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

Oct 8, 2026cs.AI

Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents

The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical memory and continual learning architecture. Hippocam draws inspiration from two characteristics of human memory: cognitive processes selectively maintain information relevant to current goals, while long-term memories form gradually through repeated consolidation. Accordingly, Hippocam structures an agent's ongoing work as nested intents. The active context remains centered on the current intent, while completed intents are consolidated into the task-relevant outcomes and state needed for subsequent work, rather than carrying forward their full working details. Concurrently, a recursive prefix consolidation mechanism repeatedly consolidates earlier history, causing long-unused experiences to become increasingly abstract. Original interactions are preserved, allowing the agent to progressively recover finer-grained details through the hierarchy and stop once sufficient information is available. Crucially, when past experiences are recalled and reintegrated into active work, they undergo subsequent consolidation alongside new experiences, thereby being reinforced, supplemented, and updated. Through this memory dynamic of use and disuse, Hippocam connects working context, long-term memory, knowledge accumulation, and skill learning within a single continuously evolving experiential process. This enables agents to learn and evolve capabilities through their own experiences without parameter updates.

Xiangyi Zeng, Baihang Liu, Xutong Wang +3

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China

Memory-Augmented Language Model Agents Continual Learning for LLM Agents LLM Agent Skill Learning Long-Horizon LLM Agents Memory Consolidation

Oct 8, 2026cs.AI

Harness Evolution Hits a Ceiling: When Weight Training Should Begin

Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the system stronger first, then cross seed and evolved harnesses with base and trained weights to learn which gains the trained model keeps and which still need the runtime. We show that the right lever can be read off the agent's failure composition: labelling failed trajectories by the first signal that fires separates process failures (blocked calls, loops, exhausted step budgets) from content failures (a delivered plan that is poor). Harness evolution repairs the former, the behaviour it instils can be trained into the weights, and content failures are what weight training is for. On DeepPlanning, a self-evolving harness loop lifts the held-out score of Qwen3.5-4B from 0.16 to 0.30 and of Qwen3.5-9B from 0.32 to 0.44; for 4B, held-out delivery rises from 55% to 90% while content failures are left for the weights. LoRA adapters trained on evolved-harness trajectories internalise the gain: under the original harness they add +0.13 on held-out tasks for both sizes; on 4B they stack with the harness to more than double the held-out score, and on 9B the adapter alone matches the full evolution line, cutting content failures from a quarter of trajectories to one in twenty. A placebo adapter trained on answer-shuffled trajectories falls below the base model. The loop transfers to WebArena-Lite (+0.09 on 117 unseen tasks), where the gain lives in what the model sees and adapters do not add to it. The result is a diagnose-then-intervene rule applied twice: read the failure composition to choose between harness and weights, then read what the accepted edits changed to decide which gains to train in. Scores are four-rollout means against fresh anchors, same-night except where marked, across eight models from six families and two benchmarks.

Yuan Tian, Bing Hu, Hao Wang +2

Independent Researcher · University of California, Berkeley · Purdue University +1

Long-Horizon LLM Agents LLM Agent Harnesses Agent Harness Optimization LLM Post-Training

Oct 8, 2026cs.CL

SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction

Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and interaction length. Code assistants require completing long chains of development work in continuously evolving repositories, while repeatedly clarifying requirements and adapting implementations through multi-turn interaction. To address these gaps, we introduce SWE-Journey, a benchmark for more realistic evaluation of coding assistants. To address the task-horizon gap, we propose a weak-to-strong synthesis pipeline that automatically constructs long-horizon coding tasks. To address the interaction gap, we mine four representative user personas from real interaction data and build a user-simulation agent to reproduce realistic code-assistance interactions. On average, models pass over 75% of tests for requested functionality with software architects, but fewer than 25% with non-coders. These results show that current coding assistants still fall short of enabling reliable coding for non-coders. We further analyze the reasons for this gap and identify asking right, finding right, and fixing right as key capabilities during interaction.

Hexuan Deng, Yue Wang, Wenyu Jiang +13

Tencent Hy AI Data · Beijing Zhongguancun Academy

Coding Agents AI Agent Benchmarks Software Engineering Benchmarks Long-Horizon LLM Agents

Oct 8, 2026cs.AI

Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds

Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking across multiple records. To address these challenges, we introduce E-Ledger, a multi-agent harness for safe and persistent execution. E-Ledger employs a code approval layer that checks every proposed action against policy before execution, and maintains a world ledger of verified hidden rules alongside evidence-backed dynamic state. Because hidden rules are typically unknown a priori, we further propose WorldAbduct, an abductive, world-model-driven harness evolution framework. WorldAbduct diagnoses execution trajectories across four complementary views (state consistency, world-observation gap, policy-gate correctness, and goal judgment) to hypothesize latent rules, and verifies them through targeted abductive interactions before integrating them into the ledger. On the enterprise benchmark World of Workflows, E-Ledger with WorldAbduct improves safe task completion across four LLM backbones, outperforming the strongest evolution baseline by 5--15 percentage points. Experiments in ScienceWorld and DiscoveryWorld further show that abductive harness evolution carries over to scientific environments. Our code is available at https://github.com/HKUST-KnowComp/E-LEDGER-WorldAbduct.

