Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-19T23:26:15.658106Z
Paper Citation Record · LEDGER
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
As of 13 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2605.17453.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
50 of 50 outbound references displayed
- verified exact32
- verified fuzzy10
- unresolved5
- parse uncertain0
- malformed identifier1
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 95d54b84-5037-45e3-8a53-b04561ee007f · outbound
This paper cites Identifying the Risks of LM Agents with an LM-Emulated Sandbox.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.388844Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 355baa8a-bbaf-47e9-9df6-175720873aab · outbound
This paper cites Stabletoolbench: Towards stable large-scale benchmarking on tool learning of large language models.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Stabletoolbench: Towards stable large-scale benchmarking on tool learning of large language models
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.259922Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 8eddef7a-33df-4682-9d48-20aa3177e5a4 · outbound
This paper cites Toolsandbox: A stateful, conversational, inter- active evaluation benchmark for llm tool use capabilities.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Toolsandbox: A stateful, conversational, inter- active evaluation benchmark for llm tool use capabilities
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.203426Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 14ab0792-eb6d-4bea-84b0-4c1c487d8688 · outbound
This paper cites 10 Guoqing Ma, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Jiawei Shen, Zilong Li, and Yidan Liang.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback 10 Guoqing Ma, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Jiawei Shen, Zilong Li, and Yidan Liang
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-19T23:27:52.401137Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 7aefcc1d-0de4-4dc1-b02f-74d1aa71de71 · outbound
This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.235138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 63a3a162-0aa1-4310-b58d-80a4ad02de2e · outbound
This paper cites Benchmarking and defending against indirect prompt injection attacks on large language models.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Benchmarking and defending against indirect prompt injection attacks on large language models
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.249277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 1f0bcdfe-3175-49be-94c1-a37d22fb733e · outbound
This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.198732Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 7d17e26e-6f7f-49b5-9d46-1694c640d5b4 · outbound
This paper cites Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents.Advances in Neural Information Processing Systems, 37:82895–82920.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents.Advances in Neural Information Processing Systems, 37:82895–82920
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.194418Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 80704353-e5d1-47cb-8147-d0976cf8267d · outbound
This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.612366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation ed513a7c-7cfb-4e25-9757-4157bba206be · outbound
This paper cites MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.575901Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation aaafa9fe-ca11-44e7-985e-e74772f91982 · outbound
This paper cites Mcp-itp: An automated framework for implicit tool poisoning in mcp.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Mcp-itp: An automated framework for implicit tool poisoning in mcp
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.518906Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 3087fba8-ba75-4b63-a545-65577d239804 · outbound
This paper cites Invisible threats from model context protocol: Generating stealthy injection payload via tree-based adaptive search.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Invisible threats from model context protocol: Generating stealthy injection payload via tree-based adaptive search
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.362575Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9afcc3eb-cb16-4c68-b5b4-e35793513a7b · outbound
This paper cites Breaking the protocol: Security anal- ysis of the model context protocol specification and prompt in- jection vulnerabilities in tool-integrated llm agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Breaking the protocol: Security anal- ysis of the model context protocol specification and prompt in- jection vulnerabilities in tool-integrated llm agents
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.569716Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 1d808a55-40c1-449e-abeb-6fc8fe68b410 · outbound
This paper cites Impossiblebench: Measuring llms’ propensity of exploiting test cases.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Impossiblebench: Measuring llms’ propensity of exploiting test cases
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.555873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation e884a4a1-0691-4954-89df-c374c085161c · outbound
This paper cites Vijayvargiya, A.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Vijayvargiya, A
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-19T23:27:52.582830Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation dc2c3041-f898-4663-ab5f-ecbda63971a1 · outbound
This paper cites Redteamcua: Realistic adversarial testing of computer-use agents in hybrid web-os environments.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Redteamcua: Realistic adversarial testing of computer-use agents in hybrid web-os environments
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.509330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 8bc899a1-8672-45ab-ac97-643fb7e14acd · outbound
This paper cites Mcp-safetybench: A benchmark for safety evaluation of large language models with real-world mcp servers.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Mcp-safetybench: A benchmark for safety evaluation of large language models with real-world mcp servers
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.618593Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation b34d59e1-633c-4807-8385-346f4f346af6 · outbound
This paper cites Mcpmark: A benchmark for stress-testing realistic and comprehensive mcp use.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Mcpmark: A benchmark for stress-testing realistic and comprehensive mcp use
Reference 18
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.295788Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation c4da4341-e137-46bd-8579-f7bbfd3e9cc5 · outbound
This paper cites Redcodeagent: Automatic red-teaming agent against diverse code agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Redcodeagent: Automatic red-teaming agent against diverse code agents
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.279574Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation d0e23d28-498d-4a9e-89f2-8930fe8996a0 · outbound
This paper cites Bluecodeagent: A blue teaming agent enabled by automated red teaming for codegen ai.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Bluecodeagent: A blue teaming agent enabled by automated red teaming for codegen ai
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.589339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation bbf9b19c-2b5a-4519-a5ce-d8e515cfb8e0 · outbound
This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.374731Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation d12efa7c-1108-42fb-9a5f-7ed9959d32e8 · outbound
This paper cites Mistral 7B.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Mistral 7B
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.562355Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation baddb7e9-fe46-472c-bb43-f1efd6668c3c · outbound
This paper cites Qwen3 Technical Report.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Qwen3 Technical Report
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.307058Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 4597fe2c-74ce-4086-8ab5-1d9430571721 · outbound
This paper cites Qwen2 Technical Report.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Qwen2 Technical Report
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.485115Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation e120a031-aa69-4e49-823c-63edaabde9fe · outbound
This paper cites 2 OLMo 2 Furious.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback 2 OLMo 2 Furious
