Long-Horizon LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

60 papers in the last four weeks, up 161% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 297

May 30, 2026cs.CL

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment for sustained exploration beyond easy high-frequency entities. We propose SPADER, a reinforcement learning framework for long-horizon tool use in Multi-Answer QA. SPADER includes Step-wise Peer Advantage (SPA), a critic-free step-level credit assignment mechanism that aligns parallel trajectories by decision step and estimates advantages from peer returns. It also includes a diversity-aware exploration reward that promotes long-tail entity discovery by upweighting rare findings and downweighting redundant ones. Experiments on QAMPARI, Mintaka, WebQSP, and QUEST show that SPADER generally improves recall and overall F1 over prompting-based agents, outcome-supervised RL methods, and recent step-level supervision approaches. Our code and model weights are available at https://github.com/KhanCold/spader.

Qiming Shi, Zhaolu Kang, Yunfan Zhou +2

State Key Lab of CAD&CG, Zhejiang University · School of Software and Microelectronics, Peking University · School of Software Technology, Zhejiang University

Credit Assignment in RL Step-Level Credit Assignment in RL Question Answering Long-Horizon LLM Agents RL for Tool Use

May 29, 2026cs.CL

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing skill libraries are typically treated as model-agnostic, reusing the same skill formulations across backbones with substantially different capacities and behaviors. However, our controlled experiments across multiple model scales show that skill effectiveness is strongly model-dependent: a skill that benefits one backbone can harm another. Motivated by this observation, we propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights. MASA operates in two stages: (1) a hierarchical skill evolution pipeline that iteratively rewrites general and task-specific skills using hill climbing and UCB-driven tree search, guided by environment feedback and model capability profiles; and (2) a lightweight model-conditioned skill rewriter trained on evolution trajectories to reproduce the adaptation in a single forward pass. Experiments across three interactive environments and four backbones show that MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline. The learned rewriter further generalizes to unseen tasks and environments without additional search, consistently outperforming a much larger teacher LLM at a fraction of the inference cost.

Jianxiang Yu, Jiapeng Zhu, Bochen Lin +3

East China Normal University, Shanghai, China

LLM Agent Skill Learning LLM Agent Skill Retrieval LLM Agents Long-Horizon LLM Agents

May 28, 2026cs.AI

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-based reinforcement learning, failing to localize where intermediate memory quality degrades. As interactions unfold, ambiguous recursive summaries progressively discard task-relevant information and introduce semantic noise. This exacerbates belief deviation, obscuring the agent's estimate of the latent task state and ultimately derailing long-horizon reasoning. We therefore argue that memory optimization should focus not merely on trajectory-level success, but on the clarity of the belief induced by intermediate summaries. To this end, we introduce Belief Entropy, a self-supervised proxy that probes how uncertain the model remains about the latent task state given its current memory. Based on this proxy, we propose Metacognitive Memory Policy Optimization (MMPO). Instead of relying only on sparse outcome-based signals, MMPO provides fine-grained, memory-specific supervision via explicitly penalizing summaries that induce high epistemic uncertainty. Experiments show that MMPO consistently outperforms existing methods on diverse long-horizon tasks, maintaining 97.1% performance even when scaled to 1.75M-token contexts.

Ziyan Liu, Zhezheng Hao, Yeqiu Chen +7

University of Science and Technology of China · Zhejiang University · Tencent

Long-Horizon LLM Agents Memory-Augmented Language Model Agents

May 28, 2026cs.CL

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents

Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is currently bottlenecked by a reliance on scraped external repositories, which limits domain diversity, environment controllability, and the targeting of specific capability deficits. We introduce LiteCoder-Terminal-Gen, a zero-dependency synthesis pipeline that autonomously generates executable and verifiable terminal training environments directly from domain specifications. Using this framework, we construct two large-scale resources: LiteCoder-Terminal-SFT, comprising 11,255 expert trajectories across 10 domains, and LiteCoder-Terminal-RL, featuring 602 verifiable environments for trajectory-level preference optimization. Supervised fine-tuning of Qwen-family models on our SFT dataset yields agents that significantly outperform their base counterparts. Notably, our 32B variant achieves 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro, respectively. Furthermore, applying Direct Multi-turn Preference Optimization (DMPO) on our RL environments yields additional performance gains. These results systematically demonstrate that fully synthetic, executable environments offer a scalable and verifiable supervision signal for mastering complex, real-world command-line workflows.

Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu +5

Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences

RL for Language Models Terminal Agents LLM Agent Training Synthetic Data Generation for Language Models Long-Horizon LLM Agents

May 27, 2026cs.CL

Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents

A long-lived LLM agent, such as OpenClaw, earns its value by acting on a user's preferences and constraints across sessions, not just the current request. Yet today's agents keep what a user volunteers but rarely ask for what stays unspoken, leaving a proactivity gap in long-lived LLM agents: an agent cannot act on a preference it never obtained. As users delegate more of their affairs to agents, the impact of this gap grows. We isolate one concrete, controllable slice of this gap as Ask-to-Remember (ATR): the agent decides whether to ask now for a reusable user preference that the current task does not need but a later session with the same user will. ATR is hard even to evaluate: the right question is underdetermined and its payoff deferred to tasks that may never arise. ATRBench, to the best of our knowledge the first ATR benchmark, makes it measurable by fixing each user's preferences as hidden ground truth, so success demands asking, not recall. Across eight frontier LLM agents, defaults fall at least 62 points below an oracle handed the relevant preference, and prompting closes little of it. Diagnostics identify acquisition as the bottleneck. ATRBench surfaces this proactivity gap in current agents and offers a diagnostic testbed for closing it.

Bin Wu, Guanyun Zou, Bingbing Wang +2

Beijing University of Posts and Telecommunications · Nanjing University of Aeronautics and Astronautics · Harbin Institute of Technology (Shenzhen) +1

LLM Agent Memory LLM Agent Evaluation Proactive Assistance Long-Horizon LLM Agents Preference Elicitation Agent Benchmarks

May 27, 2026cs.AI

Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning, tool use, and iterative state updates, remains unclear. We study this question through a systematic layer-wise analysis of complete user-agent trajectories spanning three domains: Deep Research, Code Generation, and Tabular Processing. Using residual stream probes, causal layer-skipping interventions, and effective-depth measurements, we show that agentic reasoning exhibits a distinct depth profile from static tasks. As trajectories unfold, models progressively recruit more and deeper layers, with stronger long-range inter-layer dependencies emerging in later turns. At the same time, residual updates become increasingly correction-dominant, indicating a shift from stable feature accumulation toward repeated recalibration. Effective-depth analysis further reveals a substantial construction-refinement gap: semantic direction often forms relatively early, while deep layers remain necessary for stabilizing final outputs. Across model families, this gap is pronounced in Qwen and Minimax, whereas GLM shows a more domain-dependent depth allocation pattern. These results provide mechanistic evidence that autonomous LLM agents allocate depth adaptively as reasoning complexity grows.

Zhenyu Cui, Xiangzhong Luo

LLM Interpretability Mechanistic Interpretability Long-Horizon LLM Agents Adaptive Computation

May 26, 2026cs.AI

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

MiniMax, :, Aili Chen +204

Mixture-of-Experts Language Models Agentic RL AI Coding Agents LLM Agent Training Long-Horizon LLM Agents

May 25, 2026cs.AI

Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions

Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, personalized assistance requires more than following generic instruction or recognizing object categories. In real-world scenarios, the intended target is often specified only implicitly through prior interactions, requiring agents to leverage personalized context accumulated over time. In this work, we propose POLAR, a multiomodal memory-augmented framework for personalized embodied agents over long-term user interactions. POLAR organizes prior interactions into a multimodal knowledge graph that captures semantic memory for personalized context and visual concepts, and episodic memory for embodied experiences such as agent trajectories. To execute embodied tasks, POLAR retrieves relevant memories to interpret the current request and guide task execution. We evaluate POLAR across multiple MLLM backbones and diverse evaluation scenarios to study the role of memory in long-term personalization. Results show that the proposed memory mechanism consistently improves performance by enabling more effective use of information accumulated over prior interactions. The gains are especially pronounced when the agents are required to reason across multiple interactions, perform multi-hop inference, or tracking updates in user-specific context over time.

