{"paper":{"title":"Sampling Is Not Curiosity: Why LLM Agents Should Investigate","arxiv_id":"2611.10501","primary_cat":"cs.AI","submitted_at":"2026-11-07T06:02:37+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"LLM agents are increasingly used for open-ended tasks, very common in research scenarios where they are required to explore, investigate, or act curiously.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":false,"role":"background","text":"At inference time, an LLM is a fixed map from context to next-token distribution, the pretrained weights determine the function, and only its conditioning changes as context accumulates.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.92,"id":"s2","own":false,"role":"background","text":"Mechanisms like temperature, best-of-N, tree search, or RAG vary how the distribution is sampled or what it is conditioned on, but do not update the agent's model of the environment.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.11,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.05,"method":0.0,"result":0.01,"background":0.92,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":3,"p":0.34,"id":"s3","own":false,"role":"result","text":"We argue that current LLM agents do not explore curiously; they explore stochastically.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.39,"main_claim_p":0.76,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.21,"method":0.0,"result":0.34,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.14,"interpretation":0.3}},{"i":4,"p":0.86,"id":"s4","own":false,"role":"background","text":"From how curiosity is understood in the RL literature, it requires a predictive structure over how the environment responds to the agent's actions, which improves online from current interaction, drives action selection through its predicted improvement, and persists beyond the context window.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.03,"method":0.01,"result":0.0,"background":0.86,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.04}},{"i":5,"p":0.3,"id":"s5","own":false,"role":"contribution","text":"Additionally, in its open-ended form, the agent should intrinsically originate what to investigate.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.12,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.2,"method":0.04,"result":0.01,"background":0.26,"limitation":0.0,"future_work":0.0,"contribution":0.3,"interpretation":0.19}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"contribution","text":"Thus, we propose a framework defining curiosity in LLM agents, reserving the term for systems that satisfy it.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.88,"main_claim_p":0.34,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":7,"p":0.91,"id":"s7","own":true,"role":"future_work","text":"In doing so, we identify the research directions its implementation opens up.","hedge":{"p":0.75,"label":"asserted"},"own_p":0.74,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.91,"contribution":0.09,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.95,"text":"We argue that current LLM agents do not explore curiously; they explore stochastically.","location":"abstract s3","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6232,"cost_usd_reported":0.0},"compiled_at":"2026-11-10","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.16,"human_participants":0.04,"controlled_comparison":0.03,"randomized_assignment":0.01,"states_quantitative_result":0.02,"compares_with_prior_results":0.09,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":1.0,"value":"argument","probabilities":{"argument":1.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.0}},"contribution_type":{"p":1.0,"value":"position or commentary","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":1.0}},"contribution_statement":{"p":1.0,"text":"Thus, we propose a framework defining curiosity in LLM agents, reserving the term for systems that satisfy it.","location":"abstract s6"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":8,"sentences_in_abstract":8},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}