7 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.01476.json · badge: /api/ran/2407.01476.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| kohjingyu/search-agents | community (classifier label) classifier basis not recorded on the link |
7 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| action2str | Ran ran on a synthesized input |
kohjingyu/search-agents/browser_env/actions.py code served (permissive licence) · get_code("14343f643521d39a") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| get_site_comb_from_filepath | Ran ran; our contract draft was wrong, not the code |
kohjingyu/search-agents/browser_env/auto_login.py code served (permissive licence) · get_code("824ae078c5d3295a") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| parse_action | Ran ran; our contract draft was wrong, not the code |
kohjingyu/search-agents/browser_env/envs.py code served (permissive licence) · get_code("1829c408a278c974") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned PlaywrightScript. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| pil_to_b64 | Ran ran; our contract draft was wrong, not the code |
kohjingyu/search-agents/browser_env/utils.py pointer only (licence: MIT); the stored copy get_code serves, from osu-nlp-group/webdreamer, is pointer only (licence: NONE) · get_code("d8254925e6697a59") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from osu-nlp-group/webdreamer, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| pil_to_vertex | Ran ran; our contract draft was wrong, not the code |
kohjingyu/search-agents/browser_env/utils.py pointer only (licence: MIT); the stored copy get_code serves, from osu-nlp-group/webdreamer, is pointer only (licence: NONE) · get_code("71ec370bd2568e5b") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from osu-nlp-group/webdreamer, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| png_bytes_to_numpy | Ran ran, honoured the contract we drafted |
kohjingyu/search-agents/browser_env/utils.py code served (permissive licence) · get_code("04ba3dcf1bb13e4f") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| remove_unicode | Ran ran; our contract draft was wrong, not the code |
kohjingyu/search-agents/browser_env/processors.py code served (permissive licence) · get_code("b3cfdfe328f76c2d") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| get_site_comb_from_filepath | 4 other papers 3 dated earlier, 1 later |
2305.14257 (2023-05) Hierarchical Prompting Assists Large Language Model on Web Navigation |
2307.13854 (2023-07) WebArena: A Realistic Web Environment for Building Autonomous Agents 2401.13649 (2024-01) VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks and 1 more not named here |
| parse_action | 4 other papers 3 dated earlier, 1 later |
2305.14257 (2023-05) Hierarchical Prompting Assists Large Language Model on Web Navigation |
2307.13854 (2023-07) WebArena: A Realistic Web Environment for Building Autonomous Agents 2401.13649 (2024-01) VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks and 1 more not named here |
| pil_to_b64 | 3 other papers 1 dated earlier, 2 later |
2401.13649 (2024-01) VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks |
2411.06559 (2024-11) Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents 2505.16421 (2025-05) WEBAGENT-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning |
| pil_to_vertex | 3 other papers 1 dated earlier, 2 later |
2401.13649 (2024-01) VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks |
2411.06559 (2024-11) Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents 2505.16421 (2025-05) WEBAGENT-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning |
| png_bytes_to_numpy | 2 other papers 1 dated earlier, 1 later |
2401.13649 (2024-01) VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks |
2505.16421 (2025-05) WEBAGENT-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning |
| remove_unicode | 2 other papers 1 dated earlier, 1 later |
2401.13649 (2024-01) VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks |
2505.16421 (2025-05) WEBAGENT-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language understanding and generation, struggle with multi-step reasoning, planning, and using environmental feedback when attempting to solve realistic computer tasks. Towards addressing this, we propose an inference-time search algorithm for LM agents to explicitly perform exploration and multi-step planning in interactive web environments. Our approach is a form of best-first tree search that operates within the actual environment space, and is complementary with most existing state-of-the-art agents. It is the first tree search algorithm for LM agents that shows effectiveness on realistic web tasks. On the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%. Our experiments highlight the effectiveness of search for web agents, and we demonstrate that performance scales with increased test-time compute. We conduct a thorough analysis of our results to highlight improvements from search, limitations, and promising directions for future work. Our code and models are publicly released at https://jykoh.com/search-agents.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.01476")
get_code_for_paper("2407.01476")
have("2407.01476")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.01476.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.01476)
Connect an agent — have() is free.