Jeongeun Lee, Chanyoung Park, Dongha Lee

Yonsei University · KAIST

Multimodal Memory Embodied AI Long-Horizon LLM Agents Memory-Augmented Language Model Agents

May 25, 2026cs.AI

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting context-sensitive reasoning and effective assistance. Existing benchmarks similarly provide only partial user state and therefore fail to capture performance in such a broad, always-on setting. To address this gap, we introduce Claw-Anything, a benchmark that expands agent context along three dimensions: long-horizon activity histories, interdependent backend services, and integrated GUI and CLI interaction across multiple devices. To instantiate this setting, we simulate months of user activity through multi-round event injection, producing complex world states and realistic noise, including irrelevant events and conflicting signals. Agents must reason over rich contextual environments while remaining robust to such noise. This expanded scope also enables the evaluation of proactive assistance, requiring agents to anticipate user needs and deliver timely recommendations. Experiments show that GPT-5.5 achieves only 34.5% pass@1, substantially below prior benchmarks, underscoring a gap between current agent capabilities and the demands of always-on personal assistance. Alongside the benchmark, we release an automated data-generation pipeline that yields 2,000 training environments and improves the base model by 23.7%, demonstrating its utility of scalable data infrastructure.

Yusong Lin, Xinyuan Liang, Haiyang Wang +8

Beijing Institute of Technology · Huawei Technologies Co., Ltd · Peking University +1

Computer-Use Agent Benchmarks AI Agent Benchmarks Proactive Assistance Long-Horizon LLM Agents Personal AI Agents

May 25, 2026cs.AI

Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents

Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory budget on transient interactions while failing to preserve critical context for long horizon tasks. To address this gap, we investigate an underexplored question: can LLM based memory systems learn personalized memory policies? We introduce PerMemBench, the first benchmark for evaluating personalized memory systems, featuring multi year, multi domain interaction histories across diverse user personas. We further present the first empirical study of memory personalization, proposing session level storage gating, a lightweight framework that selectively bypasses memory operations for transient sessions. Our study confirms that personalization yields substantial retention gains under perfect gating, yet reveals that accurate gating remains an open and critical challenge.

Yeonjun In, Wonjoong Kim, Sangwu Park +2

KAIST

Memorization in Language Models Persistent Memory for Language Models Memory Agent Benchmarks Long-Horizon LLM Agents Agent Memory Management

May 23, 2026cs.AI

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achieving a strong performance--cost Pareto frontier. Hera adopts a novel two-stage training paradigm: (1) imitation learning for cold-start, followed by (2) reinforcement learning that jointly optimizes task success and cloud usage efficiency. The first stage casts step-level routing as a supervised classification problem: the device agent is replayed on cloud trajectories, with each state labeled by the agreement between device and cloud actions. In the second stage, we perform cost-aware reinforcement learning by grouping identical states across trajectories and updating Hera with labels favoring higher expected return and fewer future cloud calls. We evaluate Hera on ALFWorld, WebShop, and AppWorld, where it consistently outperforms prior methods, achieving 92.5% of the cloud-only success rate with cloud use in only 46.3% of steps.

Yuxin Zhang, Mengxue Hu, Zheng Lin +8

1Fudan University · 2Alibaba Group · 3The University of Hong Kong +4

LLM Agent Training LLM Routing Long-Horizon LLM Agents RL for LLM Agents

May 23, 2026cs.AI

DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback

Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior. For long-horizon tasks, each rollout is costly, and a limited interaction budget may yield few examples of effective behavior. Sparse, delayed feedback also makes it difficult for a coding agent to diagnose failures and determine which modifications will improve performance. We present DemoEvolve, which uses human demonstrations to guide harness evolution under limited interaction budgets. The coding agent examines demonstrations alongside its own rollout history, extracts strategies and the conditions under which they apply, and turns them into reusable harness components. We compare demonstration guidance with self-rollout evolution and augmentation with retrieved textual knowledge under the same evolution procedure and agent interaction budget. On held-out seeds, DemoEvolve improves mean capped final-round progress from 16.83 to 20.00 in Balatro and mean floor reached from 18.17 to 28.83 in Slay the Spire 2, compared with the respective base harnesses. These results suggest that demonstrations can help harness evolution make better use of limited interaction experience by providing concrete guidance for diagnosis and modification.