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.473349Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 113fdabe-15fa-402d-b958-56fe8c8ae020 · outbound
This paper cites The Llama 3 Herd of Models.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback The Llama 3 Herd of Models
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.315839Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation ab64cf79-a2b9-4294-b1c7-94c2086bfbec · outbound
This paper cites Cwm: An open-weights llm for research on code generation with world models.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Cwm: An open-weights llm for research on code generation with world models
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.422287Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 8ac61058-bdd4-46c4-8c69-0cf78a278a75 · outbound
This paper cites Evaluating Privilege Usage of Agents with Real-World Tools.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Evaluating Privilege Usage of Agents with Real-World Tools
Reference 28
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.450166Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation ab467022-1356-45bb-a775-279454e2d493 · outbound
This paper cites Mcpshield: A security cognition layer for adaptive trust calibration in model context protocol agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Mcpshield: A security cognition layer for adaptive trust calibration in model context protocol agents
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.411639Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 485a45cd-f748-422b-ad6a-993cf9f4f59f · outbound
This paper cites The task shield: Enforcing task alignment to defend against indirect prompt injection in llm agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback The task shield: Enforcing task alignment to defend against indirect prompt injection in llm agents
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.244909Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 47acb930-00d5-4610-b6f8-40b5bd42ced8 · outbound
This paper cites Defeating Prompt Injections by Design.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Defeating Prompt Injections by Design
Reference 31
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.462500Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 2db7019a-4e71-4607-87ba-bd12422f5275 · outbound
This paper cites Toolsafe: Enhancing tool invocation safety of llm-based agents via proactive step-level guardrail and feedback.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Toolsafe: Enhancing tool invocation safety of llm-based agents via proactive step-level guardrail and feedback
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.438570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 2605665c-f537-4653-8067-666bff20e950 · outbound
This paper cites Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-06-12T02:08:25.633841Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation c750350c-d39e-4407-b490-a5cb9c00f92b · outbound
This paper cites Agentsentry: Mitigating indirect prompt injection in llm agents via temporal causal diagnostics and context purification.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Agentsentry: Mitigating indirect prompt injection in llm agents via temporal causal diagnostics and context purification
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.290598Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 4f2b9ce9-fa27-4d44-a7ac-6625eb5e5805 · outbound
This paper cites Commandsans: Securing ai agents with surgical precision prompt sanitization.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Commandsans: Securing ai agents with surgical precision prompt sanitization
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.348681Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 49b01948-34e7-4e35-aa04-69b3806416b6 · outbound
This paper cites AgentWatcher: A Rule-based Prompt Injection Monitor.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback AgentWatcher: A Rule-based Prompt Injection Monitor
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-07-28T02:22:29.738998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation b47adc32-c21f-42ba-974b-b6c0116eaa03 · outbound
This paper cites Agentsys: Secure and dynamic llm agents through explicit hierarchical memory management.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Agentsys: Secure and dynamic llm agents through explicit hierarchical memory management
Reference 37
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.300973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 6a8e7267-cf47-44be-b914-0f8d010ee7d7 · outbound
This paper cites BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-08-13T01:24:45.972029Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 395601be-1313-4331-a841-dddd7408b4f5 · outbound
This paper cites Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
Reference 39
- Resolution
- verified exact
- arxiv_id, observed 2026-06-04T02:07:11.549850Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation e99f00df-581c-48a3-ad27-c9efc5fd36cf · outbound
This paper cites Edward Suh.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Edward Suh
Reference 40
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T23:27:52.284887Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 3ca4c3cd-6b4d-45fd-94ef-b44b234b9aba · outbound
This paper cites SoK: The Attack Surface of Agentic AI - Tools and Autonomy.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback SoK: The Attack Surface of Agentic AI - Tools and Autonomy
Reference 41
- Resolution
- verified exact
- arxiv_id, observed 2026-08-12T02:24:10.274858Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9138402e-3948-4430-ae39-5ed1ba241556 · outbound
This paper cites Reason- ing with language model is planning with world model.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Reason- ing with language model is planning with world model
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.239852Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9eaed837-5b33-4ae1-8118-a0190b221603 · outbound
This paper cites an unresolved cited work.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T23:27:53.255357Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 172cedb8-1493-4c07-8a6b-a566e4530e00 · outbound
This paper cites Generating code world models with large language models guided by monte carlo tree search.Advances in Neural Information Processing Systems, 37:60429–60474.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Generating code world models with large language models guided by monte carlo tree search.Advances in Neural Information Processing Systems, 37:60429–60474
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.264280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation a9d17490-85cc-405b-90f8-5ee468dc51da · outbound
This paper cites an unresolved cited work.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Unresolved cited work
Reference 45
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T23:27:53.230454Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation cf620e62-8db7-44e6-84bc-7899961a0847 · outbound
This paper cites an unresolved cited work.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Unresolved cited work
Reference 46
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T23:27:53.222440Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation cf33150b-eabe-4ae3-9bf6-0b4104266d9d · outbound
This paper cites an unresolved cited work.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Unresolved cited work
Reference 47
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T23:27:53.213645Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 655e397f-3065-4b06-9f66-7f5b34b3c842 · outbound
This paper cites Candidate episodes produced by this process are retained only after a two-person audit.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Candidate episodes produced by this process are retained only after a two-person audit
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T23:27:53.218048Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 520986dc-8774-4187-bd44-2564d5667bda · outbound
This paper cites an unresolved cited work.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Unresolved cited work
Reference 49
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T23:27:53.207495Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 0e819038-85c6-4445-b77e-500192575604 · outbound
This paper cites trajectory_digest.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback trajectory_digest
Reference 50
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-19T23:27:53.226462Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Pith citing papers
No inbound Pith citation observations are available.