Yisen Gao, Yue Guo, Qing Zong +2

The Hong Kong University of Science and Technology · LIGHTSPEED · Independent Researcher

LLM Agent Harnesses LLM Agent Safety Runtime Enforcement for AI Agents Long-Horizon LLM Agents LLM Reasoning

Oct 7, 2026cs.AI

StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents

Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain static: the world moves only when the agent acts, the reward is a terminal verdict, and the pass bar is set arbitrarily. We introduce StoreBench, a live-commerce environment in which an agent runs a mid-size online apparel store on a production-grade commerce backend, testing long-horizon planning and economic judgment under uncertainty. Customers order around the clock, suppliers reprice and fail, and market shocks arrive with partial or no warning. The agent acts through the same 29 merchant tools a human operator would use, under a windowed operation budget that makes simulated time a function of actions taken, so model latency cannot influence simulated time. Pass thresholds are calibrated against scripted anchor policies, the reward is hardened against a catalogue of reward hacks, and every episode replays identically given a sequence of actions. We evaluate seven frontier LLMs on 11 scenarios of 30 to 45 days and a full simulated year, over three world seeds at matched reasoning effort. No model matches the scripted smart-triage policy on average: the best, DeepSeek-V4-Pro, passes 49% of task-seed cells against the heuristic's 97%. Human experts working through the same tools and budgets outscore every model (mean composite 0.708 vs. 0.700). Over a full simulated year under the Claude Code harness, most models show dramatic performance improvement. In a GRPO post-training run, Qwen3.5-27B trained on only five disjoint tasks raises its mean composite on the held-out evaluation tasks from 0.136 to 0.373. We release five example training-split tasks, ten sample trajectories, and the scoring and verification tooling; the full environment and evaluation suite are withheld to keep the benchmark uncontaminated.

Daksh Raghuvanshi, Ved Vedere, Yifan Wang

AfterQuery

AI Agent Benchmarks Long-Horizon LLM Agents LLM Agent Training RL for LLM Agents

Oct 7, 2026cs.AI

Plan-and-Patch: Diffusion Language Models for Agentic Planning

Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps. Yet assumptions made during planning may be invalidated by the environment, tools may return unexpected results, or actions may fail. Effective agents must therefore not only generate plans, but also revise them. Such revisions often affect only part of a plan, leaving the preceding and subsequent structure intact. Rather than regenerate the entire plan and risk unnecessary changes, repair can regenerate the affected region conditioned on the preserved prefix and suffix. We introduce Plan-and-Patch, a plan-and-act framework in which a diffusion language model (dLLM) generates a structured, program-like plan through parallel unmasking and repairs it by filling in selected regions while keeping the surrounding steps fixed. We compare DreamReasoner-8B and Qwen3-8B as diffusion and autoregressive (AR) planners. On Natural Plan without task-specific training, diffusion (53.7%) achieves nearly twice the plan repair success rate of AR (27.0%). After task-specific training on agentic benchmarks, ALFWorld and TextCraft, the planners achieve similar observed success in plan generation, while diffusion reduces mean plan-generation latency by 39-46% relative to AR. Our results show that Plan-and-Patch provides a framework for faster plan generation and effective plan repair in long-horizon agents.

Syamantak Kumar, Jiang Guo, Hassan Hamad +6

University of Texas at Austin · Amazon

LLM Planning Diffusion-Based Planning Long-Horizon LLM Agents Diffusion Language Models

Oct 7, 2026cs.AI

Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents

Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefinitely. However, existing memory mechanisms mainly retrieve, summarize, or compress past content and do not directly learn when particular kinds of thinking should be activated or discover new thinking knowledge from temporally dispersed experiences. This paper proposes a situation-conditioned thinking memory framework that transforms historical reasoning experience into a lightweight policy for predicting what should be thought about in the current situation, while leaving detailed reasoning to a large language model. Situations may represent temporal or spatiotemporal evolution rather than only current states. Temporary experiences are also periodically analyzed across multiple independent episodes to identify repeated long-range regularities, which are consolidated into new thinking knowledge and further internalized by the lightweight policy. Experiments show that the learned policy achieves 1.000 F1 on temporal-rule generalization, improves DeepSeek reasoning F1 from 0.789 to 0.868, reduces online processing time from 0.3636 ms to 0.0382 ms per query at 30,000 historical situations, and reaches 1.000 relation-discovery F1 and future-thinking accuracy after sufficient repeated cross-experience evidence.

Hong Su

School of Computer Science, Chengdu University of Information Technology, Chengdu, China

LLM Agent Memory Long-Horizon LLM Agents Policy Learning Continual Learning for LLM Agents Temporal Reasoning in Language Models

Oct 7, 2026cs.AI

World Potential Model: Pretrained World Knowledge as Progress Potentials

Long-horizon language agents often receive supervision only from terminal task outcomes, leaving little signal for distinguishing productive intermediate behavior from stagnation or even regression. Rather than learning a separate value function or process reward model for every task, we ask whether pretrained models can recognize task progress from their existing world knowledge. We formalize this capability with a World Potential Model (WPM), a goal-conditioned evaluator of task-relative realized progress in agent contexts. In ALFWorld and ScienceWorld, off-the-shelf pretrained models substantially outperform chance at recovering realized-progress structure without task-specific evaluator fine-tuning. We further anchor these progress judgments to task-specific milestones to obtain scalar world potentials, whose temporal differences provide process-sensitive step-level credit for policy optimization. Under matched comparisons, WPM-guided optimization improves success over outcome-only GRPO across all evaluated configurations. Together, these results provide initial evidence that pretrained world knowledge can support reusable realized-progress evaluation and provide useful supervision for long-horizon agents.

