Long-Horizon Agents

Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process components independently, causing redundant retrieval and conflicting descriptions across documents while producing outputs that lack hierarchical structure. Therefore, we propose MemDocAgent, a long-horizon agentic framework that generates documentation within a single, integrated context spanning the entire repository. It combines two components: (i) Dependency-Aware Traversal Guiding that predetermines a traversal order respecting dependency and granularity hierarchies; (ii) Memory-Guided Agentic Interaction, in which the agent interacts with RepoMemory, a shared memory accumulating prior work traces through read, write, and verify operations. Through an in-depth multi-criteria evaluation, MemDocAgent achieves the best performance over both open and closed-source baselines and demonstrates practical applicability in real software development workflows.

Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We introduce ASH, an agentic system that learns an embodied policy from unlabeled, noisy internet video, without reward shaping or expert annotation. ASH follows a self-improvement loop; when it gets stuck, ASH learns an Inverse Dynamics Model (IDM) from its own trajectories, and uses its IDM to extract supervision from relevant internet video. ASH uses unsupervised learning to identify key moments from large-scale internet video and retains them as long-term memory -- allowing it to tackle long-horizon problems. We evaluate ASH on two complementary environments demanding multi-hour planning: Pokemon Emerald, a turn-based RPG, and The Legend of Zelda: The Minish Cap, a real-time action-adventure game. In both games, behavioral cloning, retrieval-augmented and zero-shot foundation-model baselines plateau, while ASH sustains progression across our 8-hour evaluation. ASH reaches an average of $11.2/12$ milestones in Pokemon Emerald and $9.9/12$ in Legend of Zelda, while the strongest baseline gets stuck in both environments at an average of $6.5/12$ and $6.0/12$ milestones, respectively. We demonstrate that self-improving agents are a scalable recipe for long-horizon embodied learning.

Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burden of extended closed-loop planning and diverse physical operations. We therefore propose VLAs-as-Tools, a strategy that distributes this burden across a high-level vision language model (VLM) agent for temporal reasoning and a family of specialized VLA tools for diverse local physical operations. The VLM handles scene analysis, global planning, and recovery, while each VLA tool executes a bounded subtask. To tightly couple agent planning with VLA tool execution in long-horizon tasks, we introduce a VLA tool-family interface that exposes explicit tool selection and in-execution progress feedback, enabling efficient event-triggered agent replanning without continuous agent polling. To obtain diverse specialized VLA tools that faithfully follow agent invocations, we further propose Tool-Aligned Post-Training (TAPT), which constructs invocation-aligned training units for instruction following and adopts tool-family residual adapters for efficient tool specialization. Experiments show that VLAs-as-Tools improves the success rate of $π_{0.5}$ by 4.8 points on LIBERO-Long and 23.1 points on RoboTwin, and further enhances invocation fidelity by 15.0 points as measured by Non-biased Rate. Code will be released.

Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental Perception: agents must infer environmental constraints through trial-and-error, resulting in an Epistemic Bottleneck that traps them in inefficient failure cycles. Inspired by human affordance perception and cognitive map theory, we propose the Map-then-Act Paradigm (MAP), a plug-and-play framework that shifts environment understanding before execution. MAP consists of three stages: (1) Global Exploration, acquiring environment-general priors; (2) Task-Specific Mapping, constructing a structured cognitive map; and (3) Knowledge-Augmented Execution, solving tasks grounded on the map. Experiments show consistent gains across benchmarks and LLMs. On ARC-AGI-3, MAP enables frontier models to surpass near-zero baseline performance in 22 of 25 game environments. We further introduce MAP-2K, a dataset of map-then-act trajectories, and show that training on it outperforms expert execution traces, suggesting that understanding environments is more fundamental than imitation.