Lirong Che, Yuzhe yang, Peiwen lin +4

Tsinghua University · AgiBot

Agent Harness Optimization LLM Agent Self-Improvement Learning from Demonstration Long-Horizon LLM Agents

May 23, 2026cs.AI

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning

Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether multiple peer agents, all targeting the same task, can become an additional source of capability without relying on explicit role specialization or workflow orchestration. We study this question and propose AgentFugue, a collective reasoning framework built around a shared reasoning hub. As peer agents explore the same task in parallel, the hub records concise notes on what each agent has established, attempted, or ruled out, and enables each agent to selectively access what other agents have discovered in a form useful for its current search. This design turns otherwise isolated trajectories into a connected ecology of reusable intermediate reasoning without requiring centralized planning. We instantiate the hub as a plug-in communication layer, trained with supervised fine-tuning and end-to-end reinforcement learning. Across the challenging long-horizon settings we study, AgentFugue improves over strong baselines. Our results suggest that collective reasoning can turn scaling out peer agent systems into a distinct source of capability gains, rather than merely a way of spending more compute.

Yuyang Hu, Hongjin Qian, Shuting Wang +5

GSAI, Renmin University of China · Beijing Academy of Artificial Intelligence

Multi-Agent Reasoning Long-Horizon LLM Agents Multi-Agent Communication Memory-Augmented Language Model Agents

May 22, 2026cs.CL

An Interactive Paradigm for Deep Research

Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended queries by combining retrieval, reasoning, and generation. Yet most frameworks rely on rigid workflows with one-shot scoping and long autonomous runs, offering little room for course correction if user intent shifts mid-process. We present SteER, a framework for Steerable deEp Research that introduces interpretable, mid-process control into long-horizon research workflows. At each decision point, SteER uses a cost-benefit formulation to determine whether to pause for user input or to proceed autonomously. It combines diversity-aware planning with utility signals that reward alignment, novelty, and coverage, and maintains a live persona model that evolves throughout the session. SteER outperforms state-of-the-art open-source and proprietary baselines by up to 22.80% on alignment, leads on quality metrics such as breadth and balance, and is preferred by human readers in 85%+ of pairwise alignment judgments. We also introduce a persona-query benchmark and data-generation pipeline. To our knowledge, this is the first work to advance deep research with an interactive, interpretable control paradigm, paving the way for controllable, user-aligned agents in long-form tasks.

Lin Ai, Victor S. Bursztyn, Xiang Chen +2

Department of Computer Science, Columbia University, New York, NY, USA · Adobe Research, San Jose, CA, USA

Deep Research Agents Human-in-the-Loop AI Long-Horizon LLM Agents

May 22, 2026cs.CL

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.

Jian Xie, Tianhe Lin, Zilu Wang +16

1The Ohio State University · 2Amazon AGI SF Lab

Deep Research Agents LLM Agent Training Synthetic Data Generation for Language Models Long-Horizon LLM Agents

May 22, 2026cs.AI

Parallel Context Compaction for Long-Horizon LLM Agent Serving

Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based summarization keeps the conversation bounded, but summarization is inherently lossy and the blocking call stalls agent inference for tens of seconds. Moreover, the operator has no fine-grained control over summary volume since prompt instructions are largely ignored, and as context grows, both the amount of output tokens the model produces and the information it retains fluctuate substantially from run to run, making the agent's retained knowledge unpredictable across runs. We introduce \textbf{parallel compaction} for long-horizon agentic flows and characterize it against the sequential synchronous baseline across four backbones spanning 8B to 120B parameters, mixing dense and MoE architectures with reasoning and non-reasoning models, on the HotpotQA multi-hop QA and LoCoMo long-context dialogue benchmarks. Parallel compaction gives the operator fine-grained, predictable control over summary volume and enables more targeted prompt engineering per block. At matched compaction decode volume, it reduces end-to-end wall time and improves compaction throughput over the sequential baseline.

