfei Chen and 10 more

Published Sep 21, 2026 · 0 citations · ▲ 222 on Hugging Face · Code ★ 1,293

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

NeoHorse-1 closes an evaluation-selection-update loop via harness-mediated routing, structured post-training, and capability-guided data allocation, raising 4B and 9B macro-averages by ~6 and ~3.4 points.

NeoHorse Team, Guoliang Cao, Guohao Dai, Tianyu Guo and 33 more

Published Sep 8, 2026 · 0 citations · ▲ 327 on Hugging Face · Code ★ 1,673

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Apodex 1.1 scales agentic intelligence via environment and coordination scaling to achieve leading complex-work performance with smaller models.

B. An, B. An, B. Wang, B. L. Wang and 36 more

Published Aug 24, 2026 · 0 citations · ▲ 212 on Hugging Face · Code ★ 5,146

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

StateM improves long-horizon agent accuracy via durable-state harness scaling without model changes, reaching 95.3% on Terminal-Bench 2.1 and cutting API costs to about $15 versus $574.68.

Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang

Published Aug 15, 2026 · 0 citations · ▲ 452 on Hugging Face · Code ★ 1,312

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SkillOpt treats agent skills as external state optimized via bounded text edits validated on held-out scores, improving accuracy up to 24.8 points with stable transfer.

Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang and 11 more

Published May 22, 2026 · 2 citations · ▲ 267 on Hugging Face · Code ★ 18,090

RewardHarness: Self-Evolving Agentic Post-Training

RewardHarness evolves agentic evaluation tools from minimal preference data to judge image edits, surpassing GPT-5 accuracy with 0.05% training annotations.

Yuxuan Zhang, Penghui Du, Bo Li, Cong Wei and 10 more

Published May 9, 2026 · 0 citations · ▲ 244 on Hugging Face · Code ★ 69

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

SkillClaw enables collective skill evolution in multi-user LLM agent ecosystems by aggregating cross-user interaction trajectories and autonomously updating shared reusable skills, significantly improving real-world agent performance.

Ziyu Ma, Shidong Yang, Yuxiang Ji, Xucong Wang and 4 more

Published Apr 9, 2026 · 0 citations · ▲ 225 on Hugging Face · Code ★ 2,669

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

MiroThinker-H1 integrates local and global verification into reasoning for reliable multi-step problem solving and achieves state-of-the-art deep research performance.

MiroMind Team, S. Kamala Bai, L. Bing, L. Lei and 36 more

Published Mar 16, 2026 · 0 citations · ▲ 187 on Hugging Face

A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents

This survey organizes LLM agentic reasoning into foundational, self-evolving, and collective layers, distinguishing in-context and post-training methods across applications while outlining open challenges.

Tianxin Wei, Ting-Wei Li, Zhining Liu, Xuying Ning and 25 more

Published Jan 18, 2026 · 1 citation · ▲ 208 on Hugging Face · Code ★ 1,398

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

MiroThinker introduces interaction scaling to train open-source research agents for deeper tool use, achieving up to 81.9% on GAIA and rivaling commercial models.

MiroMind Team, Bai, Song, Lidong Bing, Chen, Carson and 36 more

Published Nov 14, 2025 · 0 citations · ▲ 197 on Hugging Face · Code ★ 8,419

ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents

ChatSOP introduces an SOP-guided MCTS framework that improves LLM dialogue agents' controllability and task success by following structured operational procedures.

Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao and 12 more

Published 2025 · 3 citations

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

RL post-training yields progress advantage, a log-ratio that recovers optimal step-level advantage without dedicated reward models, outperforming trained alternatives across agent benchmarks.

Changdae Oh, Wendi Li, Seongheon Park, Samuel (Min-Hsuan) Yeh and 2 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 12

StylePlan: Style-Conditioned Intent Planning for Zero-Shot Coordination

Xiao Su, Jian Zhou

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

The Scaling Laws of Skills in LLM Agent Systems

Qiguang Chen, Qiming Yu, Yuhang Gu, Zhuoye Huang and 11 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Refining Compositional Diffusion for Reliable Long-Horizon Planning

Kyowoon Lee, Yunhao Luo, Anh Tong, Jaesik Choi

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Wayfinder: Adaptive Resource Routing from Agent Citations

Miguel Romero Calvo, George Karypis

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

Kshitij Mishra, Abhijith Sharma, Nils Lukas, Salem Lahlou

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Med-Agentic: Distilling Agentic Medical Reasoning with Internalized Meta-Capabilities

Yucheng Zhou, Junwei Sheng, Jianbing Shen

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Unifying Reasoning and Planning through Energy Minimization

Adrian Rodriguez, Angelica Kim, Yunhui Guo, Yilun Du

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Recursive Semantic Divergence for LLM Agent Consistency

Harshavardhan Abichandani, Penny Chong, Atin Ghosh, Daniel Dahlmeier

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

The Geometry of Agent Skills: Non-Commutative Composition in Representation Space

Junda Wu, Yifan Wang, Zihan Huang, Xunyi Jiang and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

AgentAbstain: Do LLM Agents Know When Not to Act?

Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani and 4 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

AgentSSL: Can MLE Agents Leverage Unlabeled Data?

Akanksha Sarkar, Ethan Lin, Ziang Liu, Kristin Branson and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

RADAR: Routing Agents via Difficulty-Aware Recovery

Haizhou Du, Jinze Zhao, Huaicheng Yan

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents

Zimo Yin, Haipeng Jiang, Kailong Ren, Zhetao Sun and 7 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide VQA

Chunze Yang, Qidong Liu, Wenjie Zhao, Yue Tang and 9 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

ExperiGen: Agentic Hypothesis Discovery from Observational Data

Jishu Sen Gupta, Harini S I, Somesh K Singh, Mohamad Tawseeq Syed and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation

Dong Li, Yanchi Liu, Xujiang Zhao, Wei Cheng and 5 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

AgenTracer-v2: Agentic Failure Tracer for LLM Agentic Systems

Guibin Zhang, Haoyu Lu, Junhao Wang, He Zhu and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories

Xuebin Li, Hanqing Zhao, Siyuan Liang, Kejiang Chen and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy Flywheel

Meng Cao, Pengfei Hu, Yingyao Wang, Chen Wang and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

LLM-ACES: Closed-Loop Discovery of Dynamic Systems with LLM-Guided Adaptive Search

Nikhil Abhyankar, Sha Li, Sanchit Kabra, Naren Ramakrishnan and 2 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace

Simon Yu, Derek Chong, Ananjan Nandi, Dilara Soylu and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making

Heewon Park, Somin Im, Minhae Kwon

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents

Yuanpu Cao, Saket Sathe, Hanyu Wang, Ziyi Yin and 2 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Can AI Agents Synthesize Scientific Conclusions?

Hayoung Jung, Pedro V Diniz, José R Roveda, Abner F da Silva and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Agentic Video Editing from Underspecified Requests

Yongsheng Yu, Ziyun Zeng, Zhiyuan Xiao, Zhenghong Zhou and 3 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

MemeEconomy : Do LLM Agents Trade Ethics for Survival?

Syed Nazmus Sakib, Nafiul Haque, Ahnaf Manan, M. M MORSHED and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Calibration Is Not Control: Intervention Advantage for LLM-Agent Oversight

Chubin Zhang, Zhenglin Wan, Xingrui Yu, jingxuan wu and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents

Deyuan (Mike) He, Ankush Desai, Sharad Malik, Aarti Gupta

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

SeaPilot: Mobile Agent with Self-refining Environment Alignment

Zhigang Zuo, Senyao Li, Yufeng Jiang, Haozhao Wang and 4 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation

Xilin Dang, Weilin Ruan, Xue Yang, Jinghao Wang and 3 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

Temperature Guidance For Robust Reward Conditioning In Diffusion Planning

Johannes V Busch, Roberto Calandra

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Ming Zhong, Stacy Li, Nicholas Carlini, Matthew Jagielski

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

AIRA-Compose: Agentic Discovery of Neural Architectures

Alberto Pepe, Chien-Yu Lin, Despoina Magka, Bilge Acun and 4 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Plan2Sense: Open-World Task Planning in Epistemic States via Interleaved Ontic and Sensing Actions

Xiaotian Liu, Armin Toroghi, Jiazhou Liang, Ali Pesaranghader and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Runtime Verification of Multiple Natural Language Criteria for Agent Governance

Silviu Pitis, Parand A. Alamdari, Jessica Tang, Toryn Klassen and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support

Otto Nyberg, Fausto Carcassi, Davide Tugnoli, Giovanni Cinà

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory

Minghao Chen, Xinyi Hu, Zhou Yu, Yufei Yin

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud

Jinze Li, Xin Yang, Shuo Yang, Jinfeng Xu and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Sampling Is Not Curiosity: Why LLM Agents Should Investigate