Jun Zhao, Jixin Tang, Yang Shu +6

National University of Singapore · Fudan University · Tsinghua University +1

Long-Horizon LLM Agents RL for LLM Agents Process Reward Models

Oct 6, 2026cs.CL

ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents

Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessions exceed the context window. Existing methods manage the context through context requirement prediction, relying on additional model calls, heuristic rules, or trained policies. However, these predictive approaches introduce runtime overhead, invalidate prefix caches, and permanently discard content with no guarantee of recovery. To overcome these limitations, we introduce ReFold: a training-free rendering layer that preserves the underlying interaction history while compressing only the model's rendered context. It removes two kinds of inter-turn redundancy without an auxiliary predictor: content an earlier turn already displayed, replaced by a stub, and turns the agent itself reports finished, folded into a one-line note. Both operators use chunked rendering, rewriting the cached prefix once every few steps rather than at every step. Every removal is strictly reversible, a wrong removal costs one restore from the history rather than permanent content loss. Because it operates at the rendering layer, ReFold is plug-and-play across standard ReAct-style harnesses. Evaluations across five long-horizon benchmarks and two frontier LLMs demonstrate that ReFold reduces token consumption by up to 2.5x and halves the KV-cache memory per session without degrading task success rates. Under capped context budgets, it avoids up to 92% of forced compactions. Under concurrent serving workloads, it reduces request queuing delays by up to 100%, accelerating inference by up to 1.7x, while cutting inference costs by up to 3.4x.

Yupeng Su, Jiayi Tian, Zheng Zhang +1

University of California, Santa Barbara · Intel

LLM Inference Efficiency Long-Context Language Model Inference Long-Horizon LLM Agents LLM Context Management Context Compression

Oct 6, 2026cs.SE

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift. Large repositories further complicate the identification of task-relevant components. To address these challenges, we introduce \textbf{Dev-Primitives} (\emph{Development Primitives}), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering. Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication, and localized self-modification. Building on Dev-Primitives, we propose \textbf{HERMES}, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised. Extensive experiments on four software engineering benchmarks demonstrate that HERMES outperforms matched baseline harnesses by 12.4% on average. Moreover, when paired with strong activation and diagnosis models, HERMES, even with Qwen3-8B Dev-Primitives, remains within 4.5% of the homogeneous GPT-5.6 Sol configuration across all four benchmarks, while reducing inference cost by 26.2% on Terminal-Bench 4.0, highlighting the importance of harness design in software engineering agents.

Haibo Jin, Xinjie Li, Peng Kuang +1

University of Illinois Urbana-Champaign, USA · The Pennsylvania State University, USA

Multi-Agent LLM Systems Software Engineering Agents Automated Software Engineering Long-Horizon LLM Agents LLM Agent Harnesses

Oct 5, 2026cs.LG

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

Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous agents interacting with complex environments, early mistakes can propagate through trajectories and cause cascading failures. Recent approaches improve reliability by incorporating external critique or deliberation, but invoking these mechanisms at every step substantially increases token consumption and latency, limiting practical deployment. We propose SAG (Self-improving Agent with Gated critique), a cost-aware framework that formulates critique invocation as a step-wise decision problem during long-horizon interaction. SAG introduces a lightweight, training-free gating mechanism that estimates the utility of critique using action-level ambiguity signals--global entropy and local top-2 margin--computed over admissible actions. From a decision-theoretic perspective, this mechanism approximates the Value of Information (VoI) of critique, enabling the agent to selectively allocate expensive feedback only when its expected benefit justifies the cost. SAG further incorporates online bootstrapped self-improvement, allowing the actor to internalize critic-assisted behaviors and progressively reduce reliance on critique. Across three long-horizon interactive benchmarks and multiple backbone models, SAG substantially improves the performance-cost trade-off compared with both no-critique and always-on critique agents. On ALFWorld, SAG increases task success from 24.6% to 78.4% while maintaining a token budget comparable to ReAct, yielding a

3.1\times

improvement in normalized token efficiency. Moreover, a 7B actor with a lightweight 3B critic achieves performance comparable to a 14B actor without critique, showing that selective critique can recover most of the reliability benefits of deliberation while dramatically reducing inference cost.

Heewon Park, Somin Im, Minhae Kwon

Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea. · Soongsil University, Republic of Korea.