Musa Cim, Burak Topcu, Chita Das +1

The Pennsylvania State University

LLM Inference Efficiency LLM Agent Workflow Optimization Long-Horizon LLM Agents LLM Context Management

May 21, 2026cs.AI

Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play

Static benchmarks capture only part of how large language models behave in practice. Real systems place models inside repeated loops with time limits, formatting constraints, and failure modes. We study this setting in a timed multi-phase Risk environment with explicit victory targets and repeated planning and execution cycles. In a replicated 32-game cross-provider championship under frozen rules, gemini-3.1-pro-preview won 20 of 32 games against gpt-5.1, claude-opus-4-7, and kimi-k2.6, and the pooled winner distribution differs strongly from an equal-strength null (p approx 1.5 x 10^-5). We then separate planning from execution by standardizing execution on a cheaper Gemini Flash scaffold. Under this design, a pooled 32-game planner bakeoff is consistent with near-equality (p approx 0.821), which indicates that much of the earlier provider spread came from end-to-end system behavior rather than planning alone. To study mechanism, we analyze saved planning and execution traces from the provider championship. Gemini refers to the terminal objective far more often than the other models and increases that focus as victory approaches. Gemini also converts more turns into deep conquest chains, even though it is not the cleanest runtime. These results show that live-agent performance depends on objective tracking, execution conversion, cost, and runtime reliability, and they support evaluating LLMs as components in bounded workflows rather than as isolated benchmark respondents.

H. C. Ekne

LLM Agent Evaluation AI Agent Benchmarks Long-Horizon LLM Agents LLM Agent Reliability

May 21, 2026cs.AI

IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents

Large language model (LLM)-based agents solve complex tasks by leveraging multi-step reasoning with iterative tool calls and environment interactions, which incur idle time while waiting for observations. Despite the prevalence of idle time in most agentic scenarios, existing works treat it as an unavoidable overhead or propose restricted solutions that overlook varying computational budgets across different tool calls and future observation uncertainty, thereby leading to suboptimal utilization of idle time. In this paper, we introduce IdleSpec, a scalable and generic inference approach that leverages idle-time computation to improve agent performance while minimizing latency overhead. Specifically, IdleSpec iteratively generates plan candidates during idle periods and, once observations become available, aggregates them to guide the next reasoning step. For effective plan generation under observation uncertainty, IdleSpec samples between complementary drafting strategies (i.e., progressive and recovery) from a learned distribution that is updated via posterior feedback. Our experiments demonstrate that IdleSpec significantly improves agent performance in various agentic scenarios by effectively utilizing idle time. In particular, on the GAIA and FRAMES, IdleSpec achieves 55.6% average accuracy with Gemini-2.5-Flash, surpassing the vanilla baseline without idle-time usage by 5.1%. Furthermore, for MLE-Bench, which involves substantial delay from code executions, IdleSpec achieves performance gains of up to 9.1% on the Any Medal rate, highlighting its generalizability to long-horizon tasks.

Daewon Choi, Kyunghyun Park, Woomin Song +4

1KAIST · 3Together AI · 2Amazon AGI

LLM Inference Efficiency Long-Horizon LLM Agents LLM Agent Planning

May 21, 2026cs.AI

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling

A common failure mode in long-horizon agentic test-time scaling is error propagation, where factual errors or invalid deductions introduced at intermediate steps persist in the agent's belief state and contaminate later reasoning. Existing test-time scaling methods provide limited control over this process, as they often rely on agents to detect their own mistakes, select among flawed trajectories, or refine solutions only after errors have already shaped the reasoning path. We propose ExComm, a communication protocol for exploration-stage agentic test-time scaling. ExComm is motivated by the empirical observation that the majority of intermediate errors in parallel agentic reasoning produce detectable cross-agent factual conflicts. Leveraging the iterative structure of agentic workflows, ExComm periodically audits agent belief states to detect such conflicts, resolves them through a dedicated tool-based verification loop, and returns concise, targeted feedback to the involved agents. Corrections are incorporated through soft belief updates, which append verified feedback rather than overwriting existing beliefs. Furthermore, to prevent collapsing trajectory diversity due to communication, ExComm further introduces a trajectory diversification module that redirects redundant trajectories toward orthogonal strategies. Experiments on AIME 2024, AIME 2025, and GAIA with Gemini-2.5-Flash-Lite and Qwen3.5-4B show that ExComm consistently outperforms strong test-time scaling baselines, achieving average performance gains of 5.7% and 5.0% over the best-performing baselines, respectively. Further analyses demonstrate improved error recovery, favorable scaling behavior, stronger diversity than adapted communication baselines, and the best performance-cost trade-off among the evaluated methods.