Alfonso Amayuelas, Piotr Piękos, Xin Wang, William Yang Wang and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

The Agentic Oversight Tax: Human Supervision of AI Agents Has a Cost that Must be Accounted For

Olivier Oullier

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Treat Domain-Specific Languages as Design Variables in LLM Agents

Letian Li, Wenyuan Jiang, Xin Yang, Shuzhao Xie and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Long-Horizon Agency Belongs in the Harness, Not the Context Window Only

Yi Han, YUANYUAN XU, jusheng zhang, Wenhao Wang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision

Richard Csaky

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Agent-Native Research Artifacts

Jiachen Liu, Jiaxin Pei, Jintao Huang, Chenglei Si and 33 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Han Luo, Bingbing Wen, Lucy Lu Wang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Predicting What Changes: Causal Delta World Models for Risk-Aware LLM Agent Planning

Guo Yue, YANG LIU, Donghui Zhang, Tang Qingkang and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

MatCurvs: Article Real-Coordinate Curve Extraction for Agent-Ready Materials Reasoning

Liang Yin, Zhan'ao yao, Jiahui Shi, Songlin Yu and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Explanations over Graphs: An Agent Architecture for IT Enterprise Diagnostic Tasks

Saurabh Jha, Rohan R. Arora, Bhavya Bhavya, Noah Zheutlin and 5 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

PolyMind: Exploring Width Scaling for Reflective Reasoning in Language Agents

Heng Zhang, Chengyu Zhou, Jiajun Wu, Estella Liu and 7 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Who Wrote This Paper? Autonomous Scientific Discovery for 3DGS Research

Seemandhar Jain, Manmohan Chandraker

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring

Hyunjun Jeon, Dongha Lim, Kunwoong Kim, Daewon Choi and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Tokenizer Choice Shapes Generalization in State-Centric Learning for Planning

Vishal Pallagani, Nitin Gupta, John A Aydin, Biplav Srivastava

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

Yikun Zhang, Xiwei Cheng, Tianyu Liu, Yuanqi Du and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

AURA: An Autonomous Retouching Agent with Photographic Visual Thinking

Shuaizheng Liu, Fangzhou Han, Jiarong Liao, Yujing Sun and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

AIRA 2: Overcoming Bottlenecks in AI Research Agents

Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo, RISHI HAZRA and 21 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents

Karolis Jucys, George Adamopoulos, Özgür Şimşek

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents

Rongzheng Wang, Jiakai Li, Renzhong Wang, Rongwei Wang and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs

Haoran Luo, Ziyue Zhu, Shangyang Wu, LINHAO LUO and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?

Jiale Liu, Huajun Xi, Shaokun Zhang, Yifan Zeng and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Agent Explorative Policy Optimization for Agentic Multimodal Reasoning

Minki Kang, Shizhe Diao, Ryo Hachiuma, Sung Ju Hwang and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents

LLM research agents find high-performance models via compressed prompts and feedback, supporting a description-length explanation for limited overfitting.

Martin Bertran, Aaron Roth, Steven Wu

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

How to Interpret Agent Behavior

ACT*ONOMY introduces a three-level taxonomy of 10 actions and 46 subactions for describing autonomous agent behavior at runtime, plus an open repository and automated analysis pipeline that compares behavioral profiles and surfaces failure patterns.

Sophia Gao, Kaiser Sun, Jen-Tse Huang, Katherine Van Koevering and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

Agentic Multi-Turn Reasoning: A Fairness Approach

Fair-MPO improves multi-turn agentic reasoning via multi-level preference optimization and a fairness objective that fixes long-horizon credit assignment and data imbalance, achieving state-of-the-art benchmark results.

Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill, Jackson Cothren and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Reinforcement World Model Learning for LLM-based Agents

RWML learns action-conditioned world models for LLM agents via self-supervised sim-to-real alignment, outperforming direct task-success RL by up to 6.9 points without expert data.

Xiao Yu, Baolin Peng, Ruize Xu, yelong shen and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 on Hugging Face

PhotoFlow: Agentic 3D Virtual Photography Missions

PhotoFlow uses a Director-Reviewer-Reflector agent for closed-loop camera search to generate language-conditioned virtual photographs in arbitrary 3D scenes, outperforming baselines on quality, alignment, and success rate.

Jiarui Guo, Haojia Wei, Yiming Zhang, Yifei Liu and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face · Code ★ 43