Agents papers
What AI researchers are reading: the papers the Hugging Face community picks each day, and new arXiv submissions in the directions we follow. Titles and abstracts are arXiv’s; every paper links to arXiv.
Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
Ziang Liu, James J. Kim, Yijia Dai et al.
LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence…
Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents
Megha Srivastava, Michael H. Lim, Allison M. Keys et al.
Predicting how a ligand binds to its target is central to small-molecule drug discovery. Modern cofolding models can generate diverse candidate poses, but reliably ranking these candidates remains challenging. We introduce Pyrite, a pairwise pose-ranking benchmark comprising 1,500 pose pairs across diverse…
Continual-ARC: Measuring Skill Acquisition over a Working Lifetime
Daniel Lenton
Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single family of learner, so memory-based and…
Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents
Howard Zhang, Chuck Arvin, Logan Brown et al.
Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging,…
ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows
Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya et al.
Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choose every step of every run, which adds latency and cost at scale. We present ReTrace, which turns…
ARE-bench: Benchmarking Agents' Research Ability in Real-World Researcher Sessions and Workspaces
Jiahang Lin, Wanying Ren, Wanghan Xu et al.
Research agents achieve increasingly strong benchmark scores, yet these scores do not necessarily translate into reliable delivery in ongoing research projects. Many research-agent benchmarks emphasize standalone tasks and relatively self-contained workflows in clean or curated workspaces. However, researchers ask…
When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
Runxuan Tang, Haoyu Gao, Yuyan Ding et al.
LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an…
Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication
Ofri Elbaum, Amit Malik, Tomer Malkevich et al.
Children's peer conflicts increasingly play out in group chats, where tone and timing are stripped away, and a hurtful message is easier to send than to say aloud. We present Lilo, a multi-agent conversational system that lets children practice such conversations, so they are better prepared when they encounter…
Personalized Affective Perception via Continual Learning in Human-Agent Negotiation
Mehmet Onur Keskin, Berk Buzcu, Nikhil Churamani et al.
Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that…
PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles
Javier Hernandez, Andrew D. Wilson
As large language models power autonomous agents, understanding how they collaborate and where they fail becomes critical. We introduce PARLEY, an extensible platform for studying LLM agent collaboration through four asymmetric puzzle tasks grounded in cognitive psychology (referential communication, joint…
Verifiable Agentic Traffic Class: A Policed Quality-of-Service Mechanism for Agentic AI Traffic, Evaluated from Simulation to Real-Kernel Adversarial Testing
Naveen Babu Narayanan Nair, Sajay Kurup
Software agents built on large language models generate traffic unlike human web traffic, yet routers have no class for it and cannot verify a sender's claim to be an agent. This paper proposes the Verifiable Agentic Traffic Class (VATC), which combines a reserved Differentiated Services Code Point (DSCP) value…
Tree-Ising: Repairing Language Models with Bit-Level Ising Edits
Hadi Salloum, Ammar Ali
Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million tokens, and 50 forward-pass requests.…
Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
Yukyeong Lee, Yumin Choi, Jinheon Baek et al.
External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or…
LEASH: Stay Safe in Agentic Robotics
Qinfeng Zhu, Weiguang Zhao, Ke Sun et al.
Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to control robots poses serious safety…
Learning to Act with World Models by Valuing What Comes Next
Chenghao Gao, Zhi Zhang, Dian Jin et al.
A sparse terminal reward tells an agent little about its steps. Much of the missing information is implicit in the environment's dynamics, because each state transition can change the conditions for success long before the reward arrives. A world model trained on real transitions can learn to predict what each…
World In-Context Learning for Agentic Robot Manipulation
Heng Fang, Zehui Guo, Yuehan Zhang et al.
Trained action policies write manipulation skill into network weights, tying what is learned to the distribution it is learned from. In-context learning (ICL) avoids this coupling but has not matched trained policies, because a demonstration recorded in another scene carries no feedback from the world the robot…
Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning
Haozhi Yuan, Handong Li, Yifan Zhang et al.