Woomin Song, Beomjun Kim, Daewon Choi +4

1KAIST · 2Amazon AGI · 3Together AI

Test-Time Scaling Multi-Agent Systems Long-Horizon LLM Agents Multi-Agent Communication

May 20, 2026cs.LG

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments is challenging because memory turns the agent's past actions into part of its future environment. Once different rollouts write, update, or delete different memories, they no longer share the same intermediate memory state, making trajectory-level comparisons fundamentally unfair. This violates a key assumption behind group-relative methods such as GRPO, where rollouts are compared as if they were sampled from the same effective environment. Consequently, trajectory-level rewards provide noisy or biased credit signals for long-horizon memory operations. To address this challenge, we introduce Memory-R2, a training framework for long-horizon memory-augmented LLM agents. Its core algorithm, LoGo-GRPO, combines local and global group-relative optimization. The global objective preserves end-to-end learning from long-horizon trajectory-level rewards, while local rerollouts compare different memory-operation outcomes from the same intermediate memory state, yielding fairer group comparisons and more precise supervision for memory construction. Beyond credit assignment, Memory-R2 jointly optimizes memory formation and memory evolution with a shared-parameter co-learning design, where a fact extractor and a memory manager are instantiated from the same LLM backbone through role-specific prompts. To stabilize multi-step RL over long memory horizons, we adopt a progressive curriculum that increases the training horizon from 8 to 16 to 32 sessions. Together, these components provide an effective training paradigm for memory-augmented LLM agents in long-horizon multi-session settings.

Sikuan Yan, Ahmed Bahloul, Ercong Nie +4

Ludwig Maximilian University of Munich · Munich Center for Machine Learning · Huawei Heisenberg Research Center (Munich) +1

Group Relative Policy Optimization Credit Assignment in RL Long-Horizon LLM Agents Memory-Augmented Language Model Agents

May 20, 2026cs.AI

SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?

LLM agents have incredible potential for scientific discovery applications. However, the performance of LLM agents on real-world, small molecule drug design (SMDD) tasks across diverse chemistries and targets is unclear. Current evaluation methods are either ad hoc, too simple for real-world discovery, limited in scale, or restricted to single-turn question answering. In effort to standardize the evaluation of LLM agents on small molecule design, we introduce SMDD-Bench, a challenging, multi-turn, long-horizon agentic benchmark consisting of 502 guaranteed-solvable task instances spanning 5 task types: 2D Pharmacophore Identification, Interaction Point Discovery, Scaffold Hopping, Lead Optimization, and Fragment Assembly. SMDD-Bench tasks span a wide region of chemical space and involve 102 unique protein targets. Completely solving the benchmark would require having strong chemical and biological reasoning and 3D intuition, understanding specialized tool use, and displaying planning expertise over a limited number of oracle calls. We benchmark 7 frontier open and closed source LLMs and find even the most performant LLM, GPT5.4, solves only 40.2% of tasks. We hope SMDD-Bench provides a standardized testbed to invigorate the field towards training and evaluating LLM agents for fully autonomous computational drug design. We host a public leaderboard at smddbench.com .

Kevin Han, Renfei Zhang, Kathy Wei +3

Carnegie Mellon University · Stealth · Pennsylvania State University

LLM Agent Evaluation AI Agent Benchmarks Long-Horizon LLM Agents Drug Discovery

May 20, 2026cs.LG

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents

LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address this by accumulating memory and reflection across episodes rather than requiring model-weight updates. However, these agents often suffer from exploration collapse: as memory grows, behavior concentrates around familiar high-reward routines, reducing the chance of discovering better alternatives. To address this problem, we propose Autonomous Policy EXploration (APEX), which builds and maintains an explicit strategy space through a strategy map-a directed acyclic graph of milestones with prerequisite dependency edges. In APEX, Fork Discovery expands the map with evidence-grounded unexplored directions, while Policy Selection balances exploration and exploitation during planning. Evaluated on nine Jericho text-adventure games and WebArena, a realistic web interaction benchmark, APEX outperforms all baselines. Extensive ablations validate each component's contribution and demonstrate robustness across diverse settings, demonstrating APEX's effectiveness for sustained exploration in self-evolving agents.