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly focus on user histories, short traces, or downstream task success, leaving open how to directly evaluate whether memory systems effectively internalize environment-specific experience. To address this gap, we introduce LongMemEval-V2 (LME-V2), a benchmark for evaluating whether memory systems can help agents acquire the experience needed to become knowledgeable colleagues in customized environments. LME-V2 contains 451 manually curated questions covering five core memory abilities for web agents: static state recall, dynamic state tracking, workflow knowledge, environment gotchas, and premise awareness. Questions are paired with history trajectories containing up to 500 trajectories and 115M tokens. We use a context gathering formulation: memory systems consume history trajectories and return compact evidence for downstream question answering. We propose a suite of two memory methods: AgentRunbook-R, an efficient RAG-based memory with knowledge pools for raw state observations, events, and strategy notes, and AgentRunbook-C, which stores trajectories as files and invokes a coding agent to gather evidence in an augmented sandbox. Experiments show that AgentRunbook-C achieves the best performance with 72.5% average accuracy, outperforming the strongest RAG baseline (48.5%) and the off-the-shelf coding agent baseline (69.3%). Despite the strong performance gains, coding agent based methods have high latency costs. While AgentRunbook-C advances the accuracy-latency Pareto frontier, substantial room for improvement remains. Together, these results establish LME-V2 as a challenging testbed for developing long-term memory systems for environment experience.

The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, existing benchmarks primarily focus on daily open-domain conversations, failing to capture the high-stakes complexity of real-world medical applications. Motivated by the stringent production requirements of an industry-leading health management agent serving tens of millions of active users, we introduce MedMemoryBench. We develop a human-agent collaborative pipeline to synthesize highly realistic, long-horizon medical trajectories based on clinically grounded, synthetic patient archetypes. This process yields a massive, expertly validated dataset comprising approximately 2,000 sessions and 16,000 interaction turns. Crucially, MedMemoryBench departs from traditional static evaluations by pioneering an "evaluate-while-constructing" streaming assessment protocol, which precisely mirrors dynamic memory accumulation in production environments. Furthermore, we formalize and systematically investigate the critical phenomenon of memory saturation, where sustained information influx actively degrades retrieval and reasoning robustness. Comprehensive benchmarking reveals severe bottlenecks in mainstream architectures, particularly concerning complex medical reasoning and noise resilience. By exposing these fundamental flaws, MedMemoryBench establishes a vital foundation for developing robust, production-ready medical agents.

Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring and tracking a complex environment state over many steps. This leads to two challenges: partial observability requires maintaining uncertainty over unobserved world attributes, and long interaction history causes context to grow without bound, diluting task-relevant information. A principled solution to both challenges is a belief state: a posterior distribution over environment states given past observations and actions, which compactly encodes history for decision making regardless of episode length. In LLM agents, however, the open-ended nature of text makes it unclear how to represent such a distribution. Therefore, we introduce Agent-BRACE: Agent Belief state Representation via Abstraction and Confidence Estimation, a method that decouples an LLM agent into a belief state model and a policy model, jointly optimized via reinforcement learning. The belief state model produces a structured approximation of the belief distribution: a set of atomic natural language claims about the environment, each annotated with an ordinal verbalized certainty label ranging from certain to unknown. The policy model conditions on this compact, structured approximate belief rather than the full history, learning to select actions under explicit uncertainty. Across long-horizon, partially observable embodied language environments, Agent-BRACE achieves an average absolute improvement of +14.5% (Qwen2.5-3B-Instruct) and +5.3% (Qwen3-4B-Instruct), outperforming strong RL baselines while maintaining a near-constant context window independent of episode length. Further analysis shows that the learned belief becomes increasingly calibrated over the course of an episode as evidence accumulates.

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.

Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, salience, or summary quality. For an agent, however, memory is valuable not because it faithfully describes the past, but because it preserves the distinctions between histories that must remain separated under a fixed budget to support good decisions. We cast this as a decision-centric rate-distortion problem, measuring memory quality by the loss in achievable decision quality induced by compression. This yields an exact forgetting boundary for what can be safely forgotten, and a memory-distortion frontier characterizing the optimal tradeoff between memory budget and decision quality. Motivated by this decision-centric view of memory, we propose DeMem, an online memory learner that refines its partition only when data certify that a shared state would induce decision conflict, and prove near-minimax regret guarantees. On both controlled synthetic diagnostics and long-horizon conversational benchmarks, DeMem yields consistent gains under the same runtime budget, supporting the principle that memory should preserve the distinctions that matter for decisions, not descriptions.

