Language agents increasingly tackle long-horizon tasks in interactive environments, where actions often depend on latent preconditions. The core difficulty is not trajectory length but recovery: when a prerequisite is missing or an earlier decomposition fails, trying another plausible action rarely helps. ReAct and later reflection or adaptive-planning methods support local correction, but express recovery as free-form text, with no explicit control state linking the terminal goal, the active goal, and the failure source. We introduce the Verify--Backtrack Loop (VBL), a training-free extension of ReAct that turns precondition discovery and failure diagnosis into structured planning-state updates. VBL maintains the task decomposition as a bounded goal stack and, on goal activation, execution failure, or material state change, jointly verifies two horizons---whether the active goal contributes to the terminal goal and whether it is feasible in the current state. These dual-horizon judgments, combined with typed failure attribution, trigger explicit operations---Push, Pop, retry, or BacktrackTo the parent. We evaluate VBL with Qwen3.5-9B, GPT-4o, and DeepSeek-V3.2 on AppWorld, ALFWorld, and ScienceWorld. VBL improves over ReAct and reflection-based control on every backbone--benchmark pair. On the challenging AppWorld setting, it improves task success by up to 22.07 percentage points over ReAct. Ablations show that removing either verification or diagnosis degrades performance, in several settings below ReAct, confirming that the two mechanisms are complementary. These results show that reliable long-horizon interaction benefits from revising the planning state, not merely the next action.
Figures & tables
Figure 1: Control structures compared. (1) ReAct interleaves thought, action, and observation in a linear loop. (2) ReflAct replaces the thought with reflection on the current state relative to the task goal, but the loop stays linear. (3) VBL maintains an explicit goal stack: Verify checks alignment and readiness when due is set (on activation, after failure, or after a material state change), a completed goal is removed with Pop , and a failure is routed through Diagnose to one of Push (insert a prerequisite), a local retry, or BacktrackTo (resume from the parent). The executor receives the root task text together with the active goal—here g2 —not the full stack.
AppWorld
Model
Method
Normal
Chall.
ALFW.
SciW.
Qwen3.5-9B
NoThinking
14.29
7.43
69.40
21.80
ReAct
17.26
8.63
81.34
33.18
ReflAct
22.62
13.19
86.57
36.97
VBL
35.71
30.70
87.31
47.39
GPT-4o
NoThinking
17.86
10.55
67.16
35.55
Table 2: Main results: task success rate (%) on AppWorld, ALFWorld, and ScienceWorld. Chall.: AppWorld Challenge split; ALFW.: ALFWorld; SciW.: ScienceWorld. VBL is the best method on every backbone–benchmark pair.
Benchmark
Method
SR
kTok
kTok/S
AW-N
ReAct
17.26
138.9
804.8
VBL
35.71
221.5
620.2
AW-C
ReAct
8.63
223.3
2587.5
VBL
30.70
448.5
1460.9
ALFW.
ReAct
81.34
63.1
77.6
VBL
87.31
67.1
76.9
Table 3: Token cost on Qwen3.5-9B. AW-N/AW-C: AppWorld Normal/Challenge; ALFW.: ALFWorld; SciW.: ScienceWorld. SR: success rate (%); kTok: average thousands of tokens per episode (including VBL’s verification, diagnosis, and summarization); kTok/S: 100× kTok / SR. Bold : higher SR or lower kTok/S.
AppWorld
ALFW.
SciW.
Variant
Normal
Chall.
Qwen3.5-9B
VBL (full)
35.71
30.70
87.31
47.39
w/o Verify
35.12
28.06
76.12
40.28
w/o Diagnose
34.52
28.54
79.85
41.23
GPT-4o
Table 4: Leave-one-out ablation of VBL’s two control modules across three backbone models (Qwen3.5-9B, GPT-4o, DeepSeek-V3.2). Success rate (%). Each variant retains the goal stack and the other module.
Push
Backtrack
Bench.
Model
mean
%ep
mean
%ep
AW-N
Qwen3.5-9B
1.10
63.1
0.22
13.7
GPT-4o
0.42
33.9
0.05
4.8
DeepSeek-V3.2
0.77
69.0
0.04
4.0
AW-C
Qwen3.5-9B
1.55
93.5
0.47
27.3
GPT-4o
0.89
71.2
0.12
8.2
Table 5: Control-operation usage for VBL on AppWorld. AW-N/AW-C: AppWorld Normal/Challenge. “mean” is the average number of operations per episode; “%ep” is the fraction of episodes with at least one such operation. Push remains the dominant remedy; BacktrackTo is secondary but consistently higher on the harder Challenge split.
Figure 2: Case study (task 2d9f728_1 ). Baselines thrash on auth errors; VBL inserts login via Push and completes the settlement.
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
AppWorld
ALFWorld
ScienceWorld
Stack depth Dmax
6
6
6
Retry limit Nmax
8
8
8
Push limit Lpush
4
4
4
at the root goal
1
1
1
Backtrack limit Lbt
3
3
3
Diagnosis threshold K
2
2
2
Appendix
Table C.1: Hyperparameters for full VBL. Control bounds are shared across benchmarks; B matches the experimental setting in Section 4.1 . a Normal / Challenge.