Yibo Li, Jiashuo Yang, Zhi Zheng +5

1National University of Singapore · 2Beijing University of Posts and Telecommunications

LLM Agents Long-Horizon LLM Agents Self-Evolving Agents

May 20, 2026cs.CL

MemGym: a Long-Horizon Memory Environment for LLM Agents

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory formation that occurs during extended agent execution. Consequently, the memory systems they produce transfer poorly to realistic agentic environments, such as coding and web navigation. We present MemGym, a benchmark for agentic memory that unifies existing agent gyms and in-house memory-grounded pipelines behind one memory-reasoning interface. MemGym spans five evaluation tracks grouped into four agentic regimes: tool-use dialogue (tau2-bench), multi-turn deep-research search (MEMGYM-DR), coding (SWE-Gym and MEMGYM-CODEQA), and computer use (WebArena-Infinity). MemGym reports memory-isolated scores that decouple memory performance from reasoning, retrieval, and tool-use ability, so memory strategies can be ranked without those confounders. Our synthetic pipelines for MEMGYM-CODEQA and MEMGYM-DR are length-controllable, ablation-verified at every stage, and tightly aligned with downstream scenarios. To make evaluation on coding environments academically tractable, we train MemRM, a lightweight reward model (Qwen3-1.7B fine-tuned with QLoRA) that scores compression quality as a fast scalar read in place of full Docker rollouts.

Wujiang Xu, Yu Wang, Kai Mei +8

1Rutgers University · 2Capital One · 3Princeton University +1

LLM Agent Memory LLM Agent Evaluation Memory Agent Benchmarks Long-Horizon LLM Agents Agent Benchmarks

May 19, 2026cs.AI

A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents

Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object. This paper names that boundary the stochastic-deterministic boundary (SDB): a four-part contract among a proposer, verifier, commit step, and reject signal that specifies how an LLM output becomes a system action. We argue that the SDB is the load-bearing primitive of production agent runtimes. Around this primitive, we organize agent runtime design into three concerns: Coordination, State, and Control. We present a catalog of six runtime patterns that compose the SDB differently across conversational, autonomous, and long-horizon agents: hierarchical delegation, scatter-gather plus saga, event-driven sequencing, shared state machine, supervisor plus gate, and human in the loop. For each pattern, we trace its lineage to distributed-systems concepts and identify what changes when the worker is stochastic. The paper contributes a five-step methodology for selecting runtime patterns, a diagnostic procedure that maps production failures to pattern weaknesses, and a failure mode called replay divergence, in which LLM-based consumers of a deterministic event log produce different downstream outputs under model-version or prompt changes. A stylized reliability decomposition separates per-call model variance from architectural momentum, motivating the claim that as model variance decreases, pattern choice and SDB strength become increasingly important levers for long-run reliability. We apply the methodology to five workloads and provide one runnable reference implementation for a 90-day contract-renewal agent.

Vasundra Srinivasan

AI Architect, Independent Researcher · Stanford School of Engineering

LLM Agent Orchestration LLM Agents Long-Horizon LLM Agents LLM Agent Reliability

May 19, 2026cs.MA

STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision

Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, memory fragmentation, and imbalanced reasoning-tool trade-offs. In this paper, we introduce STAR-PólyaMath, a multi-agent framework that systematically addresses these challenges through meta-level supervision and structured Reasoner-Verifier interaction. STAR-PólyaMath is structured as an orchestrated state machine with nested challenge-step-replan loops, governed by a reasoning-free Python orchestrator that separates control from inference and bounds error propagation through trace-back and re-planning. Our key innovation is a persistent Meta-Strategist that maintains cross-attempt memory and exercises meta-level control by issuing high-level strategic guidance or mandatory directives, so the system can escape unproductive loops rather than stagnate or over-rely on tools. STAR-PólyaMath achieves state-of-the-art results on all eight top-tier competition benchmarks: AIME 2025-2026, MathArena Apex Shortlist, MathArena Apex 2025, Putnam 2025, IMO 2025, HMMT February 2026, and USAMO 2026. It obtains perfect scores on AIMEs, Putnam, and HMMT, and shows its largest margin on Apex 2025, scoring 93.75% compared with 80.21% by the strongest baseline GPT-5.5. Ablation studies show that the gains arise from the framework's orchestration rather than from model-level diversity since removing key components or substituting in mixed backbones consistently weakens performance. Code is available at https://github.com/Julius-Woo/STAR-PolyaMath.