Agentic reinforcement learning (RL) and multi-teacher on-policy distillation (MOPD) offer complementary routes to post-training. For visual agents, however, tool use presents two related challenges. Models may overlook useful tool-returned observations, while poorly grounded actions can limit the evidence available…
Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization
Zhengyu Hu, Zheyuan Xiao, Yike Wang et al.
In this work, we study whether frontier agent can continually improve real-world AI infrastructure over long horizons. We introduce Infrathon, a benchmark of diverse, long-horizon AI infrastructure optimization tasks across different levels. We evaluate six models across 150 runs with 24-hour budgets, totaling over…
InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure
InfraRSI Team, Yuchuan Tian, Haocheng Mei et al.
While Recursive Self-Improvement (RSI) accelerates isolated algorithm and kernel synthesis, distributed LLM training depends on tightly coupled launch settings, operator kernels, and communication schedules, where single edits often hit out-of-memory (OOM) boundaries, compiler conflicts, measurement jitter, or…
Embodied First Exam
Kangrui Wang, Qineng Wang, Changhe Chen et al.
Early successes on agentic robotics point to a potential paradigm shift toward using coding agents to control robots. Existing robotics benchmarks are built around visuomotor policy learning, leaving it open whether coding agents can reliably control diverse robots under physical-world constraints. We therefore…
How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time
Ku Onoda, Haruto Kawano, Shota Takashiro et al.
World models enable agents to plan and learn from imagined experience, but in an unfamiliar environment they must learn its mechanics from limited interaction. A mechanic is a rule for how an action or an interaction changes part of the environment. Each occurrence of a mechanic that the model observes is one…
Toward the Era of Agentic Embodied Intelligence
Chao Liang, Ke Chen, Fengxiaoxiao Li et al.
Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and…
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?
Yue Zhang, Jilei Sun, Liqiang Jing et al.
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal…
ReproBridge: Building Reproducibility into ML Research Artifacts
Yubo Wang, Rui Meng, Jaehyun Nam et al.
Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask…
SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research
Jinwoo Hwang, Sukmin Cho, Tao Zhang et al.
LLM agents increasingly drive systems research and rely on simulators to evaluate candidate designs at scale. Simulators are imperfect by design: their modeling limitations can distort predictions yet leave the recommended design correct, or change which design should be selected. We introduce Siris to test whether…
EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery
Haoran Zhang, Huizhen Sun, Hanbin Wen et al.
While multimodal agents now carry out complex data analysis with tools, their ability to turn decades of satellite imagery into reliable land-change analysis, crucial for Earth observation science, remains unmeasured. Existing benchmarks fall short: they pose questions on curated images or give agents preprocessed…
FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance
Yupeng Cao, Xueqing Peng, Lingfei Qian et al.
Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest. The data must come from the Web, the strategy lives in the user's head, and correctness depends on time, so an agent can fail silently: a strategy the user never asked for, unverified data, or a backtest that…
Micius-Flash: Lightweight Agentic Intelligence for Engineering
Hongcheng Gao, Weiheng Li, Yipeng Wei et al.
We introduce Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window. We design the Micius data pipeline as a knowledge-tree-driven data flywheel comprising three stages: knowledge tree construction and expansion, data synthesis, and…
FlyHash for LLM Agent Memory: An Empirical Validation and a New Application
Mohan Bheemadolu, Chrisogonas O. Odhiambo
Large language model (LLM) agents increasingly rely on external memory stores to retain information across conversations, typically via dense vector embeddings searched with approximate nearest-neighbor methods. The fruit fly's olfactory circuit computes a locality-sensitive hash of sensory input using a strikingly…
From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents
Xingyu Yi, Xinya Zhang, Yunshen Zhou et al.
A scientific agent can give the same verdict while reading and citing different evidence. BioAgent-DF tests this separation using paired reference and candidate values saved at the same scientific computation site. It restores or transplants those values at their original coordinates, then runs the agent on healthy…
Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation
Chengcheng Wang, Yuheng Shi, Siyu Xu et al.
Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 22.5% under the…