Long-Horizon LLM Agents LLM Agent Reliability

Oct 5, 2026cs.AI

AMBER: Training Long-Horizon Web Agents through Append-Only Memory

Modern language-model agents increasingly interact with external environments over long-horizon, multi-step trajectories, where the accumulated interaction history can quickly exceed practical context budgets. To ensure reliability, agents must maintain factual information over long horizons, remember execution errors and corrective feedback, and track progress across actions. Several approaches have been proposed to achieve this without the need for maintaining the entire execution history in context, such as using the reasoning and action history, learning to maintain a fixed-size memory through an overwrite mechanism, and periodic summarization. Although overwrite memory can in principle retain anything an append-only memory can, it must learn to carry each fact through every subsequent rewrite, which is difficult to learn from sparse outcome rewards; for interactive applications like web agents, we find that trained overwrite memories delete key information required by the trajectory, as well as corrective feedback received from the environment. We introduce AMBER (Append-only Memory Bank for Evidence Retention) - a simple and scalable framework where an agent jointly learns to reason, act, and write free-form memory, while an append-only rule guarantees retention by construction. This allows AMBER to be trained end-to-end with reinforcement learning from outcome rewards without the need for extensive curated SFT data. On WebArena Lite, AMBER improves average success over overwrite-based memory by 4.09 percentage points, increases the fraction of tasks solved in five repeated runs by 4.8 percentage points, and matches an overwrite baseline trained on substantially more expensive curated supervision. AMBER achieves these improvements while maintaining a practical token budget, providing a strong balance between context efficiency, task performance, and reliable long-horizon execution.

Chinmay Savadikar, Zhaoyu Zhang, Mingyu Zhao +4

North Carolina State University · Shopify

Long-Horizon LLM Agents Agent Memory Management RL for LLM Agents Web Agents

Oct 5, 2026cs.AI

RocketAgent: A Long-Horizon Engineering Agent for Multidisciplinary Design of Liquid-Rocket Thrust Chambers

Liquid-rocket thrust-chamber design involves interdependent analyses in which downstream constraints can require earlier design decisions to be revisited. Managing these dependencies across heterogeneous tools requires consistent design information and coordinated updates throughout the workflow. We present RocketAgent, a long-horizon engineering agent for multidisciplinary preliminary design of liquid-rocket thrust chambers. A single plan-owning Coding Agent coordinates engineering skills for performance sizing, subsystem optimization, geometry generation, and multiphysics assessment. A provenance-aware knowledge graph supports method selection, while a typed Design Intermediate Representation maintains shared parameters, artifacts, and decisions. Revision-aware checks invalidate affected results and block superseded inputs, with consequential changes subject to engineering approval. In a representative simulation-based design, RocketAgent continued from an infeasible cooling search through an engineer-authorized operating-point revision, identified feasible subsystem designs, and coordinated subsequent geometry generation and multiphysics assessment to support final configuration selection. Separate module tests assessed surrogate predictions and nozzle adaptation. A two-configuration comparison across three controlled scenarios verified the expected dependency invalidations and superseded-input blocking before solver execution. The representative case demonstrates sustained coordination across a multidisciplinary design workflow, while the controlled tests establish the behavior of the revision mechanisms supporting that execution.

Junxiang He, Runze Mao, Kun He +4

State Key Laboratory of Turbulence and Complex Systems, School of Mechanics and Engineering Science, Peking University, Beijing, 100871, China · College of Engineering, Peking University, Beijing, 100871, China · Legendspace Intelligence Technology Co., Ltd., Beijing, 100080, China +1

Model-Based Systems Engineering LLM Agent Orchestration Long-Horizon LLM Agents

Oct 5, 2026cs.AI

VERA: Scaling Verifiable Environments for Agentic co-Evolution

Competent agents need precise and verifiable environments, such as sandboxes that are resumable at any stage and evolve from observable evidence. However, most long-horizon work exposes how rare these are: for example, an agent in medical research must ground a finding, classify it, and write a report over dozens of dependent steps, yet recent environments score only the outcome. To address the challenges in stable training, we present VERA, which builds such environments at scale and lets agents evolve on them. VERA builds these environments from initial trajectories: an agent writes rubrics, executable checks, a judge verifies each sandbox, and only those that pass enter the training bank. On these environments, VERA alternates between two updates: train the model with rubric rewards, or edit the harness skills. We also create a verifier which gates model checkpoints and harness edits using explicit development-set acceptance criteria. This attribution distinguishes VERA's co-evolution from single-axis baselines: its updates target not only the cause but the outcome. With an open-source corpus of 9,000+ long-horizon verifiable environments, a 9B model paired with its co-evolved agent beats the strongest baseline by 10.3 and 13.0 points in the two domains. At 27B, it surpasses the baseline on AutoCoWorkBench (71.6) and AutoMedBench (80.7), transfers to unseen workflows, and retains general capabilities.

Junqi Liu, Yongyang Pan, Zhuosong Jiang +14

University of California, Santa Cruz · University of Illinois Urbana-Champaign · National University of Singapore +4

Reinforcement Learning with Verifiable Rewards Long-Horizon LLM Agents Self-Evolving Agents

Oct 5, 2026cs.LG

Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training

Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the \emph{supervision horizon}, the number of trajectory tokens retained for training, and show that it is a key design axis for reliability and cost. Reliability improves with longer horizons but saturates: on Terminal-Bench, a 12K-token horizon solves more tasks than 16K (