Jiaao Wu, Xian Zhang, Hanzhang Liu +3

1Tsinghua University · 2Microsoft Research · 3New York University +1

Multi-Agent Orchestration Multi-Agent Reasoning Long-Horizon LLM Agents LLM Mathematical Reasoning Memory-Augmented Language Model Agents

May 18, 2026cs.CL

Code as Agent Harness

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.

Xuying Ning, Katherine Tieu, Dongqi Fu +39

LLM Agent Orchestration Long-Horizon LLM Agents LLM Agent Harnesses LLM Agent Reliability

May 18, 2026cs.AI

Latent Action Reparameterization for Efficient Agent Inference

Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through system-level optimizations or prompt engineering, we argue that a key bottleneck lies in the representation of the action space itself. We propose Latent Action Reparameterization (LAR), a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior. By reparameterizing agent actions into latent units, LAR enables decision making over a shorter effective horizon while preserving the expressiveness of the original action space. Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model, allowing both planning and execution to operate over abstract action representations. Across a range of LLM-based agent benchmarks, LAR significantly reduces the effective action horizon and improves inference efficiency under fixed compute budgets. As a consequence, our approach achieves substantial reductions in action tokens and corresponding wall-clock inference time, while maintaining or improving task success rates. These results suggest that action representation learning is a critical and underexplored factor in scaling efficient LLM agent inference, complementary to advances in model architecture and hardware.

Wenhao Huang, Qingwen Zeng, Qiyue Chen +11

Université de Montréal · Mila - Quebec AI Institute · The University of Sydney +7

LLM Inference Efficiency Latent Action Learning Long-Horizon LLM Agents

May 18, 2026cs.LG

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected. Recent methods alleviate this issue by generating rewards or textual hints from turn-level action-output signals, or by using feedback-conditioned self-distillation. However, generating feedback at every turn is inefficient when many intermediate turns are already successful or neutral, and applying feedback at a fixed or misaligned turn often fails to supervise the actions that contributed to the failure. To bridge this gap, we propose HINT-SD, a targeted self-distillation framework that uses full-trajectory hindsight to select failure-relevant actions and applies feedback-conditioned distillation only on targeted action spans. Experiments on BFCL v3 and AppWorld show that our method improves over the dense per-turn feedback baseline by up to 18.80 percent while achieving 2.26

\times

lower time per training step, suggesting that selecting where to distill is a key factor for both effective and efficient long-horizon agent training.

Woongyeng Yeo, Yumin Choi, Taekyung Ki +1

KAIST

Credit Assignment in RL LLM Agent Training Long-Horizon LLM Agents Knowledge Distillation

May 18, 2026cs.AI

Harnessing LLM Agents with Skill Programs

Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.

Hongjun Liu, Yifei Ming, Shafiq Joty +1

New York University · Salesforce AI Research

LLM Agent Self-Improvement LLM Agent Skill Learning Long-Horizon LLM Agents LLM Agent Harnesses

May 17, 2026cs.AI

Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents

Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad history inclusion, treating retrieved memories as uniformly useful. This assumption is fragile because memories may be topically related while remaining irrelevant, stale, or misleading. We propose Causal Memory Intervention (CMI), a causal memory-selection technique that estimates how candidate memories affect the model's answer under controlled interventions, selecting memories that improve task performance while suppressing unstable, irrelevant, or harmful ones. To evaluate this setting, we introduce Causal-LoCoMo, a causally annotated benchmark derived from long conversational data, where each example contains a user request, a structured memory bank, useful memories, irrelevant distractors, and synthetic harmful memories. We compare CMI against vector, graph, reflection, summary, full-history, and no-memory baselines. Results show that CMI achieves a stronger balance between answer quality and robustness to misleading memory, suggesting that reliable long-term memory requires selecting context based on causal usefulness rather than relevance alone. The full framework, benchmark construction code, and experimental pipeline are available at https://github.com/Saksham4796/causal-memory-intervention.

Saksham Sahai Srivastava

School of Computing, University of Georgia, Athens, Georgia, USA.

Conversational Memory Long-Term Conversational Memory Causal Interventions in Language Models Long-Horizon LLM Agents