{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bag-of-tricks-for-inference-time-computation","title":"Bag of Tricks for Inference-time Computation of LLM Reasoning","arxiv_id":"2502.07191","date":"2025-02-11","proceeding":null,"authors":["Fan Liu","Wenshuo Chao","Naiqiang Tan","Hao liu"],"abstract":"With the advancement of large language models (LLMs), solving complex reasoning tasks has gained increasing attention. Inference-time computation methods (e.g., Best-of-N, beam search, et al.) are particularly valuable as they can enhance reasoning performance without modifying model parameters or requiring additional training. However, these techniques come with implementation challenges, and most existing methods remain at the proof-of-concept stage with limited practical adoption due to their computational complexity and varying effectiveness across different tasks. In this paper, we investigate and benchmark diverse inference-time computation strategies across reasoning tasks of varying complexity. Since most current methods rely on a proposer-verifier pipeline that first generates candidate solutions (e.g., reasoning solutions) and then selects the best one based on reward signals (e.g., RLHF rewards, process rewards), our research focuses on optimizing both candidate solution generation (e.g., instructing prompts, hyperparameters such as temperature and top-p) and reward mechanisms (e.g., self-evaluation, reward types). Through extensive experiments (more than 20,000 A100-80G GPU hours with over 1,000 experiments) across a variety of models (e.g., Llama, Qwen, and Mistral families) of various sizes, our ablation studies reveal that previously overlooked strategies can significantly enhance performance (e.g., tuning temperature can improve reasoning task performance by up to 5%). Furthermore, we establish a standardized benchmark for inference-time computation by systematically evaluating six representative methods across eight reasoning tasks. These findings provide a stronger foundation for future research. The code is available at https://github.com/usail-hkust/benchmark_inference_time_computation_LL","url_abs":"https://arxiv.org/abs/2502.07191v1","url_pdf":"https://arxiv.org/pdf/2502.07191v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bag-of-tricks-for-inference-time-computation","repo_url":"https://github.com/usail-hkust/benchmark_inference_time_computation_LLM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.07191","atlas_url":"https://app.syntology.ai/?focus=2502.07191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07191"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/usail-hkust/benchmark_inference_time_computation_LLM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b6b5c2ac922594c4","entry":"binary_evaluate_unwrap","repo":"usail-hkust/benchmark_inference_time_computation_LLM","repo_kind":"official","path":"prompts/binary_evaluate.py","file_url":"https://github.com/usail-hkust/benchmark_inference_time_computation_LLM/blob/HEAD/prompts/binary_evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6b5c2ac922594c4"}},{"code_sha256_prefix":"bc5eb09b92b1cee1","entry":"extract_last_answer","repo":"usail-hkust/benchmark_inference_time_computation_LLM","repo_kind":"official","path":"methods/method_utils/str_utils.py","file_url":"https://github.com/usail-hkust/benchmark_inference_time_computation_LLM/blob/HEAD/methods/method_utils/str_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc5eb09b92b1cee1"}},{"code_sha256_prefix":"9de1a71e6056d426","entry":"extract_last_question","repo":"usail-hkust/benchmark_inference_time_computation_LLM","repo_kind":"official","path":"methods/method_utils/str_utils.py","file_url":"https://github.com/usail-hkust/benchmark_inference_time_computation_LLM/blob/HEAD/methods/method_utils/str_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9de1a71e6056d426"}},{"code_sha256_prefix":"083496535dc36c5d","entry":"request_gpt","repo":"usail-hkust/benchmark_inference_time_computation_LLM","repo_kind":"official","path":"models/reward_models/request_gpt.py","file_url":"https://github.com/usail-hkust/benchmark_inference_time_computation_LLM/blob/HEAD/models/reward_models/request_gpt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"083496535dc36c5d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}