29\pm0.7

vs.\

26\pm0.8

) while requiring 30% less training time. The horizon also shapes agent behavior: short horizons cause premature termination, intermediate horizons yield productive error recovery, and long horizons induce over-persistence. We analyze this saturation through a bias--complexity bound, in which longer supervision reduces temporal supervision bias but increases finite-sample estimation error from more heterogeneous late-stage histories. Guided by this analysis, we propose \emph{selective long-horizon refinement}, which first trains on short prefixes and then refines only on continuations that are most likely under the warm-start model. It consistently outperforms full long-horizon training. At 16K, it raises successful attempts from

110\pm2.7

to

126\pm2.1

and tasks solved in at least six of eight attempts from

9\pm0.7

to

14\pm0.6

; with half of the long-horizon data, it still reaches

122\pm2.4

while cutting training time by 23%. The gains transfer across benchmarks, from

64\pm2.6

to

73\pm2.1

on Terminal-Bench v2.0 and from

137\pm2.7

to

155\pm2.2

on OpenThoughts-TBLite. For long-horizon supervision, selecting the right trajectories matters more than training on all of them.

Cuong Dang, Hoang Anh Just, Ruoxi Jia

Department of Electrical and Computer Engineering Virginia Tech Blacksburg, VA, USA

Supervised Fine-Tuning Trajectory Generation LLM Agent Training Long-Horizon Agent Tasks Long-Horizon LLM Agents

Oct 4, 2026cs.AI

Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks

Small language models (SLMs) offer a promising foundation for on-device agents through low-latency, resource-efficient inference, yet limited reasoning and planning capabilities constrain their performance on long-horizon tasks requiring multi-step interaction with the environment. Step-level collaboration between SLMs and larger cloud-hosted models can bridge this gap, but identifying states that warrant cloud assistance remains challenging: the contribution of each cloud call is entangled with subsequent actions and can be assessed only from the final task outcome. Compounding this challenge, the SLM must balance two competing objectives: maximizing task success and minimizing cloud calls. To address this, we propose Sibyl, an algorithm that trains SLM agents to selectively consult cloud models at the step level and internalize their guidance for subsequent decisions, achieving strong task performance with minimal cloud reliance. Sibyl follows a three-stage training pipeline that (1) builds a robust base policy through consultation-free self-evolving reinforcement learning (RL); (2) cold-starts consultation behavior via decisive-disagreement state mining; and (3) jointly optimizes consultation decisions and guidance internalization through consultation-aware RL. Experiments on ALFWorld and WebShop demonstrate that Sibyl, using only a 0.6B-parameter model, outperforms state-of-the-art baselines, including agent training and routing methods, by 95.2% and 80.4% in success rate while averaging only 0.8 and 3.9 cloud calls per trajectory, respectively.

Zhewei Fang, Yuxin Zhang, Zhenwei Shao +8

Hangzhou Dianzi University · Fudan University · The Hong Kong University of Science and Technology +3

LLM Agent Training Long-Horizon LLM Agents Multi-LLM Collaboration RL for LLM Agents

Oct 4, 2026cs.LG

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

A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed agents face streams of related tasks, making their trajectories a natural resource for improvement. In-context adaptation agents store reflections, memories, or skills as text, so reuse depends on retrieving the right experience and on a frozen policy executing it. We study Online Agentic Test-Time Training (OaTTT), which trains the LLM's weights on its own execution trajectories during deployment. The agent executes each task once, in one pass over the stream, and the executed trajectory with its verification result is the only learning signal for weight updates that persist across tasks. Directly imitating or reinforcing the generated tokens of this single attempt destabilizes the policy. We introduce ASCENT (Agentic Self-distillation for Cross-task EvolutioN at Test-time), which instead self-distills verified experience. A stable version of the LLM, its frozen initial copy, receives the verified trajectory as privileged information and predicts next-token distributions along it with this hindsight. Distilling them into persistent LoRA fast weights updates the agent for later tasks, without an external reference solution or stronger teacher. By further removing invalid-action turns, ASCENT distills enhanced privileged experience for more efficient execution. We characterize its population target and the limits of sparse outcome selection. Across ALFWorld, WebShop, and AppWorld at varied model scales, ASCENT improves task success and interaction efficiency as experience accumulates, outperforms online adaptation methods, and transfers to held-out scenes, showing that an agent can consolidate verified experience into its weights without a separate training phase or memory retrieval. Project page: https://artificer-ai-lab.github.io/ASCENT

Haodong Lu, Dong Gong

University of New South Wales (UNSW Sydney)

Continual Learning for LLM Agents Test-Time Training LLM Agent Training Self-Distillation Long-Horizon LLM Agents

Oct 4, 2026cs.AI

LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search

Deep search agents tackle complex knowledge tasks through iterative retrieval, multi-hop reasoning, and evidence synthesis across multiple sources. Existing approaches typically assume relatively stable retrieval systems and operate over short-horizon tool interaction. However, when retrieval is sensitive to query formulation, even a semantically appropriate query may fail to surface critical evidence because of mismatched entity names, aliases, or keyword combinations. Recovering from such failures requires repeated query reformulation and longer interaction trajectories. This setting poses a distinct training challenge, as the policy must sustain long-horizon query exploration while managing an expanding volume of retrieved content. We propose LexiHorizon, a framework for training search agents over long horizons that expands the trajectory context budget, manages accumulated retrieval content using a window over recent tool observations while preserving the reasoning history, and introduces an outcome-gated search-effort reward that provides a bounded bonus for tool invocations to trajectories with nonzero answer reward. Experiments on XBench, WebWalkerQA, and BrowseComp-ZH show that the resulting 9B model consistently outperforms both its base model and MiroThinker-1.7-mini, with maximum absolute gains of 8.7 and 23.8 percentage points, respectively. These results suggest that combining an extended context budget with reasoning-preserving context management benefits long-horizon deep search agents.