To cope with the large contexts that long-horizon LLM agents produce, modern frameworks increasingly rely on compaction -- invoking an LLM to rewrite the accumulated trajectory into a shorter summary that the agent resumes from. Today, compaction runs synchronously on the critical path of agent execution but this can unpredictably degrade accuracy due to a structural validation gap: the compactor must condense context but is fundamentally unaware of precisely what information the agent will need later. Further, because post-compaction agent steps are conditioned on the new summary, targeted validation criteria do not exist and errors silently propagate through coherent but incorrect behavior. Our key insight is that asynchronous compaction efficiently addresses this gap: by running the compactor in parallel with continued agent execution on the original context, the candidate summary and the agent's next steps are generated independently from the same pre-compaction state, yielding a validation signal independent of the summary itself. We build Slipstream, a trajectory-grounded compaction system that uses a judge to validate the candidate summary against the agent's continued reasoning, checking that it preserves both the agent's forward intent and the key facts and constraints it depends on. Across long-horizon coding (SWE-bench Verified) and web-browsing (BrowseComp) workloads, Slipstream improves task accuracy by up to 8.8 percentage points while reducing end-to-end latency by up to 39.7%.

Long-horizon AI agents execute complex workflows spanning hundreds of sequential actions, yet a single wrong assumption early on can cascade into irreversible errors. When instructions are incomplete, the agent must decide not only whether to ask for clarification but when, and no prior work measures how clarification value changes over the course of execution. We introduce a forced-injection framework that provides ground-truth clarifications at controlled points in the agent's trajectory across four information dimensions (goal, input, constraint, context), three agent benchmarks, and four frontier models (three per benchmark; one on a single benchmark only; 84 task variants; 6,000+ runs). Counter to the common intuition that "earlier is always better," we find that the value of clarification depends sharply on what information is missing: goal clarification loses nearly all value after 10% of execution (pass@3 drops from 0.78 to baseline), while input clarification retains value through roughly 50%. Deferring any clarification type past mid-trajectory degrades performance below never asking at all. Cross-model Kendall tau correlations (0.78-0.87 among models sharing identical task coverage; 0.34-0.67 across the full 4-model panel) confirm these timing profiles are substantially task-intrinsic. A complementary study of 300 unscripted sessions reveals that no current frontier model asks within the empirically optimal window, with strategies ranging from over-asking (52% of sessions) to never asking at all. These empirical demand curves provide the quantitative foundation that existing theoretical frameworks require but have lacked, and establish concrete design targets for timing-aware clarification policies. Code and data will be publicly released.

Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessions not annotated as task-relevant evidence for the query) accumulate. We present a scale-conditioned evaluation protocol for agent memory under evidence-preserving growth: for each query, task evidence is held fixed while irrelevant sessions are added. The protocol logs agent--memory trajectories and reports four diagnostics: budget-compliant reliability, tail memory-call burden, failure-regime decomposition, and the usable-scale boundary where reliability falls below the target. Applied to LongMemEval and LoCoMo across flat, planar, and hierarchical memory interfaces, the protocol shows reliability loss is not a single phenomenon. On LongMemEval, HippoRAG stays within the two-call budget but loses 16--20 percentage points in budget-compliant reliability as irrelevant sessions are added; LiCoMemory's observed failures depend strongly on the agent, with Qwen3-8B exceeding the budget while Qwen3-32B and Qwen3-235B remain reliable in the tested range. The result supports a framework for making scalable-memory claims conditional on agent, interface, scale range, and interaction budget.