Field
Content
d(gi)
Active-goal description at the time of the segment
context
Short local context (recent observation / stack focus)
action
Action (or code block) that closed the segment
outcome
Post-action observation or success/failure signal
attribution
Diagnose label z when the segment ended in failure; empty on clean Pop
Table E.1: Episode-buffer record fields. Records are written by Summarize / Update when a goal is popped, a path is marked failed, or diagnosis assigns a recovery transition.
Task: request $13 from Stacy on Venmo (note: “For yesterday’s meal”, privacy: public)
ReflAct (fail)
VBL (succeed)
login → find Stacy
Verify → Push ( login ) → token
Action: create_transaction (send money)
search_friends → arg error
Diagnose → BacktrackTo (parent)
Obs: “Sent money.” mutates Transaction
Action: create_payment_request ($13, public note)
Result: 1/7 tests
Result: 7/7 tests
Appendix
Figure H.1: Additional case (task 024c982_1 ). ReflAct inverts the goal with create_transaction ; VBL repairs the failed lookup on the stack and keeps the request operator.
Qwen3.5-9B
DeepSeek-V3.2
ALFWorld task type
ReAct
VBL
ReAct
VBL
look_at_obj_in_light
77.8
100.0
100.0
100.0
pick_and_place_simple
100.0
100.0
95.8
100.0
pick_clean_then_place
77.4
83.9
87.1
100.0
pick_cool_then_place
95.2
95.2
90.5
95.2
pick_heat_then_place
52.2
65.2
69.6
78.3
Appendix
Table I.1: ALFWorld success rate (%) by task type. Gains often fall on compositional types that require establishing an enabling state (e.g., clean or heat) before the terminal action, though the pattern is not uniform across backbones.
Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can resolve. We introduce BELIEFWEAVER, a framework that combines persistent evidence across attempts with prospective reasoning over repair directions. It maintains a relational belief state over frontiers, attempts, observations, and checkpoints. Execution evidence updates related frontier priorities across attempts and rollback, while diagnostic evidence gates execution. An implicit world model (IWM) evaluates repair hypotheses, predicts progress, and identifies relations among frontiers to guide exploration. We further distill these recurring IWM reasoning components into a 9B student through supervised fine-tuning and on-policy distillation (OPD). Across three terminal-based benchmarks, BELIEFWEAVER improves aggregate final score by 5.1 percentage points over native Terminus-2 continuation, with positive trends in exploration efficiency. The distilled 9B student improves final score by 9.8 percentage points over the reported native baseline while reducing estimated teacher API cost by 54.8% relative to the matched teacher. These results show that persistent evidence and prospective reasoning can improve recovery in long-horizon agent tasks while substantially reducing reliance on teacher-model inference.
Recent advances in reasoning backbones have empowered large language model (LLM)agentstotackle complex, multi-step tasks. However, as reasoning horizons grow, inconsistent internal beliefs induce intermediate errors that cause agents to drift from their goals. This limitation also persists in REFLACT, which reflects only on the end-goal at each step without explicitly considering intermediate sub goals. To address this problem, we propose SGG-ReflAct (Sub-Goal Guided Re flAct), a reasoning backbone that integrates sub-goals generated through a single path LLM planner into the reflection process. We further extend this framework to BeamSGG-ReflAct, which replaces the single-path planner with a beam search based LLM planner for structured plan exploration. We run experiments on ALF World, ScienceWorld, and Jericho with multiple LLM models. SGG-ReflAct out performs REFLACT in nearly all settings, achieving best success rate gains of 14.9 percentage points on ALFWorld and 8.0 percentage points on ScienceWorld with Llama-3.1-8B-Instruct. Our experimental analysis shows that SGG-ReflAct re duces hallucinated actions and achieves its largest gains on procedurally ordered tasks. Furthermore, experimental results with BeamSGG-ReflAct show that the backbone's effectiveness depends on plan quality: explicitly specifying the re quired operations recovers gains that plan searching alone cannot achieve. These results demonstrate that SGG-ReflAct offers a practical and highly effective rea soning backbone, enabling LLM agents to achieve reliable performance in com plex, long-horizon tasks through easy integration.
Jaeho Jung, Sung Hoon Jung
Independent Researcher Seoul, Republic of Korea · Department of Applied Artificial Intelligence Hansung University Seoul, Republic of Korea
Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to track and allowing incorrect self-assessments to propagate into later decisions. We reformulate long-horizon execution as a task-state management problem and propose LongHorizon-Harness, which maintains the task state explicitly outside execution and updates it only with facts independently verified from the environment. Its Manage-Execute-Audit(MEA) loop uses a manager to maintain the task state and determine the next subtask, a fresh-context executor to perform it, and a read-only auditor to verify the resulting environment state before the next round. A lightweight AgentAdapter supports interchangeable model and harness backends without modifying their native agent loops. LongHorizon-Harness improves Qwen3.7-Plus from 51.8% to 80.7% on WeaveBench, from 69.7% to 77.2% on Terminal-Bench2.1, and from 2.8% to 8.3% on OSWorld2.0. It also raises Claude Opus4.7 from 20.0% to 34.3% on an OSWorld2.0 subset, demonstrating consistent gains across models, harnesses, and interaction domains.