Zhiqing Nong, Liang Wen, Chao-Hsuan Liu

Long-Horizon Agent Evaluation RL for IR Long-Horizon LLM Agents Memory-Augmented Language Model Agents

Oct 1, 2026cs.AI

Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control

Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively immediate feedback and reset failures. Long-running physical control operates in a different regime: actions alter future states, errors compound across decisions, and an agent must improve from experience without being allowed to rewrite the physical rules that make execution safe. We study this regime through irrigation, where daily decisions interact with soil-water dynamics over entire growing seasons. We present Mimir, a physics-grounded LLM agent organized around two repair timescales. At the fast timescale, a structured physical interface and deterministic simulator turn an LLM output into a proposal that we numerically check, revise, and subject to bounded deterministic action selection before execution. At the slow timescale, recurrent failure patterns are consolidated into persistent contextual principles that condition future proposals, while the physical model, evaluator, and execution constraints remain immutable. Under a common retrospective evaluator across multiple sites, crops, and years, Mimir attains the lowest reported aggregate control cost among the evaluated references and uses about 51% less irrigation than the historical schedule replay. The ablation study show higher control cost when forward simulation, verified revision, or persistent context is removed; model-scale and model-family studies show no monotonic gain from increasing LLM size. The resulting lesson show that persistent physical agents can combine semantic reasoning with bounded, evidence-driven self-improvement while reserving physical truth and actuator authority for explicit numerical mechanisms.

Yimeng Liu, Mi Zhang, Younsuk Dong +1

Michigan State University · Ohio State University

Language Model-Based Control LLM Agent Self-Improvement Long-Horizon LLM Agents Precision Agriculture Memory-Augmented Language Model Agents

Oct 1, 2026cs.AI

Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States

Large language model (LLM) agents can now undertake increasingly complex tasks, but the way they organize interaction history into memory does not ensure a coherent understanding of the current world. We introduce PoS, an inference-time framework that constructs and continually maintains explicit belief states as the agent's decision context. Each belief combines an estimate of the current world state with unresolved task requirements, making explicit what the agent still needs to learn and accomplish. To keep this belief reliable and actionable, PoS validates its consistency and monitors task progress to detect Belief Trapping, where the agent continues to act without making meaningful progress toward the goal. Recovery is then tailored to both the trapping pattern and the type of unresolved task requirement. Experiments on four benchmarks spanning execution and diagnosis show that PoS achieves the highest overall performance on every benchmark with all three LLM backbones. Ablations demonstrate the importance of consistency validation and recovery, while context-scaling experiments show resilience to context growth. Together, these results support belief construction and continual maintenance as a foundation for long-horizon context management beyond history retention and compression.

Yu Luo, Jiamin Jiang, Yimin Zuo +9

Nankai University · Alibaba Group · Tsinghua University

Belief Updating in LLMs Long-Horizon LLM Agents LLM Context Management

Oct 1, 2026cs.AI

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened with a fixed base model, without access to reference answers or grading rubrics at test time. Repeated sampling yields multiple rollouts that can contain complementary correct claims, but we need a reliable verification mechanism to determine which claims to trust. We first find that disagreement often exposes correct alternatives, while consensus can conceal errors. These observations motivate VeriHarness, which turns the underlying LLM a generator uses into an agentic verifier by giving it a workspace, evidence tools, and reusable verification skills. A disagreement resolver checks competing claims against environmental evidence, while a consensus challenger tests shared claims and searches for omitted requirements. Their findings guide the selection and revision of the final artifact. Across five long-horizon workspace benchmarks and two frontier models, VeriHarness achieves the highest selection scores among the evaluated baselines. Evidence-backed revision further improves average performance, bringing gains over a single rollout to 6.2 points with Gemini 3.5 Flash and 6.4 points with Claude Opus 4.8. We further show that verification skills can self-improve from failure feedback, demonstrating VeriHarness as a novel and critical approach for scaling long-horizon agentic verification. We release the full pool of approximately 26,000 rollouts across all five benchmarks and both models, produced at a cost of over $100,000, to support future research on agentic verification.

Caiqi Zhang, Rujun Han, Zifeng Wang +4

University of Cambridge · Google Cloud AI Research

LLM Agent Verification Long-Horizon LLM Agents LLM Agent Harnesses

Sep 30, 2026cs.LG

PhantomEnvironments: Training LLM Agents in Fictional Worlds

Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained into capable search agents using synthetic environments generated entirely by rules, whose generation requires no LLM and has zero marginal cost. We build PhantomEnvironments, multi-turn RL environments from fictional worlds, where agents must search a corpus of templated articles to answer multi-hop questions. Despite sharing no facts with the real world, these strikingly simple environments yield agents that transfer to real-world multi-hop search benchmarks, often outperforming real-world training data on newer benchmarks. Trained agents generalize to unseen fictional universes, and Qwen models learn to scale their search budget roughly linearly with question difficulty, suggesting emergent search scaling from environment interaction alone. Ablating environment complexity reveals that hop count drives transfer more than constraints or comparisons: even the simplest rule-generated environments are a surprisingly effective, free resource for training generalizable LLM agents.