This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer that governs context construction, tool interaction, orchestration, and verification around a language model, is often a stronger determinant of agent performance than the model it wraps. We formalize and defend the Binding Constraint Thesis: in this regime, performance variance is governed more by harness configuration than by model choice, and current evaluation protocols therefore systematically misattribute harness-level gains to model improvements. We support this thesis along three lines. First, a control-theoretic formalization treats the harness as the controller of a closed-loop dynamical system and the LLM as the stochastic policy it governs, which explains why small harness changes can produce performance shifts that exceed those obtained by substituting one model for another. Second, published benchmarks, industry deployments, and a controlled variance decomposition show that harness-induced variance can substantially exceed model-induced variance, including cases of model ranking reversal. Third, we propose a harness-aware evaluation framework with a disclosure standard and a variance decomposition protocol. Until harness specifications are disclosed, leaderboard comparisons for long-horizon agents should be treated as incomplete and potentially misleading.

While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identify two root causes: credit misattribution, where correct early actions are penalized due to terminal failures, and sample inefficiency, where scarce successful trajectories result in near-total loss of learning signal. We introduce a milestone-guided policy learning framework, BEACON, that leverages the compositional structure of long-horizon tasks to ensure precise credit assignment. BEACON partitions trajectories at milestone boundaries, applies temporal reward shaping within segments to credit partial progress, and estimates advantages at dual scales to prevent distant failures from corrupting the evaluation of local actions. On ALFWorld, WebShop, and ScienceWorld, BEACON consistently outperforms GRPO and GiGPO. Notably, on long-horizon ALFWorld tasks, BEACON achieves 92.9% success rate, nearly doubling GRPO's 53.5%, while improving effective sample utilization from 23.7% to 82.0%. These results establish milestone-anchored credit assignment as an effective paradigm for training long-horizon language agents. Code is available at https://github.com/ZJU-REAL/BEACON.

Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can overwhelm the agent, increasing costs and the risk of errors. We propose that effective context management should be adaptive: parts of the agent's trajectory are maintained at different levels of detail depending on their current relevance to the task. To operationalize this principle, we introduce Context-ReAct, a general agentic paradigm for elastic context orchestration that integrates reasoning, context management, and tool use in a unified loop. Context-ReAct provides five atomic operations: Skip, Compress, Rollback, Snippet and Delete, which allow the agent to dynamically reshape its working context, preserving important evidence, summarizing resolved information, discarding unhelpful branches, and controlling context size. We prove that the Compress operator is expressively complete, while the other specialized operators provide efficiency and fidelity guarantees that reduce generation cost and hallucination risk. Building on this paradigm, we develop LongSeeker, a long-horizon search agent fine-tuned from Qwen3-30B-A3B on 10k synthesized trajectories. Across four representative search benchmarks, LongSeeker achieves 61.5% on BrowseComp and 62.5% on BrowseComp-ZH, substantially outperforming Tongyi DeepResearch (43.2% and 46.7%) and AgentFold (36.2% and 47.3%). These results highlight the potential of adaptive context management, showing that agents can achieve more reliable and efficient long-horizon reasoning by actively shaping their working memory.

Memory systems are widely adopted to enhance LLMs for long-horizon tasks, and are commonly organized as multi-agent pipelines with memory building, summarizing, and retrieval agents. To empower this system, existing RL-based methods either apply final downstream task rewards (e.g., QA accuracy) for all agents uniformly, which are coarse and ambiguous, or design task-specific rewards for agents on different subtasks, which require costly annotations (e.g., key evidence) and are difficult to define reliably. To address these limitations, we propose Tree-based Credit Assignment for Multi-Agent Memory Systems (TreeMem), which derives agent-specific credit from the final reward without task-specific annotations. Specifically, TreeMem extends the multi-agent pipeline (builder--summarizer--retrieval) into a tree structure, where each agent's outputs are expanded into multiple subsequent branches. The contribution of each agent is estimated via Monte Carlo averaging over its subsequent branches, capturing how intermediate agent actions may influence the final reward. This converts the coarse final reward into agent-specific optimization signals. These signals are then used to update all agent policies simultaneously, helping heterogeneous agents specialize effectively. Experiments on long-horizon benchmarks show that TreeMem improves memory system performance over strong baselines, validating the effectiveness of tree-structured credit assignment for the multi-agent memory system.

Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and unit-test-driven tasks. They remain less reliable in open-ended settings, including scientific assistance, long-horizon agents, high-stakes advice, personalization, and tool use, where the relevant objective is ambiguous, context-dependent, delayed, or only partially observable. We argue that many such failures are not merely failures of scale or capability, but failures of objective selection: the system optimizes a locally visible signal while missing which objectives should govern the interaction. We formulate this problem as \emph{contextual multi-objective optimization}. In this setting, systems must consider multiple, context-dependent objectives, such as helpfulness, truthfulness, safety, privacy, calibration, non-manipulation, user preference, reversibility, and stakeholder impact, while determining which objectives are active, which are soft preferences, and which must function as hard or quasi-hard constraints. These examples are not intended as an exhaustive taxonomy: different domains and deployment settings may activate different objective dimensions and different conflict-resolution procedures. Our framework models AI behavior as a context-dependent choice rule over candidate actions, objective estimates, active constraints, stakeholders, uncertainty, and conflict-resolution procedures. We outline an implementation pathway based on decomposed objective representations, context-to-objective routing, hierarchical constraints, deliberative policy reasoning, controlled personalization, tool-use control, diagnostic evaluation, auditing, and post-deployment revision.

Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-horizon, multi-engineer, ambiguous-specification deliverables. This paper takes a position on what training data is needed to close the gap. The substrate for the next generation of SWE agents is neither larger GitHub scrapes nor more solo-agent trajectories nor -- sufficient by itself -- open human-AI dialogue logs. It is triadic data: synchronized capture of the human-human conversations where engineering context is formed, the human-AI sessions where that context is partially consumed, and the multi-week cross-functional work that surrounds both. We argue that the canonical instantiation of triadic data is two complementary products: long-horizon expert trajectories captured under stimulated-recall protocols, and simulated cross-functional companies -- instrumented teams of senior engineers, product managers, designers, and data scientists working through ambiguous deliverables on shared infrastructure. We further specify a four-tier evidence framework through which any such corpus -- triadic or otherwise -- must justify its quality to a fine-tuning researcher: mechanical verification, statistical corpus characterization, probe experiments, and pre-registered blind evaluation. We argue that this data is capturable in 12-18 months with methods already mature in adjacent fields, that it is the empirical key to four open questions in agent training, and that the field's near-term research agenda should include it explicitly.

Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an enhanced multi-agent framework that decomposes automation into three roles: a planner for high-level decision-making, an actor for task execution, and a memory manager for contextual reasoning. While this modular decomposition aligns with established design patterns, our core contribution lies in a systematic compute-allocation analysis, revealing that planning is the dominant factor influencing task performance. Execution and memory management require significantly less compute and model capacity to achieve competitive results. Building on these insights, we introduce a planner-centric reinforcement learning approach, which exclusively optimizes the planner using trajectory-level rewards from a VLM-as-judge, while freezing the other components. Extensive experiments on benchmarks spanning web navigation, OS control, and tool use demonstrate that concentrating model capacity and learning on high-level planning yields robust and compute-efficient improvements in long-horizon agent automation. Our code is publicly released.

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind parameterized scripts, they fail to capture the conditional logic required for robust execution in dynamic environments. In this paper, we propose Neuro-Symbolic Skill Induction (NSI), a framework that lifts interaction traces into modular, \textit{logic-grounded} programs. By synthesizing explicit control flows and dynamic variable binding, NSI empowers agents to discover \textit{when} and \textit{why} to act. This paradigm enables the efficient generalization, allowing agents to induce skills from few-shot examples and flexibly adapt to unseen goals. Experiments on a series of agentic tasks demonstrate that NSI consistently outperforms state-of-the-art baselines, empowering agents to self-evolve into architects of logic-grounded skills.