Anmol Kabra, Swathi Saravana Selvam, Albert Gong +5

Cornell University · Stanford University

Multi-Hop QA Reinforcement Learning LLM Agent Training Long-Horizon LLM Agents RL for LLM Agents

Sep 30, 2026cs.AI

OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation

Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map observations to actions without separating persistent coordination strategies from their tactical execution. We introduce OverForge, a training-free hierarchical architecture that separates strategic reasoning over roles and divisions of labour from tactical reasoning over actions within each agent's private, partner-conditioned world model. A metacognitive Prefrontal Cortex Module couples the two levels by forming strategy-action branches, imagining their consequences with a forward model, and committing when confident. In OvercookedV2, OverForge delivers 7 soups in a connected kitchen versus 3 for each flat LLM baseline, retains agreed roles, and adopts roles proposed by unfamiliar partners. Ablations and a fixed-strategy probe show that persistent strategies guide tactical adaptation while each reasoning level contributes to coordination. Memory restarts show that cross-episode partner knowledge supports task performance and partner prediction, linking the hierarchy to continual adaptation.

Oana Madalina Fron, Ojas Shirekar, Chirag Raman

Tapri Lab, Department of Pattern Recognition and Bioinformatics, Delft University of Technology, Delft, The Netherlands

Continual Learning for LLM Agents Multi-Agent LLM Systems Multi-Agent Coordination Long-Horizon LLM Agents LLM Reasoning

Sep 30, 2026cs.LG

SparseEngine: Sparse-First Inference Engine

Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although sparse attention reduces these costs, heterogeneous cache representations and workflows hinder integration with existing inference engines, while prior sparse-serving abstractions support only specific layouts or workflows. We present SparseEngine, a ground-up, sparse-first inference engine whose shared lifecycle contract lets each method control its KV representation and computation while coordinating state transitions with common serving infrastructure. SparseEngine supports 15 methods across four categories and enables cross-request state management through Chain Cache, which resumes KV-eviction methods from retained history, and controllable Prefix-Cache Pruning, which removes KV from selected history regions while preserving logical-prefix matching. While maintaining method quality, SparseEngine delivers over 10x higher throughput with KV eviction, over 2.5x faster decoding at matched concurrency than vLLM, and over 2x end-to-end speedup on agent benchmarks. The code is available at https://github.com/CURRENTF/SparseEngine.

Jitai Hao, Quansheng Gu, Qiang Huang +1

LLM Inference Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Compression Long-Horizon LLM Agents

Sep 29, 2026cs.CL

Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent

Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume that users always accurately and sufficiently communicate a fixed intent. However, this oracle communication assumption rarely holds in practice: users may miscommunicate, change their goals, and run out of patience. We define this task setting as Interactive Intent Alignment, where agents must recover and continuously track the user's current intent despite imperfect communication and evolving goals. To study this setting, we introduce Drift-Bench++, a principled benchmark construction pipeline for verified executable tasks with controlled misalignment and intent shifts, along with an interaction protocol featuring finite patience, diverse simulated users, and silent interaction-conditioned shifts. We further develop GRIP, a comprehensive evaluation protocol covering task grounding, user realism, inquiry effectiveness, and adaptation to evolving intent. Across diverse environments, models, and interaction conditions, stronger interaction consistently helps but remains far from oracle performance; Validation on deployed ProdAgent sessions further shows that the modeled failures are prevalent and consequential in deployment. By providing a unified, executable benchmark for interactive intent alignment, Drift-Bench++ offers a foundation for evaluating and advancing agents under realistic communication and evolving intent.

Zheyuan Zhang, Mengyuan Chao, Ke Xiao +5

ByteDance Inc., USA · University of Notre Dame

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

Sep 29, 2026cs.AI

Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning

As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce agentic meta-reasoning, an inference-time harness that makes these choices an explicit and structured reasoning process. Workers carry out the task-level computation, while a controller consolidates what the run has established, explores next options, assesses what each option is worth under the remaining budget, and dispatches the chosen work with context drawn from persistent memory. Between decisions the controller carries only a compact account of the run rather than replaying its full history. Our baselines span production coding agents and research harnesses, together with a Direct Control Agent using the same workers and compute budget allowance. On ProgramBench, which tests long-horizon agentic capability through program reconstruction, meta-reasoning achieves 71.5% with GPT-5.5 against 58.0% for Codex; with Opus 4.8 it achieves 67.2% against 65.5% for Claude Code. On the other benchmarks, spanning abstract reasoning, multi-domain long-horizon reasoning, and proof generation, it gains between 3.6 and 4.2 points over direct control, averaged across three frontier models. It keeps improving over the tested budget ranges where direct control plateaus, though its overhead can hurt at small budgets. Artifact-graph analysis reveals more reuse of earlier work, higher coverage of correct solutions in most settings, and nonuniform gains in final selection. These results indicate that spending computation on structured control becomes more important as agents scale to longer runs.