We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions

Current embodied agents are often limited to passive instruction-following or reactive need-satisfaction, lacking a stable, high-order value framework essential for long-term, self-directed behavior and resolving motivational conflicts. We introduce \textit{ValuePlanner}, a hierarchical cognitive architecture that decouples high-level value scheduling from low-level action execution. \textit{ValuePlanner} employs an LLM-based cognitive module to generate symbolic subgoals by reasoning through abstract value trade-offs, which are then translated into executable action plans by a classical PDDL planner. This process is refined via a closed-loop feedback mechanism. Evaluating such autonomy requires methods beyond task-success rates, and we therefore propose a value-centric evaluation suite measuring cumulative value gain, preference alignment, and behavioral diversity. Experiments in the TongSim household environment demonstrate that \textit{ValuePlanner} arbitrates competing values to generate coherent, long-horizon, self-directed behavior absent from instruction-following and needs-driven baselines. Our work offers a structured approach to bridging intrinsic values and grounded behavior for autonomous agents.

Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended histories. However, existing agent memory systems are fundamentally constrained by text-context budgets: storing or revisiting raw trajectories is prohibitively token-expensive, while summarization and text-only retrieval trade token savings for information loss and fragmented evidence. To address this limitation, we propose Optical Context Retrieval Memory (OCR-Memory), a memory framework that leverages the visual modality as a high-density representation of agent experience, enabling retention of arbitrarily long histories with minimal prompt overhead at retrieval time. Specifically, OCR-Memory renders historical trajectories into images annotated with unique visual identifiers. OCR-Memory retrieves stored experience via a \emph{locate-and-transcribe} paradigm that selects relevant regions through visual anchors and retrieves the corresponding verbatim text, avoiding free-form generation and reducing hallucination. Experiments on long-horizon agent benchmarks show consistent gains under strict context limits, demonstrating that optical encoding increases effective memory capacity while preserving faithful evidence recovery.

Scientific Deep Research (DR) agents answer user queries by synthesizing research papers into multi-section reports. User feedback can improve their utility, but existing protocols only score the final report, making it hard to study and learn which intermediate actions DR agents should take to improve reports. We collect DRACULA, the first dataset with user feedback on intermediate actions for DR. Over five weeks, nineteen expert CS researchers ask queries to a DR system that proposes actions (e.g., "Add a section on datasets"). Our users select actions they prefer, then judge whether an output report applied their selections successfully, yielding 8,103 action preferences and 5,230 execution judgments. After confirming a DR agent can execute DRACULA's actions, we study the predictability of user-preferred actions via simulation-how well LLMs predict the actions users select-a step toward learning to generate useful actions. We discover: (1) LLM judges initially struggle to predict action selections, but improve most when using a user's full selection history, rather than self-reported or extrapolated user context signals; (2) Users' selections for the same query differ based on unstated goals, bottlenecking simulation and motivating affordances that let users steer reports; and (3) Our simulation results inform an online intervention that generates new actions based on the user's past interactions, which users pick most often in follow-up studies. Overall, while work extensively studies execution, DRACULA reveals a key challenge is deciding which actions to execute in the first place. We open-source DRACULA's study design, user feedback, and simulation tasks to spur future work on action feedback for long-horizon agents.

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies largely depend on hybrid semantic graph architectures, which impose substantial computational overhead during both ingestion and retrieval. These systems typically require large language model mediated entity extraction, explicit graph schema maintenance, and multi query retrieval pipelines. This paper introduces Memanto, a universal memory layer for agentic artificial intelligence that challenges the prevailing assumption that knowledge graph complexity is necessary to achieve high fidelity agent memory. Memanto integrates a typed semantic memory schema comprising thirteen predefined memory categories, an automated conflict resolution mechanism, and temporal versioning. These components are enabled by Moorcheh's Information Theoretic Search engine, a no indexing semantic database that provides deterministic retrieval within sub ninety millisecond latency while eliminating ingestion delay. Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively. These results surpass all evaluated hybrid graph and vector based systems while requiring only a single retrieval query, incurring no ingestion cost, and maintaining substantially lower operational complexity. A five stage progressive ablation study is presented to quantify the contribution of each architectural component, followed by a discussion of the implications for scalable deployment of agentic memory systems.