Paras Dahal, Anton Bakhtin, Taco Cohen +9

Meta Superintelligence Labs

Agentic Reasoning Inference-Time Compute Allocation Long-Horizon LLM Agents LLM Agent Harnesses

Sep 29, 2026cs.AI

Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution

Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successful planning requires two distinct capabilities: selecting an appropriate plan for the task and executing it faithfully. Existing planner--executor systems can fail at either stage, while final task success alone cannot distinguish selection from execution failures. We therefore study the Plan Declaration--Execution Gap and introduce Planning-as-Routing, where an LLM declares one of four planning modes: Predefined, Sequential, Hierarchical, or Search, and a deterministic router dispatches the task to the corresponding pattern-specific executor. Across four benchmarks and three LLMs, we find three consistent patterns. First, generic Plan+ReAct often fails to preserve declared planning structure, especially for longer plans: across three benchmarks, only (22)--(45%) of trajectories preserve it, whereas pattern-specific executors enforce the intended structure. Second, planning-mode effectiveness varies across environments and models: Search performs best on ALFWorld, Hierarchical on SWE-bench, and the strongest pattern can vary across models within the same benchmark. Third, the largest gains come from execution: pattern-specific executors improve task success from (0.48) to (0.92) on ALFWorld and from (0.36) to (0.44) on SWE-bench Verified over Plan+ReAct. Current LLMs, however, do not reliably select the strongest mode for each task, although few-shot examples improve selection in some benchmark--model combinations. Overall, reliable agent planning requires both effective mode selection and faithful execution: routing substantially closes the execution gap, while task-specific mode selection remains open.

Subba Reddy Oota, Francisco Herrera, Jordi Cabot Sagrera +2

ADIA Lab, Abu Dhabi, United Arab Emirates · University of Granada, Granada, Spain · Luxembourg Institute of Science and Technology, Luxembourg +2

LLM Agents Long-Horizon LLM Agents LLM Agent Planning LLM Agent Routing

Sep 29, 2026cs.AI

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

We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rests on two complementary capabilities: reflection, which produces a solution better than the current one, and long-horizon execution, which keeps the iteration effective over many rounds. We hypothesize that both capabilities are domain-agnostic, and can therefore be learned in scenarios that are well suited for supervision. Accordingly, we synthesize long-horizon improvement trajectories from machine learning and algorithmic programming tasks, two domains that offer verifiable feedback and reward sustained iteration. Trained on this data, our agent, built on Qwen3.8-27B, achieves strong results on MLE-bench Lite (81.8) and Frontier-CS (70.7), transfers to deep research with 84.0 on BrowseComp, 52.6 on HLE, 92.2 on GAIA, and 93.8 on DeepSearchQA, and keeps improving as its budget of rounds grows. These results show that long-horizon reflective data is an effective route toward self-improving agents.

Hongjin Qian, Chaofan Li, Kun Luo +11

Beijing Academy of Artificial Intelligence (BAAI)

LLM Self-Refinement LLM Agent Training Self-Improving Agents Long-Horizon LLM Agents

Sep 29, 2026cs.AI

ContextRender: From Execution Dependencies to Agent Context

LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even when it fits within the context window, while reducing it risks omitting needed information. Existing context management methods can overlook how earlier tool results are used in subsequent execution, leaving needed information out of context. We introduce ContextRender, which manages context through a persistent graph of execution dependencies. We develop Tool-Flow Analysis to track how later operations reuse information from earlier tool results, providing a signal called observed reuse. A renderer combines this signal with recency and semantic relevance to select results within a fixed history budget, retaining omitted results for later use. Across AppWorld and 8-objective QA with three execution models, ContextRender outperforms the evaluated context management baselines using a 6K history budget, well below the models' maximum context windows. Within this budget, it achieves task performance close to or above that of passing the full history while reducing mean inference cost by 10.2%-32.2% relative to Full history. Ablations show that observed reuse improves task performance and retention of results reused later.

Savini Kashmira, Jayanaka L. Dantanarayana, Lingjia Tang +1

University of Michigan, Ann Arbor, USA

Graph-Based Agent Memory Long-Horizon LLM Agents LLM Context Management Agent Memory Management

Sep 29, 2026cs.AI

FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents

LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilution. Existing context-compression methods learn what to discard offline: by contrastively optimizing guidelines, distilling compressors, or training compression policies. This incurs a substantial cost. Further, the compression policy is learned a priori and is not dynamically conditioned on the evolving test-time trajectories. In this paper we ask a complementary question: Which past interactions causally shape the agent's future decisions? We recast context compression as a causal decision preservation problem over discrete interaction units and introduce FOCUS, a training-free context compression framework that operates entirely at test time. Our method requires no offline data collection or fine-tuning, and is architecture-agnostic, attaching to any closed-API frontier model as a modular compression layer. We evaluate FOCUS on diverse agentic benchmarks including API and tool-calling, QA, web domain and multi-turn dialogue. Our method establishes new state of the art performance, cutting peak context by up to 48% and dependency by 73% while improving task success by up to 8.9 percentage points over uncompressed execution.

Shantanu Dixit, Anson Bastos, Xuchao Zhang +2

M365 Research, Microsoft

Long-Horizon LLM Agents LLM Context Management Context Compression