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact retrieval from past conversations, providing limited insight into agents' ability to consolidate memory over time or handle frequent knowledge updates. We introduce Memora, a long-term memory benchmark spanning weeks to months long user conversations. The benchmark evaluates three memory-grounded tasks: remembering, reasoning, and recommending. To ensure data quality, we employ automated memory-grounding checks and human evaluation. We further introduce Forgetting-Aware Memory Accuracy (FAMA), a metric that penalizes reliance on obsolete or invalidated memory when evaluating long-term memory. Evaluations of four LLMs and six memory agents reveal frequent reuse of invalid memories and failures to reconcile evolving memories. Memory agents offer marginal improvements, exposing shortcomings in long-term memory for personalized agents.

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves useful environment feedback, but also leads to context saturation and high token cost; conversely, naive compression may discard task-critical signals needed for subsequent actions. Because terminal environments are highly heterogeneous across repositories, commands, and execution states, heuristic-based or fixed-prompt compression methods are difficult to generalize. We propose TACO, a plug-and-play, training-free, self-evolving Terminal Agent Compression framework for existing terminal agents. TACO automatically discovers, refines, and reuses structured compression rules from interaction trajectories, enabling workflow-adaptive filtering of low-value terminal outputs while preserving task-relevant observations. Experiments on TerminalBench (TB 1.0 and TB 2.0) and four additional terminal-related benchmarks, including SWE-Bench Lite, CompileBench, DevEval, and CRUST-Bench, show that TACO consistently improves task performance and token efficiency across agent scaffolds and backbone models. On TerminalBench, TACO yields 1%-4% accuracy gains across strong agentic models and improves accuracy by around 2%-3% under the same token budget. On additional terminal-related benchmarks, it reduces total token consumption while maintaining or improving task success rates. These results suggest that self-evolving, workflow-adaptive observation compression is an effective path toward more reliable and efficient long-horizon terminal agents. The code is publicly available at https://github.com/multimodal-art-projection/TACO.

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this premise: each attempt produces an extended trajectory of actions, observations, errors, and partial progress taken by the agent. In this setting, the main challenge is no longer generating more attempts, but representing prior experience in a form that can be effectively selected from and reused. We propose a test-time scaling framework for agentic coding based on compact representations of rollout trajectories. Our framework converts each rollout into a structured summary that preserves its salient hypotheses, progress, and failure modes while discarding low-signal trace details. This representation enables two complementary forms of inference-time scaling. For parallel scaling, we introduce Recursive Tournament Voting (RTV), which recursively narrows a population of rollout summaries through small-group comparisons. For sequential scaling, we adapt Parallel-Distill-Refine (PDR) to the agentic setting by conditioning new rollouts on summaries distilled from prior attempts. Our method consistently improves the performance of frontier coding agents across SWE-Bench Verified and Terminal-Bench v2.0. For example, by using our method Claude-4.5-Opus improves from 70.9% to 77.6% on SWE-Bench Verified (mini-SWE-agent) and 46.9% to 59.1% on Terminal-Bench v2.0 (Terminus 1). Our results suggest that test-time scaling for long-horizon agents is fundamentally a problem of representation, selection, and reuse.

Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on "always-on" retrieval and "flat" memory storage, causing high interference and latency as histories grow. We introduce Oblivion, a memory control framework that casts forgetting as decay-driven reductions in accessibility -- not explicit deletion. Oblivion decouples memory control into read and write paths. The read path decides when to consult memory, based on agent uncertainty and memory buffer utility, avoiding redundant always-on access. The write path decides what to strengthen, by reinforcing memories contributing to forming the response. Together, this enables hierarchical memory organization that maintains persistent high-level strategies while dynamically loading details as needed. We evaluate on both static and dynamic long-horizon interaction benchmarks. Oblivion outperforms both direct and memory-augmented baselines, while reducing token cost by up to 73% at 120K interaction spans. These results show that treating memory as a control problem -- deciding when to retrieve and what to reinforce -- is essential for sustaining long-horizon agent performance.

Long-context LLMs and Retrieval-Augmented Generation defer state tracking and evidence consolidation to query time, which is brittle when facts evolve and answers depend on latent states. We introduce Unified Memory Agent (UMA) for a one-to-many setting: query-agnostic external memory is constructed once from a stream and reused across multiple future QA sessions. A single policy maintains a structured Memory Bank through CRUD operations and answers using both the Memory Bank and raw context. Task-Stratified GRPO uses the mean reward of QA trajectories branching from each sampled memory state to supervise memory maintenance, while normalizing memory and per-question QA groups separately. We also introduce Ledger-QA, a diagnostic benchmark for long-horizon state tracking over accumulated updates. At the 16k budget, UMA-Generalist achieves the highest average score among compared methods across the test-time-learning and accurate-retrieval benchmarks and transfers to Ledger-QA without task-specific training; UMA-Specialist further improves long-horizon tracking after task adaptation. These results support learned proactive memory management for long-context reasoning.

Long-horizon agentic search requires iteratively exploring the web over long trajectories and synthesizing information across many sources, enabling powerful applications like deep research systems. In this work, we show that popular agentic search frameworks struggle to scale to long trajectories primarily due to context limitations--they accumulate long, noisy content, hit context window and tool budgets, or stop early. We therefore introduce SLIM (Simple Lightweight Information Management), a simple framework that separates retrieval into distinct search and browse tools, and periodically summarizes the trajectory, keeping context concise while enabling longer, more focused searches. Across a wide range of long-horizon tasks, SLIM achieves comparable performance at substantially lower cost and far fewer tool calls than strong open-source frameworks with both proprietary and open-weight models, including RL-trained models for deep research. Specifically, with o3 as the base model, SLIM achieves 56% on BrowseComp and 33% on HLE, outperforming all open-source frameworks by 8 and 6 absolute points, respectively, while incurring 4-6x fewer tool calls. With GLM-4.7 Flash, SLIM achieves 10 points improvement over the next best open-source framework, Search-o1, on BrowseComp using a third of the cost. To systematically understand failure modes in long-horizon agentic search, we develop an automated fine-grained trajectory analysis pipeline and error taxonomy, and find that SLIM exhibits significantly fewer hallucinations than prior systems. We hope our analysis framework and simple tool design inform future long-horizon agents.

As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests while deviating from the users true goal. We study this reward hacking phenomenon by decompose software engineering tasks into three parts: (i) a natural language description of the specification (ii) visible validation tests that exercise specified features in isolation, and (iii) held-out tests that compose those same features to simulate real-world usage. Based on the specification and the visible validation test suites, a genuine agent would be able to generate a solution that can also pass all of the held-out tests. Therefore we use the gap in pass rates on these two suites to quantify reward hacking. Based on this methodology, we introduce SpecBench, a benchmark comprising 30 systems-level programming tasks ranging from short horizon tasks like building a JSON parser to ultra long horizon tasks like building an entire OS kernel from scratch. Large-scale experiments reveal a consistent pattern: while every frontier agent saturates the visible suite, reward hacking persists, with smaller models exhibiting larger gaps on holdout suites. The gap also scales sharply with task length: it grows by 28 percentage points for every tenfold increase in code size. Failures range from subtle feature isolation to deliberate exploits, including a 2,900-line hash-table "compiler" that memorizes test inputs. SpecBench offers a principled testbed for measuring whether coding agents build genuine working systems or merely game the test suites developers hand them.